# Financial Intelligence
Source: https://docs.getpg.ai/account/financial-intelligence
Share price, financials, key metrics, competitor benchmarking, and analyst forecasts for public companies
Financial Intelligence provides share price, revenue, key financial metrics, competitor benchmarking, and analyst forecasts. Understand a company's financial health and competitive position without opening a Bloomberg terminal.
Data refreshes automatically as financial reporting periods pass and new data becomes available. Available for public companies.
## What This Module Does
Financial data for public companies is technically available, but it's locked behind terminals, filings, and analyst reports that most sales teams never access. Financial Intelligence surfaces the key metrics you need for deal qualification, pricing conversations, and executive meetings - in one place.
A rep walking into a CFO meeting needs to know the company's revenue trajectory, margin pressures, and competitive standing. Financial Intelligence gets you executive-ready in minutes.
## Key Capabilities
Interactive share price chart with multiple time ranges (1D, 1W, 1M, 6M, 1Y, 5Y, All). Market cap, sector, industry, and exchange information
Revenue, EBITDA, EBIT, net income, SG\&A, earnings per share. Income statement, balance sheet, and cash flow views. Annual and quarterly toggles. Analyst forecast data
Automatically identified competitors with domain, public company status, stock ticker, exchange, and market cap
Side-by-side comparison of your account against competitors across key metrics like market cap and revenue, displayed as horizontal bar charts
## How to Use It
**Executive meetings:** Walk into a CFO meeting knowing the company's revenue, margins, and competitive standing. No manual financial research.
**Deal qualification:** Financial health indicates buying capacity and urgency. A company with strong revenue growth and margin pressure tells a different story than one in decline.
**Competitive context:** Understand who the company competes with and where it stands. Reference competitive dynamics in conversations.
**Speak the language:** Financial data lets you engage credibly with finance-oriented buyers. "I noticed your SG\&A has been increasing as you scale internationally" opens a different conversation than "tell me about your challenges."
## Related Modules
Financial data adds quantitative depth to strategic priorities and goals
Financial context enriches value propositions and discovery questions
Technology investments have financial implications; linking the two adds depth
# Jobs & Hiring Signals
Source: https://docs.getpg.ai/account/hiring-jobs
What a company is hiring for, where roles are located, and what hiring patterns reveal about priorities and investment
Jobs & Hiring Signals shows what a company is hiring for, where roles are located, and what hiring patterns reveal about its priorities, investments, and growth trajectory.
Job data enriches continuously as new postings appear across sources. Historical data is retained so you can see hiring trends over time.
## What This Module Does
Hiring is one of the strongest signals of what a company is doing next. A company building out a cloud engineering team is investing in cloud infrastructure. A company hiring its first Chief Data Officer is signalling a data transformation. A surge in sales hiring means growth mode.
PG:AI aggregates job postings across multiple sources for every account - careers pages, job boards, aggregators - so you don't have to check each one manually. You get a unified view of hiring activity across your entire portfolio.
Set up saved job searches for specific role types (e.g. "data engineer" or "VP Sales") to track how hiring for those roles changes over time across your accounts.
## Key Capabilities
Latest postings with job title, location, date posted, and source. Quick view of what's new and whether a company has been actively hiring
Full, filterable table of all job postings. Filter by role type, location, seniority, or keyword to dig deeper into hiring patterns
Persistent searches for specific role types. Track how hiring for those roles changes over time across your accounts
Job postings linked to technology detection. Hiring volume and velocity as account-level signals. Location data reveals geographic expansion or consolidation
## How to Use It
**Buying signal:** A company hiring for roles related to your product category is a strong indicator of investment and need. Spot it early.
**Account qualification:** A company hiring 50 data engineers is a different conversation than one hiring none. Hiring data adds a dimension that firmographics miss.
**Personalise outreach:** "I noticed you're building out a cloud platform team" opens a conversation that a generic email never would.
**Trend tracking:** Use saved searches to monitor specific role types across your portfolio. See which accounts are ramping up and which are slowing down.
## Related Modules
Job postings are a primary source for technology detection
Hiring patterns often reflect strategic priorities
Job postings reveal organisational structure and team composition
# Contacts & Org Chart
Source: https://docs.getpg.ai/account/org-chart
People discovery, contact profiles, career history, persona matching, and visual org chart with relationship mapping
Contacts & Org Chart helps you discover the right people at an account, understand how they relate to each other, and map the organisational structure. Contact profiles, career history, persona matching, and a visual org chart learned from data.
Contact data enriches from multiple sources: LinkedIn profiles, company directories, email enrichment services, and phone number providers. Data refreshes continuously.
## What This Module Does
Finding the right contacts at a target account is one of the most time-consuming parts of sales. Reps search LinkedIn, cross-reference company directories, and piece together who reports to whom. For large enterprises, the organisational structure is opaque.
Contacts & Org Chart gives you three views: a master contacts table, a visual interactive org chart, and a discovery engine for finding new contacts. The org chart is learned from data - job postings, contact enrichment, entity extraction - not a static database.
Use persona-based search to find decision-makers in seconds. Recommended personas like "CRO & CMO", "Sales Leaders", and "RevOps & Enablement" provide one-click access to common searches.
## Key Capabilities
Master list of all known contacts with sortable columns: name, title, headline, persona, department, location. Filter by department, seniority, persona, or location
Visual, interactive map with six relationship types (reports to, indirect, manages, peer, collaborates, related) and four node types (Division, Department, Team, Contact). Three layout modes: Hierarchy, Teams, Network
Persona-based discovery with recommended personas and free-text search. Discover new contacts not yet in your database
Contact details, career history with previous roles and companies, persona assignment, relevance graph showing topic relationships. Email and phone enrichment on demand
## How to Use It
**Find the right people:** Persona-based discovery and free-text search replace manual LinkedIn browsing. Find decision-makers in seconds, not hours.
**See the organisation:** The org chart reveals reporting lines, team structures, and relationships that a flat contact list never shows. Understand who influences whom.
**Build multi-threaded deals:** Visualise your contact coverage and identify gaps. See which departments and seniority levels you've reached and where you need more contacts.
**Enrich on demand:** Use "Get Email" and "Get Phone Number" to enrich contacts when you need to reach them.
## Related Modules
Contact context enriches Value Pyramids and Discovery Questions with persona-specific angles
Job postings reveal team composition and new hires that may not yet appear in the contacts table
Division intelligence helps you target the right part of a large organisation with the right contacts
# PG:AI Account
Source: https://docs.getpg.ai/account/overview
Deep account intelligence for every company in your pipeline
PG:AI Account gives you deep account and contact intelligence for every company in your pipeline. Everything you need to know about an account, the people inside it, and how to engage them - in one place.
Intelligence data refreshes automatically. When a company posts new jobs, publishes earnings, or shifts strategy, the profile updates so you always have the latest view.
## Account Modules
Strategic priorities, goals, SWOT analysis, division intelligence, and industry overview for every account
Which technologies a company uses, how they trend in job postings, and which ones are gaining or losing traction
What a company is hiring for, where roles are located, and what hiring patterns reveal about priorities and investment
Share price, financials, key metrics, competitor benchmarking, and analyst forecasts for public companies
People discovery, contact profiles, career history, persona matching, and visual org chart with relationship mapping
Value Pyramid, Three Whys, Custom Insights, Discovery Questions, and Facts and Figures - turn intelligence into meeting preparation
## Key Benefits
Account profile, contacts, financials, tech stack, hiring signals, and strategic insights in a single view. No more ten-tab research sessions.
Continuous enrichment means data refreshes automatically. When a company posts new jobs, publishes earnings, or shifts strategy, the profile updates.
Go beyond employee count and revenue. Understand what a company is investing in, who its competitors are, what its divisions focus on, and which roles it's hiring for.
The Sales Engagement module turns raw intelligence into meeting preparation: discovery questions, value pyramids, and tailored insight reports.
Every rep sees the same intelligence. Research done by one person benefits the entire team. No more duplicated effort or lost context.
Intelligence data flows into Territory scoring, Agent conversations, and Monitor alerts. It's the data foundation for everything else in PG:AI.
## Who It's For
Account executives, strategic account managers, and business development reps - the people who research accounts, prepare for meetings, and need to understand a company before they pick up the phone.
Sales leaders who need visibility into account quality and rep preparedness. RevOps teams who want richer data flowing into territories and scoring models. Marketing teams who need account-level context for ABM campaigns and personalised outreach.
## How It Connects to Other Products
Consumes Intelligence data for territory scoring, account ranking, and planning
The agent uses Intelligence as context for conversations, research, content generation, and Canvas documents
Monitors Intelligence accounts for changes and triggers alerts when something shifts
Account management (adding, importing, organising companies) lives at the Workspace level and feeds into Intelligence
# Sales Engagement
Source: https://docs.getpg.ai/account/sales-engagement
Value pyramids, discovery questions, custom insight reports, and facts and figures tailored to every account
Sales Engagement turns account intelligence into meeting preparation. Value pyramids, discovery questions, custom insight reports, and facts and figures tailored to every account - so reps walk into meetings ready.
All content is generated from the account's intelligence profile and updates as the underlying data changes. Nothing is boilerplate.
## What This Module Does
Reps have access to more account data than ever, but data is not preparation. Knowing a company's revenue, tech stack, and org chart is useful, but it doesn't tell you what questions to ask, what value to lead with, or which angles will resonate with this specific account.
Sales Engagement bridges the gap between "I have information about this company" and "I'm prepared for this meeting." It takes the intelligence PG:AI has gathered and structures it into five preparation tools.
Define Custom Insight topics for your organisation once - e.g. "Sales Team Operational Efficiency", "Revenue Strategies", "New Product Launches" - and get account-specific analysis for every account. Scale your sales narrative across the portfolio.
## Key Capabilities
Breaks down the company's vision, strategies, initiatives, and challenges into a structured hierarchy. Top-down view of what the company is trying to achieve and what's getting in the way
Three evidence-based reasons why the company should care about what you offer. Each "why" is grounded in evidence from the account's data. Ready-to-use conversation openers
User-defined insight topics. Each topic generates an AI-written analysis specific to the account, with supporting evidence, related facts, and source references
Topic-based questions tailored to the account, grouped by category. Each question references what PG:AI knows about the company - informed, not generic
Key quantitative data points: financial metrics, growth rates, market position. Useful for conversations, proposals, and presentations
## How to Use It
**First meetings:** Present the value pyramid to show strategic understanding. Use discovery questions to guide productive conversations. Reference specific facts to build credibility.
**Executive briefings:** Start with strategic priorities to align with C-level thinking. Use Three Whys to build a compelling change narrative. Include quantified business impact using their metrics.
**Proposals:** Embed the value pyramid as proof of solution alignment. Structure sections around the Three Whys framework. Support recommendations with their stated facts and figures.
**Outreach:** Use Custom Insights to personalise messaging. "Based on your focus on sales team operational efficiency..." is more compelling than generic outreach.
## Related Modules
Provides the strategic priorities, goals, SWOT, and division intelligence that feeds into engagement tools
Financial data appears in Facts and Figures and enriches Discovery Questions
Persona context helps target engagement preparation to the right stakeholders
Technology data enriches Custom Insights and Discovery Questions with operational context
# Strategic Insights
Source: https://docs.getpg.ai/account/strategic-insights
Strategic priorities, goals, SWOT analysis, division intelligence, and industry context for every account
Strategic Insights helps you understand what a company is prioritising, where it's headed, and what makes it tick. Strategic priorities, goals, SWOT analysis, division intelligence, and industry context - all generated and kept current from public sources.
All intelligence refreshes automatically as new public information becomes available. Every insight links back to its source so you can verify claims and reference specific data points in conversations.
## What This Module Does
PG:AI analyses public sources - earnings calls, filings, press releases, analyst reports, and news - and generates structured intelligence for every account. Instead of spending an hour reading transcripts and reports, you get a ready-made view of what the company cares about and where it's investing.
For large enterprises with multiple business units, division intelligence helps you target the right part of the organisation. See which division aligns best with what you sell.
## Key Capabilities
Top focus areas with summaries, sources, and relative importance - e.g. "Agentic AI Platform Leadership" or "Strategic Industry and Global Expansion"
Measurable targets extracted from earnings calls and filings: revenue goals, margin targets, market expansion milestones, product adoption metrics
Strengths, weaknesses, opportunities, and threats as structured cards with detailed explanations and supporting evidence
Business unit mapping with summaries, priorities, challenges, digital strategies, and relevance graphs showing how divisions connect to topics
Market context: industry size, growth rate, strategic priorities radar chart, and industry-level insights and trends
## How to Use It
**Before meetings:** Open the account and scan Strategic Priorities and Goals. You'll know what the company is focused on before you walk in the room.
**For large accounts:** Use Division Intelligence to identify which business unit to target. Stop targeting the wrong part of the organisation.
**For executive conversations:** Reference SWOT items and Goals with evidence. "I noticed in your last earnings call you mentioned..." builds credibility.
**For market context:** Check Industry Overview to understand the forces shaping your account. Know what the industry is prioritising before you pitch.
## Related Modules
Uses strategic insights as input for Value Pyramids, Discovery Questions, and Custom Insights
Technology signals complement strategic insights with operational detail
Financial data adds quantitative depth to strategic context
# Tech Stack Intelligence
Source: https://docs.getpg.ai/account/technology-intelligence
Which technologies a company uses, how they trend in job postings, and which ones are gaining or losing traction
Tech Stack Intelligence shows which technologies a company uses, how frequently they appear in job postings, and which ones are gaining or losing traction. Understand a company's technology landscape without asking.
![Tech Stack Intelligence on the company overview]()
Technology data enriches continuously. As new job postings appear and sources update, the technology profile reflects the company's current state.
## What This Module Does
PG:AI builds a technology profile for every account by analysing job postings, public sources, and enrichment data. Instead of manually checking company websites and job boards, you get a structured view of what technologies the company is investing in - including internal tools that don't appear on their website.
Set favourite technologies at the organisation level to track what matters to your business. You'll see job mention counts and last-mentioned dates for each favourite across all accounts.
## Key Capabilities
Technologies you've told PG:AI to track. See job mention counts and last-mentioned dates for each - your at-a-glance view of whether a company is investing in technologies relevant to your sale
Full breakdown of all technologies detected across job postings, displayed as a donut chart ranked by frequency. Reveals the company's overall technology landscape
Technologies referenced recently with recency indicators (High, Medium, Low). Spot emerging trends - a technology suddenly appearing in many job postings signals a new investment
Captures internal technology use from job postings, not just web-facing tools. BuiltWith catches websites; Tech Stack catches what they're building with
## How to Use It
**Account qualification:** Instantly see whether a company uses your product's competitors, complements, or prerequisites. No manual research needed.
**Personalise outreach:** Reference specific technologies in outreach. "I noticed ServiceNow has been increasing its investment in Python and React" is more compelling than a generic message.
**Spot investment signals:** A technology suddenly appearing in many job postings signals a new initiative. Catch it early.
**Solution engineering:** Before a demo, understand the company's tech environment. Know what they're already using so you can position integrations and migrations.
## Related Modules
Job postings are a primary source for technology detection
Technology investments often align with strategic priorities
Technology context enriches discovery questions and value propositions
# Search for accounts
Source: https://docs.getpg.ai/api-reference/accounts/search-for-accounts
/openapi.json post /accounts
Search for accounts using various filters. No search filters required - empty body returns all results.
# Create workspace agent session
Source: https://docs.getpg.ai/api-reference/agent/create-workspace-agent-session
/openapi.json post /agent/sessions
Create a new agent session.
# List workspace agent sessions
Source: https://docs.getpg.ai/api-reference/agent/list-workspace-agent-sessions
/openapi.json get /agent/sessions
List agent sessions for the workspace (user-scoped server-side).
# List alerts (workspace)
Source: https://docs.getpg.ai/api-reference/alerts/list-alerts-workspace
/openapi.json get /alerts
Paginated alerts with optional status, type, and time filters.
# Update alert status
Source: https://docs.getpg.ai/api-reference/alerts/update-alert-status
/openapi.json patch /alerts/{alert_id}
Transition an alert to viewed, acknowledged, resolved, or dismissed.
# List canvas templates
Source: https://docs.getpg.ai/api-reference/canvas/list-canvas-templates
/openapi.json get /canvas/templates
Catalog of org and PG:AI canvas templates (content settings + reference templates). Filter by category, output type, or search query.
# List canvases (workspace)
Source: https://docs.getpg.ai/api-reference/canvas/list-canvases-workspace
/openapi.json get /canvas
Paginated list of canvas records for the organisation. Supports filters such as company_ids, contact_id, content_type, and date ranges.
# Add a company (async enrichment)
Source: https://docs.getpg.ai/api-reference/companies/add-a-company-async-enrichment
/openapi.json post /companies
Submit a single company for discovery and enrichment. Returns 202 with a public_operation_id for polling via GET /operations/{public_operation_id}. Requires company_name, domain, or id.
# Get company by ID
Source: https://docs.getpg.ai/api-reference/companies/get-company-by-id
/openapi.json get /companies/{company_id}
Retrieve detailed information about a specific company. Requires "insights:read" permission.
# Get company relevance
Source: https://docs.getpg.ai/api-reference/companies/get-company-relevance
/openapi.json get /companies/{company_id}/relevance
Ranked relevance signals for a single company — recent material changes, leadership moves, funding, product launches, hiring trends, technology mentions and strategic shifts — drawn from PG:AI insights, public filings and news, web pages, jobs and technologies. By default uses a material-changes query; pass `q` to override. Returns `{ items, total, page, per_page }`. `GET /companies/{company_id}/graph` is a legacy alias for this endpoint.
# Get company relevance graph
Source: https://docs.getpg.ai/api-reference/companies/get-company-relevance-graph
/openapi.json get /companies/{company_id}/graph
Ranked relevance signals for a single company — recent material changes, leadership moves, funding, product launches, hiring trends, technology mentions and strategic shifts — drawn from PG:AI insights, public filings and news, web pages, jobs and technologies. Identical behaviour to `GET /companies/{company_id}/relevance`; this alias is retained for legacy clients. Returns `{ items, total, page, per_page }`.
# Get customizable company profile
Source: https://docs.getpg.ai/api-reference/companies/get-customizable-company-profile
/openapi.json get /companies/{company_id}/profile
Retrieve a company profile, choosing which sections to return. Use `include` (comma-separated) to request specific sections — pass `full` to return everything. Use `exclude` (comma-separated) to drop sections from the response. Set `sources=true` to receive source citations alongside the profile content.
# List agent sessions for a company
Source: https://docs.getpg.ai/api-reference/companies/list-agent-sessions-for-a-company
/openapi.json get /companies/{company_id}/agent/sessions
Retrieve agent sessions scoped to a company.
# List alerts for a company
Source: https://docs.getpg.ai/api-reference/companies/list-alerts-for-a-company
/openapi.json get /companies/{company_id}/alerts
Alerts filtered to the given company.
# List canvases for a company
Source: https://docs.getpg.ai/api-reference/companies/list-canvases-for-a-company
/openapi.json get /companies/{company_id}/canvas
Same as GET /canvas but scoped to a single company_id path parameter.
# List job postings for a company
Source: https://docs.getpg.ai/api-reference/companies/list-job-postings-for-a-company
/openapi.json get /companies/{company_id}/jobs
Job postings scoped to a company. Supports ?live=true for refresh.
# List monitoring events for a company
Source: https://docs.getpg.ai/api-reference/companies/list-monitoring-events-for-a-company
/openapi.json get /companies/{company_id}/events
Same as GET /events scoped to one company.
# Search company contacts
Source: https://docs.getpg.ai/api-reference/companies/search-company-contacts
/openapi.json post /companies/{company_id}/contacts
Search and retrieve contacts associated with a specific company. Supports filtering by name, job title, location, and LinkedIn URL.
# Search contacts for a company
Source: https://docs.getpg.ai/api-reference/companies/search-contacts-for-a-company
/openapi.json post /companies/{company_id}/contacts/search
Per-company contact search. Append ?live=true to force a live refresh (returns 202 when async).
# Enrich contact (phone/email)
Source: https://docs.getpg.ai/api-reference/contacts/enrich-contact-phoneemail
/openapi.json post /contacts/{contact_id}/enrich/contact_info
Queue Airscale-style contact info enrichment. Returns 202 when accepted.
# List contacts
Source: https://docs.getpg.ai/api-reference/contacts/list-contacts
/openapi.json get /contacts
Retrieve a list of contacts with pagination.
# Search contacts (workspace)
Source: https://docs.getpg.ai/api-reference/contacts/search-contacts-workspace
/openapi.json post /contacts/search
Cached workspace-wide contact search. Optional JSON filters in body; ?live=true is not supported on this route.
# List monitoring events (workspace)
Source: https://docs.getpg.ai/api-reference/events/list-monitoring-events-workspace
/openapi.json get /events
Timeline of monitoring events with optional filters for type, source, time range, and pagination.
# Get filter metadata
Source: https://docs.getpg.ai/api-reference/filters/get-filter-metadata
/openapi.json get /filters
Returns filter definitions for the requested entity type (accounts, contacts, content, or jobs).
# List job postings (workspace)
Source: https://docs.getpg.ai/api-reference/jobs/list-job-postings-workspace
/openapi.json get /jobs
Employment listings with filters. ?live=true is not supported without a company scope.
# Poll async operation status
Source: https://docs.getpg.ai/api-reference/operations/poll-async-operation-status
/openapi.json get /operations/{public_operation_id}
Poll enrichment or bulk jobs using the public_operation_id (op_*) returned from async POST endpoints.
# Get organization credits
Source: https://docs.getpg.ai/api-reference/organization/get-organization-credits
/openapi.json get /organization/credits
Retrieve credit information for the authenticated organization.
# Unified semantic search
Source: https://docs.getpg.ai/api-reference/search/unified-semantic-search
/openapi.json get /search
Semantic search across the data PG:AI holds for your accounts — public filings and news, your uploaded materials, web pages, jobs, technologies, contacts, conversations, insights and more. Use `scope=organisation` to search every account tracked for your workspace, or `scope=companies` to restrict to a comma-separated list of `company_ids`. Returns a ranked `{ items, total, page, per_page }` envelope (organisation scope additionally includes `resolved_company_count`).
# Get territory by ID
Source: https://docs.getpg.ai/api-reference/territories/get-territory-by-id
/openapi.json get /territories/{territory_id}
Retrieve detailed information about a specific territory.
# List territories
Source: https://docs.getpg.ai/api-reference/territories/list-territories
/openapi.json get /territories
Retrieve a paginated list of territories for the authenticated organization.
# Authentication
Source: https://docs.getpg.ai/api/authentication
Authenticate with the PG:AI API using API keys
All API requests (except `/health`) require authentication via an API key passed in the `x-api-key` request header.
## Getting Your API Key
Go to **Settings > API Keys** in your PG:AI workspace.
Click **Generate API Key**, give it a descriptive name, and select the permission scopes it should have.
Copy the key immediately — it won't be shown again. Store it in environment variables or a secrets manager.
## Using Your API Key
Include the API key in the `x-api-key` header on every request:
```bash cURL theme={null}
curl -X GET "https://api.getpg.ai/public-api/v1/territories" \
-H "x-api-key: your_api_key" \
-H "Content-Type: application/json"
```
```python Python theme={null}
import requests
headers = {
"x-api-key": "your_api_key",
"Content-Type": "application/json"
}
response = requests.get(
"https://api.getpg.ai/public-api/v1/territories",
headers=headers
)
data = response.json()
```
```javascript JavaScript theme={null}
const response = await fetch("https://api.getpg.ai/public-api/v1/territories", {
method: "GET",
headers: {
"x-api-key": "your_api_key",
"Content-Type": "application/json"
}
});
const data = await response.json();
```
Never expose your API key in client-side code, public repositories, or browser requests. Always keep it server-side.
## Base URL
All API endpoints use the following base URL:
```
https://api.getpg.ai/public-api/v1
```
## Permissions & Scopes
API keys are scoped with granular permissions. Each endpoint requires a specific permission — requests made with a key that lacks the required scope will receive a `403 Forbidden` response.
| Scope | Description |
| ------------------- | ------------------------------------------------------------- |
| `accounts:read` | Search and list accounts |
| `companies:read` | Read company data (relevance, graph, search, jobs, canvas) |
| `contacts:read` | Read contact data |
| `contacts:write` | Create or enrich contacts |
| `insights:read` | Read company intelligence, profiles, alerts, and technologies |
| `insights:write` | Create or modify company enrichment data |
| `integrations:read` | Read integration status |
| `jobs:read` | Read job postings |
| `monitoring:read` | Read monitoring events |
| `monitoring:write` | Manage monitoring events |
| `org_settings:read` | Read organization settings and credits |
| `sequences:read` | Read sequences and templates |
| `sequences:write` | Create or modify sequences |
| `tasks:read` | Read tasks |
| `tasks:write` | Create or modify tasks |
| `territories:read` | Read territories and their companies |
| `workflows:read` | Read workflows |
| `workflows:execute` | Trigger workflow executions |
| `*` | Full access (all permissions) |
Wildcard scopes are also supported. For example, `insights:*` grants both `insights:read` and `insights:write`.
## Rate Limits
API requests are rate-limited based on your plan. If you exceed the limit, the API returns a `429 Too Many Requests` response.
| Header | Description |
| ----------------------- | ----------------------------------------- |
| `X-RateLimit-Limit` | Maximum requests allowed per window |
| `X-RateLimit-Remaining` | Requests remaining in current window |
| `X-RateLimit-Reset` | Unix timestamp when the rate limit resets |
If you're hitting rate limits, consider batching requests or adding short delays between calls.
## Error Responses
All error responses follow a consistent structured format. Every error includes a `type`, a machine-readable `code`, and a human-readable `message`. Some errors include a `details` object with additional context.
```json theme={null}
{
"error": {
"type": "validation_error",
"code": "invalid_uuid",
"message": "Not a valid UUID.",
"details": {}
}
}
```
All responses (including errors) include an `X-Request-Id` header you can use when contacting support to identify the specific request.
| Status Code | Description |
| ----------- | ---------------------------------------------------------------------------------- |
| `400` | Bad Request — invalid parameters or missing required fields |
| `401` | Unauthorized — missing or invalid API key |
| `402` | Insufficient Credits — your organization has run out of credits for this operation |
| `403` | Forbidden — API key lacks the required permission scope |
| `404` | Not Found — the requested resource does not exist |
| `429` | Rate Limited — too many requests, slow down and retry |
| `500` | Internal Server Error — something went wrong on our end |
| `503` | Service Unavailable — a downstream service is temporarily unreachable |
# Common Flows
Source: https://docs.getpg.ai/api/common-flows
End-to-end workflow guides for common PG:AI API integrations
This page walks through common end-to-end workflows with the PG:AI API. Each flow includes the full sequence of API calls with examples. For request parameters and response schemas, see the endpoint pages below in the **API** tab sidebar.
## Setup
Set your API key before running any example:
```bash theme={null}
export PGAI_API_KEY="pgai_live_your_key_here"
export PGAI_BASE="https://api.getpg.ai/public-api/v1"
```
Generate keys in **Settings → API Keys** in your PG:AI workspace.
***
## First request: search accounts
The simplest integration check — authenticate and list accounts in your workspace.
```bash theme={null}
curl -X POST "$PGAI_BASE/accounts" \
-H "x-api-key: $PGAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"per_page": 10}'
```
Response (200):
```json theme={null}
[
{
"id": "0472a8a1-bdc4-4f53-93f6-7d9a967beb76",
"company_name": "Example Corp",
"website_domain": "example.com"
}
]
```
Send an empty body `{}` to return all accounts (paginated).
***
## Add a company and wait for enrichment
Adding a company is **async**. You receive a `public_operation_id` and poll until enrichment completes.
### Step 1: Submit the company
```bash theme={null}
curl -X POST "$PGAI_BASE/companies" \
-H "x-api-key: $PGAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"company_name": "Acme Corporation",
"domain": "acme.com"
}'
```
Response (202):
```json theme={null}
{
"public_operation_id": "op_abc123",
"status": "queued"
}
```
Provide at least one of `company_name`, `domain`, or `id` (existing PG:AI company UUID).
### Step 2: Poll operation status
```bash theme={null}
curl "$PGAI_BASE/operations/op_abc123" \
-H "x-api-key: $PGAI_API_KEY"
```
Poll until `status` is `completed` or `failed`. Typical intervals: 2–5 seconds.
### Step 3: Read the enriched profile
Once complete, the operation result includes the company id (or use the id you already had):
```bash theme={null}
curl "$PGAI_BASE/companies/{company_id}/profile" \
-H "x-api-key: $PGAI_API_KEY"
```
### Full Python example
```python theme={null}
import os
import time
import requests
API_KEY = os.environ["PGAI_API_KEY"]
BASE = os.environ.get("PGAI_BASE", "https://api.getpg.ai/public-api/v1")
HEADERS = {"x-api-key": API_KEY, "Content-Type": "application/json"}
# 1. Add company
add = requests.post(
f"{BASE}/companies",
headers=HEADERS,
json={"company_name": "Acme Corporation", "domain": "acme.com"},
)
add.raise_for_status()
op_id = add.json()["public_operation_id"]
print(f"Operation: {op_id}")
# 2. Poll until done
while True:
op = requests.get(f"{BASE}/operations/{op_id}", headers=HEADERS).json()
status = op.get("status")
print(f"Status: {status}")
if status in ("completed", "failed"):
break
time.sleep(3)
if status == "failed":
raise SystemExit(f"Enrichment failed: {op}")
company_id = op.get("result", {}).get("company_id") or op.get("company_id")
if not company_id:
raise SystemExit("No company_id in operation result")
# 3. Fetch profile
profile = requests.get(
f"{BASE}/companies/{company_id}/profile",
headers={"x-api-key": API_KEY},
).json()
print(f"Profile ready for {profile.get('company_name', company_id)}")
```
***
## Research an account
Combine account search, semantic search, and profile data for a research pipeline.
### Step 1: Find the company
```bash theme={null}
curl -X POST "$PGAI_BASE/accounts" \
-H "x-api-key: $PGAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"company_name": "Acme"}'
```
### Step 2: Unified search across your workspace
```bash theme={null}
curl "$PGAI_BASE/search?q=cloud%20migration&per_page=10" \
-H "x-api-key: $PGAI_API_KEY"
```
### Step 3: Company profile and relevance
```bash theme={null}
curl "$PGAI_BASE/companies/{company_id}/profile" \
-H "x-api-key: $PGAI_API_KEY"
curl "$PGAI_BASE/companies/{company_id}/relevance" \
-H "x-api-key: $PGAI_API_KEY"
```
Use `GET /filters` to discover filter metadata available for your workspace before building search UIs.
***
## Find and enrich contacts
### Step 1: Search contacts
```bash theme={null}
curl -X POST "$PGAI_BASE/contacts/search" \
-H "x-api-key: $PGAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "VP Sales",
"per_page": 10
}'
```
### Step 2: Enrich email or phone
```bash theme={null}
curl -X POST "$PGAI_BASE/contacts/{contact_id}/enrich/contact_info" \
-H "x-api-key: $PGAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'
```
Enrichment may be async — check the response for an operation id and poll `GET /operations/{public_operation_id}` if needed.
***
## List canvases for a company
Use the workspace canvas list with a `company_ids` filter. This is the canonical pattern — prefer it over company-scoped list paths.
```bash theme={null}
curl "$PGAI_BASE/canvas?company_ids=%5B%22{company_id}%22%5D&per_page=25" \
-H "x-api-key: $PGAI_API_KEY"
```
Or pass the filter in a clearer form:
```bash theme={null}
curl -G "$PGAI_BASE/canvas" \
-H "x-api-key: $PGAI_API_KEY" \
--data-urlencode "company_ids=[\"{company_id}\"]" \
--data-urlencode "per_page=25"
```
Optional filters: `contact_id`, `content_type`, `created_after`, `created_before`.
Fetch a single document with `GET /canvas/{canvas_id}`.
***
## List territories
```bash theme={null}
curl "$PGAI_BASE/territories" \
-H "x-api-key: $PGAI_API_KEY"
```
```bash theme={null}
curl "$PGAI_BASE/territories/{territory_id}" \
-H "x-api-key: $PGAI_API_KEY"
```
***
## Check credit usage
```bash theme={null}
curl "$PGAI_BASE/organization/credits" \
-H "x-api-key: $PGAI_API_KEY"
```
Useful before batch enrichment or contact enrichment flows.
***
## MCP instead of REST
For AI clients (Claude, Cursor, etc.), the MCP server exposes the same workspace data as tools — no need to wire every REST call yourself. See the **Integrations** tab for MCP setup, or connect to `https://mcp.getpg.ai`.
| Task | REST API | MCP |
| ---------------- | ------------------------------------------------- | ---------------------------------------- |
| Account research | `/accounts`, `/search`, `/companies/{id}/profile` | `company`, `search` tools |
| Add company | `POST /companies` + poll | `companies_add` + `get_operation_status` |
| Content | `GET /canvas`, templates | `canvas_list`, `template_generate` |
***
## Error handling
All flows should handle standard HTTP status codes in production:
| Status | Meaning |
| ------ | -------------------------------------------- |
| `401` | Missing or invalid API key |
| `403` | Key lacks required permission scope |
| `404` | Resource not found |
| `429` | Rate limit — retry with backoff |
| `202` | Async job accepted — poll `/operations/{id}` |
See [Authentication](/api/authentication) for permission scopes and rate limit headers.
# API Overview
Source: https://docs.getpg.ai/api/overview
Integrate PG:AI intelligence into your applications and workflows via the REST API
The PG:AI API gives you programmatic access to account intelligence, territory data, contacts, content, and AI-powered insights. Use it to pull intelligence into your own tools, automate workflows, or build custom integrations.
## Base URL
```
https://api.getpg.ai/public-api/v1
```
## Quick Start
Generate an API key in **Settings → API Keys** within your PG:AI workspace.
```bash theme={null}
curl -X POST "https://api.getpg.ai/public-api/v1/accounts" \
-H "x-api-key: your_api_key" \
-H "Content-Type: application/json" \
-d '{}'
```
See [Common Flows](/api/common-flows) for end-to-end examples — add a company, enrich contacts, list canvas, and more.
Scroll the **API** sidebar — **Getting started** is at the top, then Accounts, Companies, Contacts, and the rest.
API key setup, permissions, and error handling
End-to-end integration patterns with curl and Python
Connect Claude, Cursor, and other AI clients — see the **Integrations** tab
## Async operations
Some endpoints return `202 Accepted` with a `public_operation_id`. Poll `GET /operations/{public_operation_id}` until the job completes. See [Common Flows](/api/common-flows#add-a-company-and-wait-for-enrichment) for a full example.
## Rate limits
API requests are rate-limited based on your plan. When you hit the limit, the API returns `429 Too Many Requests`. See [Authentication](/api/authentication) for rate limit headers.
# Contact Enrichment
Source: https://docs.getpg.ai/configuration/contact-enrichment
Control how contacts are auto-enriched across the organisation and by persona
Contact enrichment settings control whether PG:AI automatically enriches contacts with email, phone, both, or neither.
## How it works
* **Organisation default** applies to all contacts.
* **Persona overrides** let you use different enrichment behavior for specific personas.
* If a contact has no persona override, the organisation default is used.
## Enrichment modes
| Mode | Behavior |
| ------------------ | ------------------------------- |
| `none` | No automatic contact enrichment |
| `email` | Enrich email only |
| `phone` | Enrich phone only |
| `email_and_mobile` | Enrich both email and phone |
## Recommended setup
1. Set an organisation default first.
2. Add persona-specific overrides only for high-priority personas.
3. Review monthly to balance quality, speed, and credit usage.
Keep persona overrides limited to the personas your team actively sells to. Too many overrides make behavior harder to reason about.
# Content Settings
Source: https://docs.getpg.ai/configuration/content-settings
Configure content groups and templates used by Studio and workflows
Content settings define how PG:AI generates output for your team, including templates, prompts, context recipes, and output structure.
## Core concepts
* **Content groups**: reusable containers of templates.
* **Content templates**: individual items such as email, notes, call script, document, or persona content.
* **Context recipe**: what evidence and context should be used.
* **Research prompt**: instruction set for generation behavior.
## Where this is used
* Studio canvas and agent flows
* Workflow runs
* Sequence content assembly
## Recommended setup order
1. Create 1-2 content groups per team or motion.
2. Add templates for your most common outputs first.
3. Standardize context recipes for consistency.
4. Iterate prompts based on real usage.
# Credits
Source: https://docs.getpg.ai/configuration/credits
Manage organisation credit limits and usage controls
Credits control usage limits for key PG:AI activities like company enrichment, content generation, territory operations, and contact enrichment.
## Credit controls
* Company credits
* Content credits
* Custom insights credits
* Territory credits
* Contact credits
* Contact enrichment credits
## Capacity controls
* Licenses allowed
* Datasets allowed
* Custom insights allowed
* Workflow search terms allowed
* Optional per-user credit distribution
## Operating guidance
1. Set monthly guardrails at organisation level.
2. Enable per-user limits only if you need strict allocation control.
3. Track usage trends before changing limits.
If teams frequently hit limits, review workflow frequency and monitoring scope before increasing credits.
# Custom Insights
Source: https://docs.getpg.ai/configuration/custom-insights
Configure specific research queries to generate targeted intelligence about your accounts
Custom Insights let you create specific research questions that PG:AI answers for every account. Define queries that align with your sales process to generate consistent, targeted intelligence across all accounts.
Custom Insights determine what targeted intelligence appears on the Custom Insights tab for each account. Well-configured insights provide sales-relevant research that would otherwise require manual investigation.
## How It Works
Custom Insights consist of two components:
* **Individual Insights** - Specific research questions answered for each account
* **Insights Groups** - Collections of insights with shared sources and timeframes
## Creating Individual Insights
Use clear names like "Cloud Security Challenges" or "AI Implementation Status"
Create specific questions that PG:AI will answer about each account
Choose Short (50-100 words), Medium (100-200 words), or Long (200+ words)
Generate sample insights on known accounts to validate effectiveness
## Writing Effective Queries
**Good Examples:**
* "What are the recent cloud security challenges faced by this company?"
* "How is this company leveraging AI in their operations?"
* "What data infrastructure challenges are mentioned about this company?"
**Avoid Generic Queries:**
* "Tell me about their strategy" (too broad)
* "What do they do?" (basic information)
* "Are they a good fit?" (requires solution context)
Make queries specific to your solution area. Generic questions produce generic insights that don't help with sales conversations.
## Creating Insights Groups
Groups let you organize related insights with shared parameters:
* **Sources** - Public documents (annual reports, SEC filings) vs web information (news, press releases)
* **Time span** - Last week, month, quarter, year, or all time
* **Keywords** - Terms that help focus research on relevant topics
Most companies create 2-4 insights groups covering their key sales focus areas.
## Quick Actions
Set up research queries and groups
See generated insights in action
Include groups in automated account onboarding
# Datasets
Source: https://docs.getpg.ai/configuration/datasets
Upload and manage your sales collateral to train PG:AI on your value proposition and solution capabilities
Datasets are collections of your sales documents that train PG:AI on your value proposition and messaging. Upload PDFs of your sales collateral, and PG:AI uses this content to generate personalized materials aligned with your actual sales approach.
Your first dataset is automatically created from your company website. You can then add additional datasets with your internal sales materials.
## Types of Sales Documents to Upload
Value proposition documents, messaging frameworks, positioning guides
Competitive battle cards, objection handling guides, differentiation documents
Customer success stories, case studies, reference materials, testimonials
Product datasheets, capability overviews, technical specifications, feature guides
Use case documents, solution briefs, implementation guides, industry solutions
Buyer persona guides, role-specific messaging, audience-targeted content
## Adding Datasets
### **Document Upload Process**
Upload your existing sales collateral in PDF format to organized datasets
PG:AI reads and analyzes the text content to understand your messaging and value propositions
The platform learns your specific language, positioning, and solution capabilities
PG:AI uses this knowledge to create personalized content that reflects your actual sales materials
## Dataset Organization & Management
### **Creating Effective Datasets**
Label your datasets clearly and organize them logically. This makes it easier to select the right datasets for specific content templates and engage settings.
**Organization Examples:**
* **By Content Type**: Case Studies, Battle Cards, Product Info, Value Frameworks
* **By Solution Area**: Platform, Security, Integration, Analytics
* **By Audience**: Financial Services, IT Leaders, Executives, End Users
### **Best Practices**
1. **Clear Labels**: Use descriptive names that indicate content type and purpose
2. **Current Content**: Upload your most recent, approved sales materials
3. **Quality PDFs**: Ensure documents have clear, readable text for AI analysis
4. **Regular Updates**: Add new materials as they're created
## Using Datasets
Your uploaded datasets are used to:
* **Train Engage Settings**: Power Value Pyramids and Three Whys with your specific messaging
* **Generate Content**: Create emails, call scripts, and presentations using your proven materials
* **Enhance Intelligence**: Connect prospect needs to your actual solution capabilities
## Quick Actions
Add your PDFs to create and organize datasets
Select datasets for Value Pyramids and Three Whys
Choose datasets for personalized content generation
# Engage Settings
Source: https://docs.getpg.ai/configuration/engage-settings
Configure how PG:AI builds value propositions and engagement insights for your accounts
Engage Settings control how PG:AI generates Value Pyramids, Three Whys frameworks, and Discovery Questions. These settings train the system to understand your solution and map it to account priorities.
Engage Settings directly determine the quality and relevance of your generated sales content. Well-configured settings produce more compelling and accurate Value Pyramids and Discovery Questions.
## How It Works
Engage Settings consist of three components:
* **Solution Description** - What your solution does and the value it delivers
* **Search Signals** - Keywords that identify relevant account initiatives
* **Dataset Selection** - Which sales collateral to use for content generation
## Setting Up Engage Settings
Create descriptive names like "Enterprise Financial Services" or "Mid-Market Manufacturing"
Describe your solution's capabilities, challenges addressed, and strategic value
Add keywords that identify relevant account initiatives and challenges
Choose which uploaded sales collateral to reference for content generation
Generate sample content and adjust settings based on quality and relevance
## Solution Description Structure
Organize your solution description with clear sections:
**Challenges:**
* Specific business problems you solve
* Pain points your solution addresses
* Operational inefficiencies you eliminate
**Strategies and Initiatives:**
* Transformation goals you enable
* Strategic outcomes you deliver
* Implementation benefits you provide
Avoid mentioning your company name in the solution description. Focus on solution value, not company branding.
## Search Signals
Add keywords that help identify relevant accounts:
* **Business initiatives** - Digital transformation, operational efficiency, cost optimization
* **Technology areas** - Cloud migration, AI implementation, data modernization
* **Pain points** - Manual processes, security vulnerabilities, compliance gaps
* **Industry terms** - Regulatory compliance, sector-specific challenges
## Multiple Configurations
Create different Engage Settings for:
* **Different industries** - Financial Services vs Healthcare vs Manufacturing
* **Company segments** - Enterprise vs Mid-Market vs SMB approaches
* **Use cases** - New Logo vs Expansion vs Competitive Replacement
Most companies start with 2-3 configurations and add more as needed.
Regularly update your Engage Settings based on successful sales conversations. Outdated configurations generate less relevant content.
# Favourite Technologies
Source: https://docs.getpg.ai/configuration/favourite-technologies
Select the technologies most relevant to your sales process from our 12,000+ tracked technologies
Favourite Technologies allows you to select from PG:AI's 12,000+ tracked technologies to create a personalized view focused on what matters most to your sales success.
## How It Works
1. Go to **Settings > Technologies**
2. Use the search bar or filters to find relevant technologies
3. Click the **heart icon** to add technologies to your favourites
4. Remove technologies by clicking the **X** on any favourite
Once configured, your Favourite Technologies appear as a dedicated "Favourites" category in the Tech Stack tab of company profiles.
## What to Include
Select technologies that are:
* **Competitors** you need to monitor or replace
* **Integration partners** that create opportunities
* **Buying signals** that indicate good fit for your solution
* **Complementary technologies** that enhance your value proposition
Keep your list focused - choose 15-25 technologies rather than 100+ to maintain filtering effectiveness.
## Quick Actions
Set up your favourite technologies in Settings
See your favourites in company tech stack analysis
Get recommendations for which technologies to include
# Monitoring Rules
Source: https://docs.getpg.ai/configuration/monitoring-rules
Define what signals should trigger alerts, for which scope, and through which channels
Monitoring rules define when PG:AI should generate alerts and who should receive them.
## Rule components
* **Source type**: what to monitor (jobs, employee changes, custom columns, external events, etc.)
* **Condition type**: how to evaluate change (threshold, equals, created, changed, etc.)
* **Scope**: organisation-wide, territory, or selected companies
* **Frequency**: real-time, hourly, daily, weekly, or on-change
* **Channels**: in-app, email, Slack, webhook
## Recommended rollout
1. Start with a small set of high-value rules.
2. Set severity and cooldowns to reduce noise.
3. Review trigger volume after one week.
4. Tighten conditions before adding more rules.
Over-broad rules create alert fatigue quickly. Start narrow, then expand once signal quality is proven.
# Organisation Use Cases
Source: https://docs.getpg.ai/configuration/organisation-use-cases
Define organisation-level use cases that can be attached to territories
Organisation use cases are reusable definitions of the GTM motions your team runs (for example, expansion, replacement, or new logo).
## What use cases do
* Create a shared taxonomy for planning and reporting.
* Let territories reference one or more use cases.
* Keep strategic language consistent across teams.
## Suggested fields
* **Title**: clear use-case name
* **Criteria**: what makes an account fit this use case
* **Other info**: context notes for reps and RevOps
## Best practices
1. Start with 3-5 core use cases.
2. Use clear criteria that a rep can validate quickly.
3. Revisit quarterly as ICP and messaging evolve.
# Configuration
Source: https://docs.getpg.ai/configuration/overview
Make PG:AI specific to your business - the difference between generic output and intelligence that speaks your language
Configuration is what separates PG:AI from a generic research tool. An unconfigured PG:AI gives you good account intelligence. A well-configured PG:AI gives you intelligence that's specific to what you sell, who you sell to, and how your team talks about it.
**The difference is night and day:**
* Without favourite technologies → you see a list of 200 technologies at every account. With them → your competitors and partners are highlighted instantly.
* Without personas → you see all contacts. With them → the roles you sell to are surfaced first.
* Without custom insights → you get generic strategic analysis. With them → every account is analysed through the lens of your specific market and use cases.
* Without datasets → the AI generates content in generic B2B language. With them → content references your actual product, messaging, and methodology.
Configuration takes about 30 minutes upfront and pays off across every account, every rep, and every interaction.
Set organisation structure first: users, roles, and access boundaries for each team.
Upload sales materials and documentation so output reflects your messaging and product reality.
Configure the roles your team sells to so contacts and content are prioritised correctly.
Set default and persona-level enrichment behavior for email and phone data.
Configure how engagement content is generated from signals, datasets, and context.
Create insight queries that analyse accounts through your specific market lens.
Highlight competitor and partner technologies across account tech stacks for immediate relevance.
Define reusable GTM motions that can be attached to territories and planning workflows.
Manage usage guardrails and credit limits across company, content, territory, and contact operations.
Configure content groups and templates used by Studio, workflows, and sequence generation.
Link engage settings, custom data groups, and content groups into reusable workflow definitions.
Build and manage ordered template sequences for repeatable outreach and follow-up patterns.
Define what changes trigger alerts, where they apply, and which channels they notify.
## Recommended Setup Order
If you're setting up PG:AI for the first time, work through configuration in this order:
1. **Favourite Technologies** - immediate impact on every account view (5 min)
2. **Personas** - improves contact discovery and content relevance (5 min)
3. **Custom Insights** - adds depth specific to your market (10 min)
4. **Datasets** - upload 2-3 key documents: product brief, messaging guide, case study (5 min)
5. **Engage Settings** - fine-tune how engagement content is generated (5 min)
6. **Team & Permissions** - invite the team and assign access (5 min)
7. **Content + Workflow Settings** - configure once your core data model is stable
Configuration is an ongoing process, not a one-time setup. As your team uses PG:AI, you'll refine favourite technologies, add new custom insights, and update datasets. The best-configured organisations revisit their settings quarterly.
# Personas
Source: https://docs.getpg.ai/configuration/personas
Configure contact groups to find relevant people and generate role-specific content
Personas help you identify the right contacts at target accounts and generate content tailored to their specific roles and responsibilities.
Personas must be configured in Settings → Personas before they appear in the Contacts tab. The system finds contacts whose job titles match your persona criteria.
## How It Works
1. **Define persona groups** - Create categories like "Technical Decision Makers" or "Security Leadership"
2. **Set search criteria** - Add job titles, departments, and organizational levels
3. **Find contacts** - System identifies matching people at your target accounts
4. **Generate content** - Create role-specific messaging for each persona
## Persona Configuration
### **Setting Up Personas**
Create descriptive names like "Technical Decision Makers" or "Security Leadership"
Choose the primary department or functional area where this persona operates
Define maximum number of contacts to find per account for this persona
Select applicable organizational levels (Executive, VP, Director, Manager, Individual Contributor)
Include job titles, functions, and role-specific terms for contact identification
Choose which sales collateral to use when generating content for this persona
Create personas that match your typical buying committee. Too many personas create confusion, while too few may miss important stakeholders.
## Quick Actions
Set up personas in Settings
Discover contacts at target accounts
Create persona-specific messaging
# Sequence Settings
Source: https://docs.getpg.ai/configuration/sequence-settings
Define reusable sequences by linking ordered content templates
Sequence settings define multi-step sequences and attach the content templates used in each step.
## What sequence settings include
* Sequence name
* Description
* Ordered list of content template IDs
## Typical use cases
* Multi-touch outbound sequences
* Nurture follow-up structures
* Persona-based messaging journeys
## Best practices
1. Keep sequences focused and short.
2. Reuse proven templates instead of duplicating them.
3. Version major changes so performance comparisons stay clean.
# Team & Permissions
Source: https://docs.getpg.ai/configuration/team-permissions
Manage users, roles, and team structures in your PG:AI workspace
Team settings let you manage user access, assign roles, and create team structures within PG:AI. Control who can access your workspace and organize users into logical teams for better collaboration.
## User Roles
PG:AI has three user role levels:
Full system access including billing, settings, and user management
Manage users and teams, configure settings, view analytics
Add accounts, create content, use AI features
## Managing Users
* Change user roles
* Delete user accounts
* Send password reset emails
* View user activity status
* Email address and current role
* Account creation date
* Last activity timestamp
* Team membership
## Team Structure
Create teams that reflect your sales organization:
Define a clear team name (e.g., "North America Sales", "Enterprise AEs")
Designate a team manager for analytics visibility
Select users to include in the team
Finalize the team structure for reporting
## Best Practices
Limit Super Admin access to 1-2 essential personnel. Most users should have Common User roles.
**Role Guidelines:**
* **Super Admin**: Sales ops leaders, system administrators (1-2 people)
* **Admin**: Team managers, sales enablement staff
* **Common User**: Sales reps, AEs, SDRs, end users
**Team Structure:**
* Mirror your actual sales organization
* Keep teams simple and meaningful for analytics
* Update teams as your organization evolves
## Quick Actions
Add users and change roles
Organize users into teams
Analyze team performance
# Workflow Settings
Source: https://docs.getpg.ai/configuration/workflow-settings
Define workflow configurations by linking engage, custom data, and content groups
Workflow settings define how an organisation-level workflow is assembled by linking three building blocks:
1. Engage settings
2. Custom data group
3. Content group
## Why this matters
* Ensures workflows produce consistent outputs.
* Makes workflow behavior auditable and repeatable.
* Lets RevOps tune one workflow config without editing every downstream run.
## Configuration checklist
* Name and describe each workflow clearly.
* Confirm the linked engage settings are current.
* Confirm content groups map to the intended output types.
* Keep obsolete workflows archived or removed.
Treat workflow settings as system configuration, not one-off experiments. Use naming conventions your team can understand quickly.
# Contact Discovery
Source: https://docs.getpg.ai/contact/discovery
Find the right people at target accounts
Contact Discovery helps you find the right stakeholders at your target accounts. Search by name, role, department, or seniority. Use AI-powered recommendations to discover decision-makers and influencers you didn't know about. Run single searches or batch discoveries across hundreds of accounts.
Contact Discovery works across multiple data sources - enrichment providers, company directories, LinkedIn, and job posting databases - so you get comprehensive coverage even for companies with limited public information.
## How It Works
Specify what you're looking for: job title or role keywords, department, seniority level, name, location, or a combination of these filters.
Choose which data providers to search across - multiple sources ensure broader coverage and reduce gaps in contact information.
Conduct a single account search or batch discover across your entire account list. Results stream back with match quality indicators.
Evaluate results, preview contact profiles, and add matches to your database. Duplicate detection prevents adding the same person twice.
Leverage AI-powered suggestions for stakeholders who fit your search criteria or buying profile, even if they don't match keyword searches exactly.
## What You Can Discover
Find CFOs, VPs of Engineering, directors, managers, or any role. Filter by seniority level to target decision-makers or gather broader coverage.
Discover everyone in Finance, Engineering, Sales, Marketing, Operations, or any function within an account.
Use pre-built personas like "Budget Owners", "CRO & CMO", "Sales Leaders", or "RevOps & Enablement" to find people matched to your buying criteria.
Search for specific people by name, or find contacts in particular geographies or office locations.
## Key Capabilities
**Batch Discovery:** Run a single search across 100+ accounts to find all matching contacts at once. Perfect for identifying budget owners across your target list or finding new hiring managers after funding rounds.
**AI-Powered Recommendations:** Go beyond keyword matching. AI surfaces people who match your buying profile or stakeholder type even if they don't have the exact title you searched for.
**Multiple Data Sources:** No single database has everyone. Discovery queries multiple enrichment providers and directories simultaneously, so you find people that others might miss.
**Match Quality Indicators:** Each result shows confidence scores and source information, so you know how verified each contact is before you reach out.
## Tips and Best Practices
* **Start broad, then refine:** Search for a role + department first, review results, then narrow by seniority or keywords if needed.
* **Use persona-based discovery:** Pre-built personas like "Budget Owners" or "Technical Decision Makers" are often faster than building custom role searches.
* **Batch discover before outreach campaigns:** Run batch discovery across your target account list before launching campaigns to ensure you have complete coverage.
* **Review data sources:** Some sources are more complete for specific industries or company sizes. If a search returns sparse results, adjust data source selection and try again.
* **Deduplicate across batch operations:** The system automatically checks for duplicate contacts when adding, but review the dedupe report to catch variations on names and titles.
## Related Modules
Once discovered, enrich contacts with verified email addresses and phone numbers to reach them immediately.
Turn discovered contacts into insights: background, expertise, and likely buying role for each person.
Discovered contacts feed into account profiles and org charts, giving you a complete picture of account coverage.
# Contact Enrichment
Source: https://docs.getpg.ai/contact/enrichment
Get verified email addresses, phone numbers, and professional data
Contact Enrichment adds verified contact details to your people profiles. Get email addresses, phone numbers, location, timezone, and organisational assignments. Enrich individual contacts on demand or run bulk operations across hundreds of people at once.
Enrichment data comes from multiple verified providers - email validation services, phone number databases, location services, and company directory integrations - ensuring accuracy and coverage across different industries and company sizes.
## How It Works
Choose individual contacts from your database, bulk-import lists, or let the system queue contacts that need enrichment.
Run enrichment with a click. Single enrichment is immediate; batch enrichment processes hundreds or thousands of contacts in the background.
The system queries email providers, phone databases, location services, and enrichment APIs simultaneously to maximise match rates.
Enriched data shows source information and verification status. Email and phone numbers are validated before being added to your database.
Continuous background enrichment means contact details stay current as people move, change roles, or update their professional profiles.
## What Gets Enriched
Business email addresses, verified against company directories and validated for deliverability. Includes confidence scores and source information.
Direct phone numbers and office lines with country and area code. Sourced from company directories and enrichment databases.
Office location, country, city, timezone. Essential for scheduling and personalising outreach by region.
Department, reporting line, team assignment. Helps you understand who reports to whom and where someone sits in the structure.
Current company tenure, previous roles, industry experience, skills. Enriched from LinkedIn profiles and professional databases.
Enrichment date and source. Older enrichments can be refreshed to capture role changes and new information.
## Key Capabilities
**Batch Enrichment:** Process hundreds or thousands of contacts in a single operation. Queue all your discovered contacts and let enrichment run in the background while you work on other things.
**On-Demand Enrichment:** Need someone's email right now? Enrich individual contacts with a single click before you reach out.
**Multiple Data Providers:** Each enrichment query checks multiple sources - email validators, phone databases, company directories, LinkedIn - to increase match rates and data quality.
**Verified Data:** Email and phone numbers are validated for accuracy. Confidence scores and source information let you know how reliable each enriched field is.
**Continuous Updates:** Already-enriched contacts are periodically re-enriched in the background, so you capture role changes, location moves, and updated professional information.
## Tips and Best Practices
* **Enrich before outreach:** Always enrich contacts before launching campaigns. Verified emails and phone numbers dramatically improve connection rates.
* **Use batch enrichment for scale:** Don't enrich one by one. Batch operations are faster and more cost-effective, especially for large prospect lists.
* **Review confidence scores:** Not every enrichment returns perfect data. Look at confidence scores and source information, especially for older data or niche roles.
* **Refresh enrichment on old contacts:** If a contact hasn't been enriched in 6 months, refresh them. People move, companies restructure, and email addresses change.
* **Check for duplicates before enriching:** Batch import deduplication to avoid enriching the same person twice under slightly different names.
Enrichment relies on accurate initial contact information. If you provide a common name like "John Smith" without title or company context, enrichment may return incorrect matches. Be specific about title, department, or company to improve accuracy.
## Related Modules
Newly discovered contacts are automatically queued for enrichment to fill in missing email and phone details.
Enriched contact details feed into intelligence profiles, enriching background analysis and persona assignment.
Enriched contact details - email, timezone, location - personalise outreach timing and channel selection in Studio conversations.
# Contact Intelligence
Source: https://docs.getpg.ai/contact/intelligence
AI-powered insights about each person
Contact Intelligence surfaces AI-powered insights about each person at your target accounts. Go beyond the job title to understand their background, expertise, likely role in a purchase decision, and recent activity. AI builds a profile of what matters to each person, what they care about, and how they fit into your deal.
Contact Intelligence combines professional history, job posting data, content engagement signals, organisational context, and AI analysis to build a complete picture of each contact - far richer than what any job title or firmographic database can tell you.
## How It Works
The system ingests LinkedIn profiles, career history, previous roles, companies, and tenure to understand someone's experience and expertise.
Account intelligence (strategic priorities, technology initiatives, hiring patterns) is matched against individual profiles to determine relevance and likely buying role.
AI identifies skills, technologies, industry knowledge, and domain expertise based on career history, current role, and professional activity.
Using account context, purchase cycle patterns, and role signals, AI determines whether someone is likely a decision-maker, influencer, champion, stakeholder, or end user.
Recent job changes, new hires in their team, content engagement, LinkedIn activity, and company announcements provide up-to-date context about someone's current priorities.
## What Intelligence Reveals
Career history, previous companies, roles, tenure, education. Understand where someone comes from and how they got to where they are today.
Technical skills, domain expertise, industry knowledge. What does this person actually know about - and what problems are they likely trying to solve?
Decision-maker, influencer, champion, stakeholder, or end user. What's their likely role in a purchase decision for your solution?
How does this person's background and role align with the account's strategic priorities, hiring patterns, and technology investments?
New hires, promotions, job moves, content engagement, company announcements. What's changed recently that might create urgency or opportunity?
AI-powered suggestions for what might resonate with this person based on their background, role, account context, and strategic priorities.
## Key Capabilities
**Persona Assignment:** Contacts are automatically matched to pre-built personas (CRO, CFO, Chief Data Officer, VP Sales, etc.) or custom personas you define in Settings. This helps you group people by role and reach the right buyers.
**Background Intelligence:** Career timeline showing previous companies, roles, and tenure. Understand someone's experience level and how their background prepares them to evaluate your solution.
**Expertise Extraction:** AI identifies technical skills, industry knowledge, and functional expertise from career history and current role. This helps you personalise your value proposition.
**Buying Role Prediction:** Machine learning models trained on successful deals predict whether someone is likely a decision-maker, influencer, champion, or stakeholder for your specific solution.
**Activity Monitoring:** Recent job changes, promotions, new hires in their team, and company news trigger updates to contact intelligence, signalling potential deal opportunities.
**Content Engagement Signals:** When available, engagement with your company's content, website visits, webinar attendance, and other signals inform intelligence and help you personalise outreach.
## Using Intelligence for Better Conversations
**Personalise Your Approach:** Use background and expertise insights to tailor your messaging. A VP with a data science background will respond differently than one who came up through sales operations.
**Identify Champions:** Contacts whose background aligns with your solution's value and whose role suggests influence are ideal champions to recruit early in the deal.
**Spot Buying Signals:** Recent promotions, new hires into roles that matter for your solution, or company announcements about new initiatives often signal buying intent.
**Build Multi-Threaded Relationships:** Understand what each person cares about. This helps you know who to loop in for different conversations - technical for engineers, financial for CFO, business impact for executives.
**Avoid False Starts:** Intelligence reveals who is and isn't a relevant contact. This helps you focus effort on real buying-side stakeholders and avoid wasting time on people who aren't decision-makers.
## Tips and Best Practices
* **Use buying role signals to prioritise:** Focus your effort on decision-makers and champions first. Intelligence shows you who actually influences purchases in your solution area.
* **Match background to your value proposition:** A contact with a background in operational efficiency is more likely to buy a cost-reduction tool than one with pure technical background.
* **Combine with account intelligence:** Use account strategic priorities to interpret individual intelligence. Someone's background might signal buying potential only if the account is pursuing relevant strategic goals.
* **Personalise at scale:** Intelligence makes it possible to personalise outreach for hundreds of contacts. Use it to customise emails, discovery questions, and value angles by person.
* **Monitor activity signals:** Recent activity - job moves, promotions, new hires - are the best buying signals. Use these to time outreach and spike conversations.
Contact Intelligence is probabilistic, not definitive. AI predictions about buying role and relevance are most accurate when combined with your sales expertise and account knowledge. Use intelligence as a research tool, not a replacement for conversation.
## Related Modules
Discovery finds the people; Intelligence tells you which ones matter most and why.
Enrichment provides verified contact details; Intelligence provides context about who that person is and what they care about.
Studio uses Contact Intelligence to personalise conversation threads, value propositions, and discovery questions for each person.
# Contact
Source: https://docs.getpg.ai/contact/overview
Find, enrich, and understand the people at your target accounts
Contact is the people layer that turns account targets into human opportunities. Discover the right stakeholders at your accounts, enrich their profiles with verified contact details, and build AI-powered intelligence about their role, influence, and likely buying decisions.
![Contact on the company overview]()
Contact data flows from multiple sources - search providers, enrichment services, LinkedIn, and company directories - and refreshes continuously as people move and companies evolve.
## Who It's For
Account executives, sales development reps, and strategic account managers - the people who research accounts, identify stakeholders, and build multi-threaded deals.
Sales leaders who need visibility into rep outreach and contact coverage. RevOps teams who want to track contact quality and enrich CRM data. Marketing teams who need contact insights for ABM campaigns and personalised outreach.
## Contact Module Capabilities
Find the right people by role, department, seniority, or name. Use AI recommendations to discover stakeholders you didn't know about. Run batch discoveries at scale.
Get verified email addresses, phone numbers, locations, and organisational data. Enrich individual contacts or run bulk operations across your database.
Surface AI-powered insights about each person: background, expertise, likely buying role, and content engagement signals. Go beyond the job title.
## Key Benefits
Discover decision-makers and influencers you didn't know about. Find the right contacts for your specific use case, not just the obvious ones.
Enriched email addresses, phone numbers, and location data mean you can reach people immediately without manual research.
AI-powered background, expertise, and buying role insights personalise your approach before you ever speak to someone.
Batch discovery and enrichment replace LinkedIn scrolling and manual data entry. Process hundreds of accounts in minutes.
Every contact is tied to its account. When an account's intelligence changes, it flows into contact profiles automatically.
See who you've reached, what departments you've covered, and where you need more contacts. Visual org charts show relationship gaps.
## How It Connects
Contact profiles live inside account records. Contact discovery and enrichment are powered by the same data foundation that feeds Account Intelligence.
Contact data enriches conversation context. The AI agent uses contact intelligence to personalise value propositions and discovery questions.
Territory scoring and account assignment factored in contact coverage and seniority distribution.
Monitoring tracks people changes: job moves, role changes, new hires. Alerts fire when monitored contacts leave or switch roles.
Contact Personas defined in Settings personalise discovery recommendations and intelligence insights.
Contact management - adding, importing, deduplication, linking to accounts - is handled at the Workspace level.
# FAQ
Source: https://docs.getpg.ai/get-started/faq
Common questions about PG:AI's features, data sources, and pricing
***
## General
PG:AI is an AI Knowledge platform for B2B sales people that helps teams research target accounts, prepare for meetings, and create personalized outreach content. It solves the problem of time-consuming manual research by automatically generating comprehensive account intelligence and mapping it to your company's value proposition. Instead of spending hours on pre-meeting research, sales professionals can get strategic insights in minutes.
PG:AI goes beyond basic contact and firmographic data. Unlike traditional tools that focus on data aggregation, PG:AI analyzes strategic priorities, digital initiatives, and business goals to help you understand what matters most to your prospects. It then maps these insights to your value proposition, creating contextual messaging and meeting preparation materials.
PG:AI has several core components:
* **Overview section**: Provides strategic priorities, goals, digital initiatives, and org structure information about target accounts
* **Custom Insights**: Pre-populated answers to key questions about the account
* **Engage section**: Maps your value proposition to the account's priorities and challenges
* **Personas**: Identifies key stakeholders and builds persona-specific messaging
* **Content generation**: Creates emails, call scripts, and meeting preparation notes
* **Agent**: Allows you to ask specific questions about accounts
PG:AI is industry-agnostic and works for companies of all types, though it delivers the most value for complex B2B selling environments. It's particularly useful for technology sales, financial services, logistics, insurance, enterprise software, and other solutions where understanding a prospect's strategic priorities is crucial. While it works best when used for public companies (due to more available information), it can also be effective for larger private companies.
Yes, PG:AI can analyze your entire target account list to identify which accounts have strategic priorities that best align with your solution. This helps sales teams focus on accounts with the highest likelihood of conversion rather than just working through alphabetical or revenue-based lists.
Absolutely. Many companies use PG:AI to prepare for quarterly business reviews, identify expansion opportunities, and stay informed about their customers' evolving priorities. It's particularly useful for account managers and customer success teams who need to stay on top of customer initiatives.
Yes, by understanding a prospect's strategic priorities, you can position your solution against competitors in the context of what matters most to the prospect. Some companies also use PG:AI to research accounts that use competitive solutions to identify potential displacement opportunities.
Yes, PG:AI works with companies worldwide and supports multiple languages. For non-English companies, it will analyze content in both English and the local language to ensure comprehensive coverage. The output can also be generated in multiple languages to support global sales teams.
## Data
PG:AI uses multiple data sources including:
* **For public companies**: Annual reports, quarterly reports, earnings call transcripts, investor presentations
* **For all companies**: Company websites, executive interviews, press releases, news articles
* Industry reports and analyses
* Job postings and descriptions (for technology stack information)
* Optional integration with your CRM data
Yes, PG:AI analyzes job postings to identify technologies mentioned in job requirements. This gives you insights into a company's tech stack. The platform tracks over 12,500 different technologies and can show you which ones a company is likely using based on their hiring patterns. This is particularly valuable for technology vendors who need to understand a prospect's existing landscape.
## Pricing and Licensing
PG:AI uses an account-based pricing model. You pay for the number of accounts you want to research, not the number of users. This means everyone on your team can access all accounts without additional per-user fees. The standard price is \$25 per account per year, with volume discounts available for larger account packages.
A credit represents one account. When you add a company to PG:AI, you use one credit, which gives you access to all information about that company for 12 months, including all updates and new insights. Credits cannot be reused - if you remove an account, you cannot apply that credit to a new account.
Yes, PG:AI offers evaluation accounts with a limited number of credits so you can test the platform with your own target accounts. During the evaluation period, you'll have access to all features and can fully explore how PG:AI fits into your sales process. Many customers start with 10-20 accounts to test effectiveness before expanding.
## Have More Questions?
Can't find what you're looking for? Our team is here to help.
# For AEs & SCs
Source: https://docs.getpg.ai/get-started/for-aes-scs
Your first 10 minutes in PG:AI as an Account Executive or Solutions Consultant
You sell to accounts. You need to understand them deeply, prepare for meetings quickly, and engage with relevant, informed messaging. Here's how to get going.
## Your First 10 Minutes
Go to your workspace, click **Add Company**, and add the account you have a meeting with soonest. While it enriches (5-10 min), keep going with the next steps.
This is the thing that makes PG:AI specific to what you sell.
Go to **Configuration → Favourite Technologies** and add your competitors and key partner technologies. When you look at any account's tech stack, these will be highlighted automatically - you'll instantly see who's using a competitor.
Then go to **Configuration → Personas** and add the roles you typically sell to (e.g. VP Engineering, CTO, Head of Data). PG:AI will surface these people first in contact discovery.
Once enriched, click into the account. Start with **Strategic Insights** - read the priorities and goals. Then check **Tech Stack** - look for your competitors highlighted in the list. Then check **Contacts** - find the people you'd want to talk to.
This is what every account in your territory will look like once enriched.
Go to **Agent → Agent** and ask: "What should I focus on in my meeting with \[Company]? We sell \[what you sell]." See how the response uses real account data, not generic advice.
Go to **Intelligence → Sales Engagement**. Look at the **Value Pyramid** - this maps your solution to their specific priorities. Look at **Discovery Questions** - these are tailored to what this account actually cares about.
## What You'll Use Most
What the account is prioritising, their goals, SWOT, and division intelligence. Your starting point for any account.
What technologies they use, with your competitors and partners highlighted. Know the competitive landscape before the call.
Ask questions about any account. "What are their strategic priorities?", "Who should I talk to?", "How should I position against \[competitor]?"
Create meeting prep briefs, account plans, and engagement documents - all grounded in real intelligence.
Value pyramids, discovery questions, custom insights, and three whys - tailored to each account.
Find the right people, understand the org structure, and map the buying committee.
## Your Key Playbooks
These are the workflows you'll use regularly:
Prepare for any meeting in 15-20 minutes with deep account context. **Start here.**
Build a full account plan with stakeholder maps, competitive analysis, and engagement strategy.
Understand the competitive landscape at a specific account and position against alternatives.
Prepare executive-ready materials backed by real account intelligence.
## Daily Workflow
Once you're set up, your typical workflow looks like:
1. **Before any meeting:** Run the [Meeting Prep playbook](/playbooks/meeting-preparation) (15-20 min). Check priorities, tech stack, contacts, generate a prep sheet.
2. **For strategic accounts:** Build a full [Account Plan](/playbooks/account-planning) (30-45 min). Review and update before key touchpoints.
3. **For content needs:** Use [Canvas](/agent/canvas) to generate emails, proposals, and briefs grounded in account data.
4. **To stay current:** Set up [monitoring alerts](/playbooks/account-monitoring) on your key accounts so you know when something changes.
# For BDRs
Source: https://docs.getpg.ai/get-started/for-bdrs
Your first 10 minutes in PG:AI as a Business Development Representative
You're prospecting. You need to identify the right accounts, find the right people, and write outreach that references what the prospect actually cares about - not generic templates. Here's how to get going.
## Your First 10 Minutes
Go to your workspace and add the accounts you're targeting this week. Each takes 5-10 minutes to enrich. Add a few at once and they'll process in parallel.
Go to **Configuration → Favourite Technologies** and add your competitors. When you look at any account's tech stack, competitors are highlighted - you'll immediately know if this is a displacement opportunity.
Go to **Configuration → Personas** and add the roles you prospect into (e.g. VP Sales, Director of Engineering, CTO). PG:AI will surface these contacts first.
Once an account is enriched, open **Strategic Insights** and scan the priorities. Find the one most relevant to what you sell. That's your outreach angle - not "I wanted to reach out" but "I noticed you're prioritising X and we help companies with exactly that."
Go to **Contacts & Org Chart**. Your configured personas are surfaced first. Find someone with the right title and seniority. Check their career history for anything useful (e.g. they came from a company that uses your product).
Go to **Agent → Agent** and ask: "Write a cold email to \[Name], \[Title] at \[Company]. Reference their priority around \[X]. We sell \[what you sell]. Keep it under 100 words."
Or use **Canvas** with an email template to generate something more structured.
## What You'll Use Most
Find decision-makers, champions, and the people who matter. Filtered by your configured personas.
What the account cares about - your outreach angle. "I noticed you're prioritising X..."
Buying signals from hiring patterns. If they're hiring 10 engineers in your space, they're investing.
Are they using a competitor? That changes your entire approach. Know before you call.
Generate personalised outreach grounded in real account intelligence. Not templates - account-specific content.
Create outreach sequences, call scripts, and engagement content at scale.
## Your Key Playbooks
End-to-end prospecting workflow - from identifying accounts to crafting outreach. **Start here.**
Create account-relevant emails, call scripts, and LinkedIn messages.
Just got a new territory? Get up to speed fast with bulk enrichment and scoring.
When your prospecting works and you book a meeting - prepare for it in 15 minutes.
## Daily Workflow
1. **Start of day:** Check your target accounts in PG:AI for any new hiring signals or strategic changes.
2. **Before any outreach:** Spend 2-3 minutes on the account. Read top priority, check tech stack for competitors, find the right contact. Write outreach that references something specific.
3. **When you book a meeting:** Hand off to the AE with context - share the account intelligence or Canvas brief so they don't start from scratch.
# For RevOps
Source: https://docs.getpg.ai/get-started/for-revops
Your first 10 minutes in PG:AI as a Revenue Operations professional
You own the GTM infrastructure. Territories, scoring models, data quality, integrations. PG:AI gives you a planning layer built on strategic signals - not just firmographics. Here's how to get started.
## Your First 10 Minutes
Before anyone else uses PG:AI, set up the foundation. Go to **Configuration** and work through:
* **[Favourite Technologies](/configuration/favourite-technologies)** - Add your competitors and key partner technologies. This is the single most impactful configuration. Every account's tech stack will highlight these automatically.
* **[Personas](/configuration/personas)** - Add the roles your team sells to. PG:AI uses these for contact matching and content generation.
* **[Custom Insights](/configuration/custom-insights)** - Set up custom intelligence queries that run against every account. E.g. "What is this company's approach to \[your market category]?"
* **[Datasets](/configuration/datasets)** - Upload your sales materials, product briefs, and messaging so the AI generates content in your language.
Go to **Territory → Territory Management** and create a territory. You can import accounts via CSV or add them from your workspace.
For your first test, import 50-100 accounts from one team's territory. This lets you validate the enrichment and scoring before rolling out to everyone.
Go to **Territory → Enrichment** and configure which intelligence to pull: tech stack, jobs, employee groups, strategic insights. Run enrichment on your test territory.
This populates the data that scoring models will use.
Go to **Territory → Scoring Models**. Create a model that reflects your ICP. Weight the signals: strategic insight criteria, tech stack fit, hiring signals, employee groups, firmographics.
Run it against your test territory and check the results. Do the top-scored accounts look right? If not, tune the weights.
This is the step most people skip and it's the most important. Take your closed-won deals from last quarter and check their scores. Take your closed-lost deals and check theirs. If the model ranks won deals higher than lost deals, it's working. If not, adjust the criteria.
## What You'll Use Most
The foundation - technologies, personas, custom insights, datasets. Set up once, every rep benefits.
Create and manage territories. Import accounts, assign reps, configure enrichment.
Build scoring models that combine multiple signals into one account score. Validate against real outcomes.
Define strategic topics and score accounts on alignment with what matters to your business.
Model different territory designs. AI recommendations for rebalancing and coverage optimisation.
Invite users, assign roles, and control who can see which territories and settings.
## Your Key Playbooks
Full territory planning workflow - import, enrich, score, segment, assign. **Start here.**
Set up a new territory for a new hire or restructure. Pre-load intelligence so they're productive from day one.
Run a comprehensive territory analysis - coverage, balance, quality, trends.
## Setup Checklist
After the first 10 minutes, here's the full setup path:
* [ ] Configure favourite technologies (competitors + partners)
* [ ] Configure personas (target roles)
* [ ] Set up custom insights (market-specific queries)
* [ ] Upload datasets (sales materials, product briefs)
* [ ] Create territories and import accounts
* [ ] Run enrichment across territories
* [ ] Build and validate scoring models
* [ ] Set up monitoring agents for key accounts
* [ ] Invite the team and assign territories
* [ ] Set up workflow templates for common activities
**Configuration is what makes PG:AI valuable.** An unconfigured PG:AI produces generic intelligence. A well-configured PG:AI produces intelligence that speaks your team's language - competitors highlighted, relevant personas surfaced, insights framed around your methodology. The 30 minutes you spend on configuration pays off across every account and every rep.
# For Sales Leaders
Source: https://docs.getpg.ai/get-started/for-sales-leaders
Your first 10 minutes in PG:AI as a VP Sales, CRO, or Sales Director
You need your team performing consistently, your territories making sense, and visibility into what's happening across your accounts. Here's how PG:AI helps and how to get started.
## Your First 10 Minutes
Ask your admin or RevOps to add a few accounts you know well. Once enriched, open one and review the intelligence. Compare what PG:AI produces against what you know about the account. This builds confidence in the data quality.
If your team has a territory set up, go to **Territory** and look at the companies table. You'll see every account with a score, enrichment data, and badges. This is the view your reps will use to prioritise.
Sort by score. Are the top accounts the ones you'd expect? If not, the scoring model needs tuning - that's a [configuration task](/configuration/overview) for RevOps.
Go to **Territory → Analytics**. This shows score distribution, segment breakdown, and territory coverage. You'll immediately see: how many accounts are scored, how they're distributed, and where there are gaps.
Go to **Monitor** and see what alerts are set up. Monitoring agents watch your accounts for changes - leadership moves, strategy shifts, hiring patterns. As a leader, this is how you stay informed about your team's key accounts without relying on rep updates.
## What You'll Use Most
See your team's entire book of business. Scored, ranked, enriched. The replacement for spreadsheet-based territory reviews.
How accounts are prioritised. Review and tune the criteria to match your ICP and sales motion.
Territory health, score distributions, segment breakdowns. The data for territory reviews and QBRs.
Alerts when something changes at key accounts. Stay informed without chasing reps for updates.
## Your Key Playbooks
Score, segment, and prioritise territories. Make data-driven decisions about where your team focuses. **Start here.**
Run a full territory analysis - useful for QBRs, annual planning, or restructuring.
Set up monitoring across key accounts so you know when something changes.
Prepare executive-ready materials backed by real account intelligence.
## What to Do After Setup
* **Review scoring with RevOps.** The scoring model determines how accounts are ranked. Make sure the criteria reflect what actually predicts success for your team.
* **Set the expectation with your team.** PG:AI works best when reps use it before every meeting. Set the standard: "every meeting, every account, fully prepared."
* **Use Territory Analytics in your reviews.** Replace "how's your territory going?" with data. Score distributions, coverage gaps, and enrichment quality give you a real picture.
# Welcome to PG:AI
Source: https://docs.getpg.ai/get-started/introduction
Deep account intelligence for B2B revenue teams
PG:AI gives your revenue team instant access to deep, continuously updated intelligence about every account in their territory - strategic priorities, competitive landscape, stakeholder maps, hiring signals, financial context - so they can focus on the right accounts, walk into every meeting prepared, and engage prospects at the highest standard.
Full account intelligence in minutes. Strategic priorities, tech stack, contacts, competitive positioning - one place, always current.
Every account in your territory with a current, data-driven plan. Not just the top 10 you know well.
Territories come pre-loaded with intelligence. New hires are productive from day one.
Every rep as prepared as your best rep. Research is institutional, not individual.
## The Platform
PG:AI is six product modules that work together:
**Focus your team on the right accounts.** Score and rank entire territories based on strategic signals - not just firmographics. Build territories in hours, validate scoring against real outcomes, and run AI-powered scenarios.
→ [Explore Territory](/territory/overview)
**Know your accounts inside out.** Strategic priorities, SWOT analysis, technology stack, contacts and org charts, financial intelligence, and sales engagement content - generated automatically from public sources, updated continuously, configured to how you sell.
→ [Explore Account](/account/overview)
**Find and understand the people at your accounts.** Discover the right stakeholders, enrich their profiles with verified contact details, and build AI-powered intelligence about each person's role and influence.
→ [Explore Contact](/contact/overview)
**Research, create, and prepare - with full account context.** An agent and content workspace that knows your accounts. Generate meeting briefs, account plans, outreach sequences, and business documents grounded in real intelligence.
→ [Explore Studio](/studio/overview)
**Know when something changes.** Configurable monitoring agents that watch your accounts for strategy shifts, leadership moves, hiring surges, technology adoption, and competitive entries. Your team knows first.
→ [Explore Monitoring](/monitoring/overview)
**Configure PG:AI for your team.** Set up technologies, personas, scoring models, integrations, and more. Build the foundation for all other modules.
→ [Explore Settings](/configuration/overview)
## Who Uses PG:AI
Prepare for meetings in minutes. Walk into every conversation knowing strategic priorities, competitive landscape, and stakeholder dynamics. Generate discovery questions, value propositions, and account plans grounded in real data.
→ [Get started as an AE/SC](/get-started/for-aes-scs)
Turn outbound from generic to targeted. Know what every account cares about and why they should talk to you. Find the right contacts, craft personalised outreach, and spot buying signals from hiring patterns.
→ [Get started as a BDR](/get-started/for-bdrs)
Visibility across every territory. Consistent preparation quality across the team. New reps productive in days. Territory decisions backed by real account signals, not spreadsheets.
→ [Get started as a Sales Leader](/get-started/for-sales-leaders)
Territories built on strategic signals, not firmographics. Configurable scoring models validated against real outcomes. Always-current account data without manual refresh.
→ [Get started as RevOps](/get-started/for-revops)
ABM targeting based on what accounts actually care about. Campaign messaging anchored to real strategic priorities. Competitive displacement campaigns built on tech stack intelligence.
Continuous intelligence on every customer account. Division-level expansion opportunities. Alerts when strategy shifts or stakeholders change. QBRs backed by data.
## Get Started
Add your first account and explore the intelligence in 5 minutes
Step-by-step guides for meeting prep, account planning, territory planning, and more
Set up PG:AI for your team - technologies, personas, scoring, integrations
# Quickstart
Source: https://docs.getpg.ai/get-started/quickstart
Add your first account and see what PG:AI produces - in 5 minutes
This guide gets you from login to full account intelligence in about 5 minutes. By the end, you'll have one account fully enriched and you'll understand what PG:AI gives you.
**Prerequisites:** A PG:AI account. If you don't have one yet, [get access here](https://www.getpg.ai/sign-up).
## 1. Log In
Go to [app.getpg.ai](https://www.app.getpg.ai/login/) and sign in. You'll land on your workspace - this is where all your accounts live.
## 2. Add Your First Account
Click **Add Company** in the top right. Type a company name - pick one you're actively working on or about to meet with. Click **Add**.
PG:AI will start enriching the account. This takes 5-10 minutes and uses 1 credit. You'll get a notification when it's ready.
Pick a larger company for your first account (public companies work great). They have more public data, so the intelligence will be richer and you'll see the full range of what PG:AI produces.
## 3. Explore the Intelligence
Once the account is ready, click into it. You'll see several tabs:
**Strategic Insights** - The account's strategic priorities, goals, SWOT analysis, division intelligence, and industry context. This is the strategic brain of the account - what they care about, where they're headed, what keeps them up at night.
**Tech Stack** - Technologies detected from job posting data. If you've configured [favourite technologies](/configuration/favourite-technologies), your competitors and partners are highlighted automatically.
**Jobs & Hiring Signals** - What they're hiring for, where, and what it tells you about their priorities and investment areas.
**Financial Intelligence** - For public companies: share price, key metrics, competitor benchmarking, and analyst forecasts.
**Contacts & Org Chart** - Key people at the company with contact details, career history, persona matching, and a visual org chart showing relationships.
**Sales Engagement** - This is where intelligence becomes action: Value Pyramid (how your solution maps to their priorities), Discovery Questions (account-specific), Custom Insights, and Three Whys.
## 4. Try the Agent
Go to **Agent → Agent** and ask a question about the account you just added:
> "What are the top 3 reasons \[Company] should talk to us? We sell \[brief description of what you sell]."
The agent draws on all the intelligence - priorities, tech stack, financials, contacts - and gives you a tailored answer with sources.
Try a few more:
* "Who should I talk to at \[Company] about \[your use case]?"
* "What technology does \[Company] use that competes with us?"
* "What should I focus on in my meeting with \[Company] tomorrow?"
## 5. What to Do Next
Set up favourite technologies, personas, and custom insights so the intelligence speaks your language
Use the Meeting Preparation playbook to walk into your next call fully prepared
Add the rest of your territory - individually or via CSV import
Browse workflows for account planning, territory planning, competitive research, and more
**The single most impactful thing you can do after this quickstart** is [configure your favourite technologies](/configuration/favourite-technologies) and [personas](/configuration/personas). This is what makes PG:AI specific to your business - competitors get highlighted, relevant contacts get surfaced, and engagement content speaks your language. Takes 10 minutes, transforms the output.
## Need Help?
* Email: [support@getpg.ai](mailto:support@getpg.ai)
* In-app chat: Click the chat bubble in the bottom right
* [FAQ](/get-started/faq)
# What's New in PG:AI V2
Source: https://docs.getpg.ai/get-started/whats-new-v2
A new GTM agent, composable canvases, territory planning, continuous monitoring, and a unified workspace. Everything rebuilt.
The way GTM teams research accounts hasn't changed in a decade. You Google the company, skim a 10-K, check LinkedIn, open a few tabs, and hope you remember what you found by the time you're on the call. Multiply that across 200 accounts and it's obvious why most reps only deeply understand a handful of their book.
PG:AI V2 changes that. A new Agent that researches autonomously. Composable canvases that turn intelligence into deliverables. Workflows that run at scale across your entire territory. Continuous monitoring that tells you when something changes and what to do about it. And a unified workspace that ties it all together.
This page covers what's new.
## Studio
Studio is where intelligence becomes action. The Agent researches. Canvas creates. Workflows scale. Everything is grounded in what PG:AI actually knows about your accounts.
### The Agent
This isn't the Q\&A assistant from V1. The new Agent works autonomously on your behalf: multi-step research, live data sources, content generation, and actions across your accounts. Ask it to prepare you for a meeting and it pulls strategic priorities, attendee profiles, competitive positioning, and recommended questions, all cited back to sources.
The Agent has full access to every intelligence dimension for the account you're viewing. Every response is grounded in what PG:AI actually knows, not a generic LLM answer.
### Canvas
A composable content surface for generating, editing, and refining deliverables. Pick a template or start from scratch. The Agent writes a first draft pre-filled with account intelligence. You refine through conversation: "Make the competitive section stronger." "Add the CFO's comments from last quarter." Each revision draws on the full intelligence graph.
Account briefs, meeting prep, email sequences, discovery questions, competitive comparisons, value pyramids. You can use the built-in templates or create your own that your team can reuse.
### Workflows
Multi-step agentic pipelines that run across accounts at scale. Define a sequence of steps (research, analyse, find contacts, generate outreach) and run it across 50 or 500 accounts at once. Workflows branch, run in parallel, and produce different outputs per step. Build once, run across your entire territory.
## Territory
The go-to-market planning layer. Score and rank accounts, run AI-powered scenarios, and focus your team on the opportunities that matter most. Instead of static spreadsheets, Territory brings together enriched account data, configurable scoring models, and AI recommendations in one place.
**Territory scoring** — Score and rank accounts using configurable models that go beyond firmographics, incorporating strategic signals, hiring data, tech stack alignment, and competitive positioning.
**AI scenarios** — Run what-if scenarios across your territory: "What if we weighted hiring signals higher?" or "Show me accounts where our use cases align with their stated priorities." The AI re-ranks in real time.
**Team alignment** — Assign reps to territories and track coverage. See which accounts are under-covered and which reps need support.
## Monitoring
Seven agent types run continuously across every account on your watchlist: jobs, contacts, web mentions, annual reports, earnings calls, public filings, and strategic insight changes. When something changes, monitoring doesn't just notify you. It contextualises the signal, explains why it matters, and tells you what to do about it.
Signals are ranked by relevance, not just recency. A new VP of Engineering doesn't show up as "new contact detected." The alert maps their background to your solution and your buyer personas. Alerts can trigger Studio workflows automatically.
## Workspace
The cross-account layer of PG:AI. While Account gives you deep intelligence on a single company and Territory helps you prioritise, Workspace lets you search, explore, and monitor activity across your entire portfolio from one place.
### Unified Search
One search box for every piece of intelligence across all your accounts. Insights, contacts, jobs, public events, news mentions, web pages, technologies, internal documents, and conversations, all queryable from one place. Unified Search understands the meaning of your query and ranks results by relevance, not just keyword match. Instead of remembering which tab or system holds what, you type what you're looking for and get the answer.
The same search engine powers single-company timelines, dashboards, and the global search bar. Three scopes: a single account, your tracked book of business, or every account in your entire organisation. Three views: timeline (most recent first), company (grouped by account), and relevance graph (visual network showing how accounts and topics connect).
### Activity Pulse
The dashboard sellers open first thing in the morning. Activity Pulse brings together every meaningful event from every account, strategic priorities, earnings calls, leadership changes, hiring activity, technology adoption, news mentions, and regulatory filings, so you can see what needs attention today.
Built-in weighting ensures high-signal events stand out from routine noise. A new strategic priority from an earnings call reads differently from a standard job posting. A company posting a thousand jobs in a week won't drown out three earnings-call insights from the same period. You don't need to configure it. Activity Pulse understands which events matter most and surfaces them accordingly.
## Contacts
Better contact discovery with more sources and higher match rates.
Direct phone numbers and verified email addresses, enriched automatically.
Visual org charts showing reporting lines and team structures, built from enrichment data.
Track job changes, promotions, and departures for key contacts across your accounts.
## Faster enrichment
Account enrichment is **3-4x faster**. What used to take 5-10 minutes now completes in 2-3. The underlying pipeline parallelises research across data sources, so you're waiting less and working sooner.
## New interface
A completely new UI that's faster to navigate and better to look at. The company view retains the same structure you're used to, but surfaces more data in a cleaner layout.
Product tour - scroll sideways to preview the new interface
## Platform & integrations
Programmatic access to PG:AI: companies, contacts, intelligence, the agent, and more. Build integrations, automate workflows, and pull PG:AI data into your existing tools.
Connect PG:AI to AI tools that support MCP (Model Context Protocol). Use PG:AI intelligence directly from Claude, Cursor, and other MCP-compatible clients.
Enhanced analytics for admins and team leaders. Track adoption, usage patterns, and team activity across the platform.
## Getting started
If you're an existing user, everything has been migrated. Your accounts, contacts, and intelligence data are all in V2, ready to go. Log in and explore.
If you're new to PG:AI:
Add your first accounts and see intelligence in minutes.
How account executives and solutions consultants use PG:AI day to day.
How business development reps use PG:AI for prospecting and outreach.
What the agent can do and how to get the most out of it.
# Alerts
Source: https://docs.getpg.ai/monitoring/alerts
View, triage, and act on detected account changes - each alert includes Intelligence context so you know not just what changed, but why it matters
View, triage, and act on detected account changes. Each alert includes Intelligence context so you know not just what changed, but why it matters.
When a monitoring agent detects a change that matches its rules, it generates an alert. Each alert includes what changed, when it was detected, which monitoring agent triggered it, and contextual information from the account's Intelligence profile.
## Key capabilities
* **Alert feed** with filtering and sorting
* **Triage actions**: acknowledge, resolve, dismiss
* **Intelligence context** embedded in every alert
* **Alert history** and pattern analysis
* **Alert instances** for recurring signals
## What alerts look like
Each alert includes:
* **What changed** - the specific change detected (e.g., "12 new cloud engineering roles posted this week")
* **When** - timestamp of detection
* **Which agent** - the monitoring agent that triggered the alert
* **Intelligence context** - relevant data from the account's Intelligence profile (strategic priorities, tech stack, financials, etc.)
* **Why it matters** - a contextual explanation connecting the change to the account's broader situation
## Triage workflow
Alerts have three triage states:
| State | Meaning | When to use |
| ---------------- | ---------------------------------- | --------------------------------- |
| **New** | Not yet reviewed | Default state for all alerts |
| **Acknowledged** | Reviewed, action planned | You've seen it and will follow up |
| **Resolved** | Action taken or no longer relevant | You've acted or dismissed it |
### Recommended triage cadence
Scan new alerts. Acknowledge anything that needs follow-up. Resolve anything that's not relevant.
Review acknowledged alerts. Take action or resolve. Adjust monitoring agent rules if too many irrelevant alerts are appearing.
## Acting on alerts
Alerts are signals. The value comes from what you do with them.
### Common response patterns
**Hiring signal alert → Outreach**
A company posted 15 new roles relevant to your solution. Draft a personalised email referencing the hiring activity.
Example: "I noticed you're scaling your cloud engineering team. We help companies at this stage of infrastructure investment..."
**Leadership change alert → Relationship building**
A new VP was appointed. Research their background. Identify mutual connections. Prepare an introduction.
**Competitive signal alert → Defence or displacement**
A customer adopted a competing technology. Schedule a check-in with your champion. Understand the evaluation. Reinforce your value.
**Financial event alert → Deal timing**
The company announced strong earnings and raised guidance. The budget environment is favourable. Accelerate your engagement.
## Using alerts with Agent
Alerts provide the "what changed." The Agent provides the "what to do about it."
Notice an alert about hiring activity at an account.
Open the Agent tab for that account.
Ask: "Based on their recent hiring in cloud engineering, what's the best approach for outreach?"
The agent generates a recommendation using both the alert context and the full Intelligence profile.
## Related modules
Configure the agents that generate alerts - define rules, thresholds, and watchlists.
Use the Agent to research and respond to alert signals.
Automate responses to alerts with multi-step workflows.
# Monitoring Agents
Source: https://docs.getpg.ai/monitoring/monitoring-agents
Configure what to watch and which accounts to monitor - define rules, data sources, and thresholds for the signals that matter
Configure what to watch and which accounts to monitor. Define rules, data sources, and thresholds for the signals that matter to your business.
A monitoring agent is a configured watcher. You define what type of changes it should look for - new job postings, leadership changes, technology adoption signals, financial events - and which companies it should monitor. Agents run continuously, evaluating new data against your defined rules.
## Key capabilities
* **Create and configure** monitoring agents with specific rules and thresholds
* **Manage company watchlists** per agent (add/remove companies)
* **Scheduled and real-time** evaluation modes
* **Multiple agents** with different focus areas running in parallel
## Recommended agent configurations
### For new business teams
**Agent: Hiring Signals** Watch target accounts for hiring that indicates investment in areas relevant to your solution. A company tripling its data engineering headcount is likely investing in data infrastructure.
**Agent: Strategic Initiatives** Watch for public strategic announcements that create openings for your solution. A company announcing a digital transformation initiative is a warmer prospect.
### For customer success teams
**Agent: Champion Tracking** Watch customer accounts for leadership changes. Your champion leaving is an early churn signal. A new leader is an opportunity to re-establish the relationship.
**Agent: Competitive Signals** Watch customer accounts for competitive technology adoption. A customer hiring people with competitor product experience may be evaluating alternatives.
### For account executives
**Agent: Deal Signals** Watch active deal accounts for changes that affect the deal: financial events, leadership changes, strategic shifts, and competitive moves. Any of these can accelerate or derail a deal.
## How many agents should you create?
Start with **1–2 agents** focused on the signals that matter most to your role.
| Role | Recommended starting agents |
| ------------------ | -------------------------------------------------------------- |
| Account executives | Hiring signals + leadership changes |
| SDRs | Strategic initiatives (identifies warm outreach opportunities) |
| Customer success | Champion tracking + competitive signals |
| RevOps | Broad coverage across signal types for territory health |
You can add more agents over time as you see what surfaces valuable alerts.
## Tuning your agents
After the first week of alerts, review:
If you're getting too many irrelevant alerts, tighten your rules - higher thresholds, more specific signal types.
If important changes are being missed, add more signal types or lower thresholds.
If you're monitoring too many companies, prioritise your active pipeline and key accounts. You can always expand later.
## Tips
"Hiring Signals - Active Pipeline" is better than "Agent 1."
One agent per signal type is easier to manage than one agent trying to watch everything.
Set aside 15 minutes per week to review and triage alerts. This keeps the system useful and the noise manageable.
An alert that's acknowledged but never acted on is a missed opportunity. If the alert isn't actionable, adjust the rules.
## Related modules
View, triage, and act on the changes your monitoring agents detect.
Use the Agent to research accounts flagged by monitoring agents.
Trigger automated workflows in response to monitoring alerts.
# PG:AI Monitoring
Source: https://docs.getpg.ai/monitoring/overview
Watch your accounts for changes and get alerted
PG:AI Monitoring watches your accounts for changes and alerts you when something happens. Configurable monitoring agents track hiring, strategic shifts, competitive moves, financial events, and more - so your team never misses a signal.
Enterprise sellers manage portfolios of 50–200+ accounts. It's impossible to manually track what's happening at every company, every day. Monitor replaces ad-hoc checking (Google Alerts, LinkedIn notifications, manual scans) with systematic, contextual monitoring powered by Intelligence data.
## Who it's for
**Primary users:**
* **Account executives** and **strategic account managers** who manage a portfolio of accounts and need to know when something changes
**Secondary users:**
* **RevOps teams** who want systematic coverage across territories
* **Sales leaders** who need early warning systems for key accounts
* **Customer success teams** monitoring renewal risk signals
## Modules
Configure what to watch and which accounts to monitor. Define rules, signal types, and thresholds for the changes that matter to you.
View, triage, and act on detected changes. Each alert includes Intelligence context and an explanation of why the change matters.
## Key benefits
1. **Never miss a signal** - Systematic monitoring replaces ad-hoc checking. Every account in your portfolio is watched continuously.
2. **Contextual alerts** - Alerts include Intelligence context. Not just "new job posting at ServiceNow" but "ServiceNow posted 12 new cloud engineering roles this week, which aligns with their strategic priority around platform modernisation."
3. **Configurable** - Define what matters. One monitoring agent might track hiring signals. Another might track competitive moves. You decide what's worth watching.
4. **Scalable** - Monitor hundreds of accounts simultaneously. Coverage doesn't degrade as your portfolio grows.
5. **Actionable** - Alerts are designed for triage: acknowledge, resolve, or dismiss. Integrate with Agent workflows to automate responses.
## How it connects
* **PG:AI Account** provides the account data and enrichment that monitoring evaluates against. Alerts reference account profiles.
* **PG:AI Territory** lets you monitor territory accounts as a group, with alerts surfacing in territory context.
* **PG:AI Studio** workflows can be triggered by monitoring alerts for automated responses to account changes.
# Examples & Prompts
Source: https://docs.getpg.ai/platform/mcp/examples
Real-world prompts for PG:AI MCP in Claude and other clients
Once PG:AI is connected, use natural language. These examples show what the model typically does behind the scenes - you do not need to name tools yourself.
***
## Account research
**Profile and insights**
> Get the SWOT analysis and strategic priorities for Salesforce.
*Uses `company` with `include: ["swot_analysis", "strategic_priorities"]`.*
**Deep dive**
> Give me the full company profile for Tesco - overview, competitors, events, and value pyramid.
*Uses `company` with `include: ["full"]` or multiple sections.*
**Semantic search**
> Search my workspace for anything about cloud migration at Frasers Group.
*Uses `search` with `scope: "organisation"` and a company filter if needed.*
**Jobs**
> What data engineering roles is Harness hiring for in the UK?
*Uses `jobs_search` with `q`, `company`, and `country_code`.*
***
## Accounts and discovery
**List your book**
> List my tracked accounts.
*Uses `accounts` with default `scope: "user"`.*
**Org-wide view**
> Show all accounts in the organisation that mention "fintech".
*Uses `accounts` with `scope: "org"` and `query`.*
**Find new companies**
> Search globally for companies named Snowflake - tell me if we already track them.
*Uses `companies_search` - check `is_in_user_accounts` in the response.*
**Add to workspace**
> Add stripe.com to my tracked accounts.
*Uses `companies_add`, then `get_operation_status` until enrichment completes.*
***
## Contacts
**Find by role**
> Find VP of Engineering contacts at Salesforce.
*Uses `contact_search` with title criteria and company scope.*
**Full profile**
> Get full details for contact ID `abc-123-…`.
*Uses `contact` (after search returns an ID).*
**Save a contact**
> Save Jane Doe, Head of Data at Tesco - [jane.doe@tesco.com](mailto:jane.doe@tesco.com) - to my workspace.
*Uses `create_contact`.*
**Enrich email**
> Find the work email and mobile for contact `abc-123-…`.
*Uses `contact_find_email_phone`, then polls `get_operation_status`, then `contact`.*
***
## Content generation (full flow)
### Single document (e.g. value pyramid)
**You:**
> I want to generate a value pyramid for Salesforce. What templates are available?
**AI:** Calls `templates` with `produces: "document"` (or unfiltered), shows options.
**You:**
> Use the Value Pyramid template for Salesforce. Focus on data platform consolidation.
**AI:**
1. `template_generate` - `template_kind: "canvas"`, `template_id` from step 1, `company: "Salesforce"`, `user_instruction` with your focus
2. `get_operation_status` - poll until `completed`
3. `canvas_get` - `format: "text"` for readable output
### Email or call script
> List email templates, then generate a professional email to the CIO at Airtable about analytics governance.
*Same flow - pick a canvas template where `produces` is `email` or `call_script`.*
### Outreach sequence
> Show sequence templates, then generate a 5-step email sequence for Harness aimed at platform engineering leaders.
1. `templates` with `produces: "sequence"`
2. `template_generate` with `template_kind: "sequence"`
3. `get_operation_status`
4. `sequence_get`
***
## Browse existing content
**List documents**
> What value pyramids have we already generated for Salesforce?
*Uses `canvas_list` with `company` and `content_type: "value_pyramid"`.*
**Read one**
> Open canvas `98b4c290-…` as plain text.
*Uses `canvas_get` with `format: "text"`.*
**Sequences**
> List draft sequences for my territory.
*Uses `sequence_list` with `status: "draft"`.*
***
## Agent conversations (advanced)
> Start a company-scoped agent chat about Microsoft - ask what changed in their earnings narrative this quarter.
*Uses `agent_message_send` with `company: "Microsoft"`, then `get_operation_status`.*
> List my recent agent sessions for Airtable.
*Uses `agent_sessions_list`.*
***
## Multi-step conversation
A natural research → generate chain:
| Turn | You say | Tools used |
| ---- | -------------------------------------------------- | ------------------------------------------------------------------------- |
| 1 | *"List my accounts in software"* | `accounts` |
| 2 | *"Which are hiring for platform roles?"* | `jobs_search` |
| 3 | *"Get insights overview for the top match"* | `company` |
| 4 | *"Generate meeting prep using the right template"* | `templates` → `template_generate` → `get_operation_status` → `canvas_get` |
***
## Tips for better results
Say which angles you care about: *"SWOT and competitors"* rather than *"everything about them"* unless you want `include: ["full"]`.
Names are fuzzy-matched against tracked accounts. Domains (`stripe.com`) also work.
After generation or company add, ask the model to *"check operation status"* if it stops early.
Ask for *"templates I can use to generate"* vs *"canvases we already created"* - different tools.
Adding companies and contact enrichment use credits. If you get a 402 error, check your organisation credit balance in PG:AI.
# MCP Server
Source: https://docs.getpg.ai/platform/mcp/overview
Connect Claude and other AI clients to your PG:AI workspace
The PG:AI MCP server lets AI assistants read your account intelligence, search your workspace, manage accounts and contacts, and generate sales content - through a single secure connection.
## What is MCP?
The **Model Context Protocol** (MCP) is an open standard for connecting AI clients to external tools and data. Instead of copying context into a chat window, the model calls PG:AI tools directly when your prompt needs account data, search, or content generation.
MCP is supported by Claude (Connectors), Cursor, and other MCP-compatible clients. PG:AI hosts the production server at `https://mcp.getpg.ai`.
## What you get
Research, search, accounts, contacts, jobs, content generation, and optional agent sessions
Passive lists of tracked companies and territories
No self-hosting required for production - connect with OAuth or an API key
## How it works
```
Your AI client ── HTTPS ──→ mcp.getpg.ai ──→ PG:AI Data Hub ──→ Your workspace
(Claude, Cursor) (MCP server) (secure proxy) (org-scoped data)
```
When you ask *"What are the latest insights for Salesforce?"*, the model calls the `company` tool (and others if needed). You do not need to name tools in your prompt - the client picks them from the tool list.
## Authentication
| Method | Best for | How org is chosen |
| ---------------------------------- | --------------------------------- | ------------------------------------------------------ |
| **OAuth** (recommended for Claude) | Claude.ai, Claude Team/Enterprise | Your PG:AI login email → your organisation |
| **API key** | Cursor, scripts, automation | Key is tied to one organisation in Settings → API Keys |
API keys start with `pgai_live_`. Send them as `x-api-key: pgai_live_…` or `Authorization: Bearer pgai_live_…`.
## Tool groups (at a glance)
| Group | Tools | Purpose |
| ---------------------- | ------------------------------------------------------------------------- | --------------------------------------------------------------- |
| **Research** | `company`, `search`, `jobs_search` | Profiles, semantic search, job postings |
| **Accounts** | `accounts`, `companies_search`, `companies_add` | List tracked accounts, discover new companies, add to workspace |
| **Contacts** | `contact_search`, `contact`, `create_contact`, `contact_find_email_phone` | Find people, read profiles, save contacts, enrich email/phone |
| **Content - browse** | `canvas_list`, `sequence_list`, `canvas_get`, `sequence_get` | Already-generated documents and sequences |
| **Content - generate** | `templates`, `template_generate`, `get_operation_status` | Discover recipes → start job → poll → read result |
| **Agent** (optional) | `agent_message_send`, `agent_sessions_*` | Full PG:AI agent chat and sessions |
| **Write** | `canvas_update` | Edit an existing canvas record |
See [Tools reference](/platform/mcp/tools) for every parameter. See [Examples](/platform/mcp/examples) for copy-paste prompts.
**Templates vs finished content:** use `templates` to see what you *can* generate. Use `canvas_list` / `sequence_list` to browse what you *already* generated.
## Supported clients
Claude.ai Pro / Team / Enterprise - Custom connector with OAuth ([setup guide](/platform/mcp/quickstart))
Project or global MCP config with an API key
Streamable HTTP at `https://mcp.getpg.ai/mcp` or SSE at `https://mcp.getpg.ai/sse`
## Get started
Claude users: OAuth via a Custom connector. Developers: create an API key in **Settings → API Keys**.
Follow the [Quickstart](/platform/mcp/quickstart) for Claude step-by-step instructions.
Try *"List my tracked accounts"* or *"Get the profile overview for \[company name]"*.
Step-by-step connector setup with screenshots
# MCP Quickstart
Source: https://docs.getpg.ai/platform/mcp/quickstart
Connect PG:AI to Claude and other MCP clients
This guide gets you connected to the hosted PG:AI MCP server at `https://mcp.getpg.ai`. Most users connect **Claude** with OAuth; developers often use an **API key** in Cursor or scripts.
## Before you start
* A PG:AI account with access to at least one organisation
* For Claude: a plan that supports **Connectors** (Pro, Team, or Enterprise)
* For API key auth: permission to create keys in **Settings → API Keys**
***
## Option A - Claude (recommended)
Claude connects through a **Custom connector** and signs in with your PG:AI identity (OAuth). Your organisation is resolved automatically from your PG:AI user email - you do not paste an org ID into Claude.
### Step 1: Open Connectors in Claude
1. Open [Claude.ai](https://claude.ai) and sign in.
2. Go to **Settings** (profile menu → Settings).
3. Open **Connectors** (sometimes under **Integrations** depending on your plan).
**Screenshot needed:** Claude Settings → Connectors page with the **Add connector** button visible.
### Step 2: Add the PG:AI connector
1. Click **Add connector** (or **Add custom connector**).
2. Enter a name, for example **PG:AI**.
3. Enter the server URL:
```
https://mcp.getpg.ai/mcp
```
If your Claude build only supports SSE connectors, use:
```
https://mcp.getpg.ai/sse
```
4. Save the connector.
**Screenshot needed:** The "Add custom connector" form filled in with name **PG:AI** and URL `https://mcp.getpg.ai/mcp`.
### Step 3: Sign in with PG:AI
1. Claude will prompt you to authenticate.
2. Complete the PG:AI / Auth0 login with the **same email** as your PG:AI workspace user.
3. Approve access when asked.
Your PG:AI account email must match your login email. Org membership is resolved server-side - if login succeeds but tools return no data, check that your user exists in the correct organisation in PG:AI.
**Screenshot needed:** OAuth consent / PG:AI login screen during connector authorisation.
### Step 4: Enable the connector in a chat
1. Start a **new** chat in Claude.
2. Open the **+** or tools menu near the message box.
3. Enable the **PG:AI** connector for that conversation.
**Screenshot needed:** New chat with the PG:AI connector toggled on in the tools/connectors menu.
### Step 5: Verify it works
Try these prompts in order:
| Prompt | Expected behaviour |
| --------------------------------------------------- | ------------------------------------------------------------- |
| *"List my tracked accounts"* | Calls `accounts` - returns companies in your territory or org |
| *"Get the company profile overview for Salesforce"* | Calls `company` with `include: ["overview"]` |
| *"What templates can I use to generate content?"* | Calls `templates` - lists canvas and sequence recipes |
If Claude says it cannot reach PG:AI or authentication failed, see [Troubleshooting](#troubleshooting) below.
### Claude Team / Enterprise
An **admin** can add the same connector once under **Admin settings → Connectors**. Each user still connects with their own PG:AI login so data stays scoped to their organisation membership.
***
## Option B - API key (Cursor, scripts, other clients)
Use this when OAuth is not available (for example Cursor or local testing).
### Step 1: Create an API key
In PG:AI go to **Settings → API Keys**
Click **Create API Key**. Name it (e.g. "Cursor MCP"). Enable MCP scopes if prompted.
Copy the key immediately - it starts with `pgai_live_` and is only shown once.
**Screenshot needed:** PG:AI Settings → API Keys with **Create API Key** and scope selection visible.
Treat API keys like passwords. Revoke compromised keys in Settings immediately.
### Step 2: Configure Cursor
Create or edit `.cursor/mcp.json` in your project (or add via **Cursor Settings → MCP**):
```json theme={null}
{
"mcpServers": {
"pgai": {
"url": "https://mcp.getpg.ai/mcp",
"headers": {
"x-api-key": "pgai_live_YOUR_KEY_HERE"
}
}
}
}
```
You can also use `Authorization: Bearer pgai_live_YOUR_KEY_HERE` instead of `x-api-key`.
Reload Cursor (**Cmd/Ctrl + Shift + P** → **Developer: Reload Window**). You should see **pgai** as a connected MCP server.
### Step 3: Verify with tools/list
Any MCP client can list tools with a JSON-RPC `tools/list` call. Example with curl:
```bash theme={null}
curl -s -X POST https://mcp.getpg.ai/mcp \
-H "x-api-key: pgai_live_YOUR_KEY" \
-H "Accept: application/json, text/event-stream" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
```
You should see tools such as `company`, `search`, `accounts`, and `templates`.
***
## Connection details (reference)
| Setting | Value |
| ------------------- | --------------------------------------------------------------- |
| Streamable HTTP URL | `https://mcp.getpg.ai/mcp` |
| SSE URL | `https://mcp.getpg.ai/sse` |
| OAuth metadata | `https://mcp.getpg.ai/.well-known/oauth-protected-resource` |
| API key header | `x-api-key: pgai_live_…` or `Authorization: Bearer pgai_live_…` |
***
## Troubleshooting
* Confirm you completed OAuth with the same email as your PG:AI user.
* Try removing and re-adding the connector.
* For Team/Enterprise, confirm an admin enabled custom connectors.
* API key: check the key starts with `pgai_live_` and was not revoked.
* Claude: ensure the connector is **enabled for the current chat**.
* Enable the connector in the chat's tools menu (not only in Settings).
* Ask a PG:AI-specific question: *"Use PG:AI to list my accounts"*.
Template discovery depends on the Data Hub and Xano template routes. If you see a UUID validation error, contact support - this is a known routing issue being fixed on the backend.
* Reload the window after editing `mcp.json`.
* Check JSON syntax and that the URL has no trailing slash issues.
Generation and enrichment are asynchronous. After `template_generate`, `companies_add`, or `contact_find_email_phone`, poll `get_operation_status` every few seconds until `status` is `completed` or `failed`.
***
## Next steps
All 22 tools and parameters
Prompts for research, contacts, and generation
Passive company and territory lists
# Resources
Source: https://docs.getpg.ai/platform/mcp/resources
Passive MCP resources - tracked companies and territories
MCP **resources** are read-only data URIs your client can fetch for background context. Unlike tools, they do not perform actions - they provide lists your AI can use to resolve company names and understand workspace structure.
Not every client surfaces resources in the UI. Claude may use them implicitly when relevant. Tools such as `accounts` and `company` are more reliable for explicit requests.
## Available resources
**Tracked companies**
All companies your organisation tracks in PG:AI (id, name, domain).
Helps the model resolve *"Tell me about Airtable"* to the correct account UUID.
**Territories**
Territories configured for your organisation.
Useful for prompts like *"What accounts are in my EMEA territory?"* when combined with tools.
## Resources vs tools
| | Resources | Tools |
| ------------- | ----------------------------- | ----------------------------------- |
| **Purpose** | Static lists for context | Query and action |
| **When used** | Client-driven background read | When the model needs data or writes |
| **Examples** | `pgai://companies` | `accounts`, `company`, `search` |
For most workflows, prefer **`accounts`** (filtered, paginated, enrichment metadata) over the companies resource. Use **`company`** for rich profile data on one account.
## Example shapes
Responses are JSON. Exact fields may include additional metadata from your workspace.
### Companies
```json theme={null}
[
{
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"name": "Salesforce",
"domain": "salesforce.com"
},
{
"id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
"name": "Harness",
"domain": "harness.io"
}
]
```
### Territories
```json theme={null}
[
{
"id": "t1u2v3w4-x5y6-7890-zabc-def123456789",
"name": "EMEA Enterprise",
"company_count": 45
}
]
```
Start exploration with *"List my tracked accounts"* (`accounts` tool) - it returns more useful fields than the passive resource alone.
# Tools Reference
Source: https://docs.getpg.ai/platform/mcp/tools
Complete reference for all PG:AI MCP tools
PG:AI exposes **22 tools** through MCP. Your AI client selects tools automatically - you normally interact in natural language. This page documents names, behaviour, and parameters for builders and power users.
Tool names are plain snake\_case (`company`, `templates`) - there is no `pgai_` prefix.
## Async operations
Several tools start background jobs and return an `operation_id`:
| Tool | Then poll with | Then read result with |
| -------------------------- | ---------------------- | ------------------------------------ |
| `template_generate` | `get_operation_status` | `canvas_get` or `sequence_get` |
| `companies_add` | `get_operation_status` | `accounts` or `company` |
| `contact_find_email_phone` | `get_operation_status` | `contact` |
| `agent_message_send` | `get_operation_status` | `agent_sessions_get` (if applicable) |
Poll every \~2 seconds while `status` is `queued` or `running`. Status values: `queued`, `running`, `completed`, `failed`, `cancelled`.
***
## Content generation (4-step flow)
Use this flow for documents, emails, call scripts, analysis, and sequences.
```
templates → template_generate → get_operation_status → canvas_get | sequence_get
(STEP 1) (STEP 2) (STEP 3) (STEP 4)
```
| Step | Tool | Purpose |
| ---- | ---------------------- | --------------------------------------------------------------------------------------------------------------------- |
| 1 | `templates` | List **recipes** (not finished content). Returns `template_id`, `template_kind` (`canvas` \| `sequence`), `produces`. |
| 2 | `template_generate` | Start generation for a company. Requires `template_id`, `template_kind`, and `company` (name, domain, or UUID). |
| 3 | `get_operation_status` | Poll with `operation_id` until `completed`. |
| 4a | `canvas_get` | Read a single deliverable when `template_kind` was `canvas`. Use `format: "text"` for readable prose. |
| 4b | `sequence_get` | Read steps when `template_kind` was `sequence`. |
Do not use `canvas_list` or `sequence_list` for step 1 - those list **already generated** content, not recipes.
### `templates`
List generation recipes (workspace + PG:AI templates).
| Parameter | Type | Default | Description |
| ---------- | ------------------------------------------------------------------ | ------- | -------------------------- |
| `filter` | `org` \| `pgai` \| `all` | `all` | Whose templates to include |
| `category` | string | - | Filter by category |
| `produces` | `document` \| `email` \| `call_script` \| `analysis` \| `sequence` | - | Filter by output type |
| `q` | string | - | Search template titles |
| `page` | number | 1 | Page number |
| `per_page` | number | 50 | Page size |
### `template_generate`
Start async generation from a template.
| Parameter | Type | Required | Description |
| ------------------ | ---------------------- | -------- | ------------------------------------------------------- |
| `template_id` | string | Yes | From `templates` |
| `template_kind` | `canvas` \| `sequence` | Yes | Must match the row from `templates` |
| `company` | string | Yes\* | Company name, domain, or UUID |
| `company_name` | string | Yes\* | Alias for `company` |
| `company_id` | string | Yes\* | Company UUID |
| `contact_id` | string | No | Personalise for a contact |
| `persona_id` | string | No | Persona for sequence generation |
| `inputs` | object | No | Canvas template-specific fields (topic, audience, etc.) |
| `user_instruction` | string | No | Free-text context or answers to planning questions |
\* One of `company`, `company_name`, or `company_id` is required.
### `canvas_get`
Read one finished canvas (document, email, call script, analysis).
| Parameter | Type | Default | Description |
| ----------- | ---------------- | ------- | ------------------------------------------------------------------ |
| `canvas_id` | string | Yes | From `template_generate`, `get_operation_status`, or `canvas_list` |
| `format` | `json` \| `text` | `json` | `text` returns LLM-friendly plain text |
### `sequence_get`
Read one finished sequence (metadata + steps).
| Parameter | Type | Required | Description |
| ------------- | ------ | -------- | -------------------------------------------------------------------- |
| `sequence_id` | string | Yes | From `template_generate`, `get_operation_status`, or `sequence_list` |
### `canvas_list`
Browse **already generated** canvases.
| Parameter | Type | Description |
| ----------------------------------------- | ------ | -------------------------------------------------------------------------- |
| `company` / `company_name` / `company_id` | string | Scope to one company |
| `contact_id` | string | Filter by contact |
| `content_type` | enum | `notes`, `email`, `call_script`, `document`, `value_pyramid`, `three_whys` |
| `q` | string | Search |
| `page`, `per_page` | number | Pagination |
### `sequence_list`
Browse **already generated** sequences.
| Parameter | Type | Description |
| ----------------------------------------- | ------ | ---------------------------------------------------- |
| `company` / `company_name` / `company_id` | string | Scope to one company |
| `contact_id`, `persona_id` | string | Filters |
| `status` | enum | `draft`, `active`, `paused`, `completed`, `archived` |
| `channel` | string | e.g. `email`, `call` |
| `q`, `sort_by`, `sort_order` | | Search and sort |
| `page`, `per_page` | number | Pagination |
### `canvas_update`
Update an existing canvas (title, body, sections, tags). At least one field besides `canvas_id` is required.
***
## Company research
### `company`
Rich company profile for one **tracked** company.
| Parameter | Type | Default | Description |
| ----------------------------------------- | --------- | -------------- | ------------------------------------------- |
| `company` / `company_name` / `company_id` | string | - | Name, domain, or UUID (fuzzy match on name) |
| `include` | string\[] | `["overview"]` | Profile sections to return |
| `exclude` | string\[] | - | Sections to omit after `include` |
| `sources` | boolean | - | Include source citations |
**Include sections:** `overview`, `key_executives`, `divisions`, `geographical_operations`, `swot_analysis`, `competitors`, `industry_insights`, `strategic_priorities`, `digital_strategies`, `risks`, `goals`, `insights_scores`, `events`, `value_pyramid`, `three_whys`, `discovery_questions`, `how_they_make_money`, `how_they_lose_money`, `custom_insights`, `employee_groups`, `favourite_technologies_count`, `territory_custom_scores`, `content`, `canvas`, or `full` for everything.
### `search`
**Semantic** search across PG:AI vector indexes (not keyword grep).
| Parameter | Type | Required | Description |
| ---------------------- | ----------------------------- | ---------------------- | -------------------------------------------------------------------- |
| `query` | string | Yes | Search text |
| `scope` | `organisation` \| `companies` | Yes | `organisation` = all tracked accounts; `companies` = listed IDs only |
| `company_ids` | string\[] | When scope=`companies` | Company UUIDs |
| `sources` | string\[] | No | Limit indexes (see below) |
| `per_source` | number | 25 | Max hits per source (max 50) |
| `page` | number | 1 | Page |
| `date_from`, `date_to` | string | No | ISO date bounds |
**Sources:** `public_docs`, `web_pages`, `organisation_company_docs`, `organisation_docs`, `pgai_insights`, `contacts`, `technologies`, `conversations`, `company_content`, `company_jobs`.
### `jobs_search`
Search job postings across tracked companies.
| Parameter | Type | Description |
| ----------------------------------------- | ------ | --------------------------------------------------- |
| `company` / `company_name` / `company_id` | string | Scope to one company |
| `q` | string | Search title and description |
| `seniority` | enum | `c_level`, `staff`, `senior`, `junior`, `mid_level` |
| `country_code` | string | ISO 2-letter code |
| `page`, `per_page` | number | Pagination |
***
## Accounts
### `accounts`
List companies **already in your workspace**.
| Parameter | Type | Default | Description |
| --------------------------- | --------------- | ------- | ----------------------------------------- |
| `scope` | `user` \| `org` | `user` | `user` = your territory; `org` = org-wide |
| `query` / `company_name` | string | - | Search name or domain |
| `industry`, `country`, etc. | | | Additional filters |
| `page`, `per_page` | number | 1, 25 | Pagination |
### `companies_search`
Discover companies **globally** (workspace + external directory). Returns `is_in_org_accounts` and `is_in_user_accounts` flags.
| Parameter | Type | Description |
| ----------------------------------- | ------- | ----------------------------------------- |
| `q` | string | Company name or domain |
| `industry_ids`, `country_ids`, etc. | arrays | Filters |
| `include_external` | boolean | Include external directory (default true) |
| `page`, `per_page` | number | Pagination |
### `companies_add`
Add companies to the workspace (max **5 per call**). Async and **credit-gated** - poll `get_operation_status`. HTTP 402 means credits exhausted.
| Parameter | Type | Description |
| ------------------------------------------------------------------ | ----- | ----------------------------- |
| `company` / `company_name` / `website` / `domain` / `companies_id` | | Single company |
| `companies` | array | Up to 5 companies in one call |
***
## Contacts
### `contact_search`
Search contacts in your tracked workspace.
| Parameter | Type | Description |
| -------------------------------------------- | ------ | ----------------------------------------------------- |
| `search_definition` | object | SearchDefinition v1 (`entity: "contact"`) - preferred |
| `company` / `company_ids` | | Scope to company(ies) |
| `titles`, `personas`, `regions`, `seniority` | | Legacy filters (still supported) |
| `max_contacts`, `page`, `per_page` | number | Limits |
### `contact`
Full contact record by UUID. Use `contact_search` first to find IDs.
| Parameter | Type | Required |
| ------------ | ------ | -------- |
| `contact_id` | string | Yes |
### `create_contact`
Save a contact to a tracked company. Use `companies_add` first if the company is not tracked.
| Parameter | Type | Required |
| ----------------------------------------- | ------ | ------------ |
| `company` / `company_name` / `company_id` | string | Yes |
| `contact_name` or `contact_email` | string | Yes (one of) |
| `contact_title`, `contact_linkedin` | string | No |
### `contact_find_email_phone`
Enrich email and/or phone for an existing contact. Async and **credit-gated**.
| Parameter | Type | Default |
| ------------ | ---------------------------------------- | ------------------ |
| `contact_id` | string | Required |
| `type` | `email` \| `phone` \| `email_and_mobile` | `email_and_mobile` |
***
## Operations
### `get_operation_status`
Poll any async job by `operation_id`.
| Parameter | Type | Required |
| -------------- | ------ | -------- |
| `operation_id` | string | Yes |
***
## Agent (advanced)
These tools talk to the full PG:AI agent (chat, plan, sessions). They are optional - most sellers use `template_generate` for content instead.
### `agent_message_send`
Send a message to the agent queue. Returns `operation_id`.
| Parameter | Type | Description |
| ----------------------------------------- | --------------------------- | -------------------------------------------- |
| `message` | string | User message |
| `session_id` | string | Continue existing session |
| `company` / `company_name` / `company_id` | string | Company-scoped agent |
| `mode` | `ask` \| `plan` \| `studio` | Workspace mode (ignored when company is set) |
### `agent_sessions_create`
Create a session (`chat`, `plan`, `document`, `email`, `workspace`, `project`, `canvas_settings`).
### `agent_sessions_list`
List sessions with optional company filter.
### `agent_sessions_get`
Fetch one session (metadata + transcript) by `session_id`.
***
## Permissions
| Scope | Allows |
| ----------- | -------------------------------------------------------------------------- |
| `mcp:read` | Read tools (`company`, `search`, `accounts`, `templates`, etc.) |
| `mcp:write` | Write tools (`create_contact`, `companies_add`, `template_generate`, etc.) |
API keys are issued with appropriate scopes in Settings. OAuth users receive scopes from their PG:AI account.
***
## Not available via MCP (yet)
The following exist in the PG:AI app but are **not** exposed as MCP tools today:
* Monitoring agents and alert configuration
* Territory admin and scoring configuration
If you need REST access to these areas, use the [PG:AI API](https://api.getpg.ai).
# Account Monitoring
Source: https://docs.getpg.ai/playbooks/account-monitoring
Stay on top of changes across your accounts automatically - without manually checking
Set up monitoring so you know when something changes at your accounts - strategy shifts, leadership moves, hiring surges, technology changes - without manually checking each one.
**Who this is for:** AEs, account managers, sales leaders, CS managers.
**Time:** 10 minutes to set up. Then it runs continuously.
**What you'll have at the end:** Monitoring agents watching your key accounts and alerting you when something changes.
## Step 1: Decide What to Monitor
Go to **Monitor → Monitoring Agents**. You can monitor for different types of changes:
* **Strategy changes** - Priorities or goals shift (e.g. a company announces a new strategic initiative)
* **Leadership changes** - Key stakeholders move roles, new decision-makers join
* **Hiring changes** - Significant shifts in hiring patterns (e.g. hiring surge in a new area)
* **Technology changes** - New technologies appearing in job postings, existing ones declining
* **Financial changes** - Earnings surprises, acquisitions, restructuring announcements
## Step 2: Configure Your Agents
Create monitoring agents for the change types that matter most to your role:
**For AEs managing active deals:**
* Leadership changes at the account (your champion might leave)
* Competitive technology changes (new competitor showing up in job postings)
* Strategy shifts that affect your deal positioning
**For account managers / CS:**
* Strategy changes (priorities shifting means your value prop might need updating)
* Leadership changes (new stakeholders to build relationships with)
* Expansion signals (new divisions, new hiring areas)
**For sales leaders:**
* Aggregate changes across the team's portfolio
* Competitive entries across multiple accounts
* Major financial events (acquisitions, earnings)
## Step 3: Set Scope
Choose which accounts to monitor:
* **Tier 1 accounts** - Monitor everything. These are your most important accounts.
* **Active deals** - Monitor leadership and competitive changes. These directly affect deal outcomes.
* **Customer accounts** - Monitor strategy and expansion signals. These drive retention and growth.
* **Full territory** - Monitor for major events only. Avoid alert fatigue.
## Step 4: Review and Act
When alerts come in:
* **Triage** - Is this actionable right now? Some changes are informational, others require immediate action.
* **Update your plan** - If a key stakeholder changed, update your stakeholder map. If priorities shifted, revisit your positioning.
* **Engage** - Some changes create engagement opportunities. A new VP joining is a reason to reach out. A strategy shift is a reason to reframe your value proposition.
## Tips
* **Don't monitor everything on every account.** That leads to alert fatigue. Be selective about what matters for each tier.
* **Review alerts weekly.** Set a cadence - Monday morning, review the week's alerts across your portfolio.
* **Use alerts as conversation starters.** "I noticed you recently brought on a new VP of Engineering" is a natural, informed opening.
## Related
Build plans that stay current through monitoring
Reference guide for configuring monitoring agents
Reference guide for alert management
# Account Planning
Source: https://docs.getpg.ai/playbooks/account-planning
Build comprehensive account plans grounded in real intelligence - not CRM fields and guesswork
Build an account plan that goes beyond what's in the CRM. This playbook walks you through creating a data-driven plan for any account - using PG:AI intelligence to identify opportunities, map stakeholders, understand competitive dynamics, and build an engagement strategy.
**Who this is for:** AEs, SCs, strategic account managers, anyone responsible for a named account.
**Time:** 30-45 minutes for a thorough plan (vs hours or days of manual research, if it gets done at all).
**What you'll have at the end:** A structured account plan with: strategic context, stakeholder map, competitive landscape, opportunity identification, engagement strategy, and next steps - all grounded in real data.
## The Problem This Solves
Most teams have account plans for maybe 10-15% of their territory. The rest get worked on gut feel and whatever the rep remembers from the last conversation. Even the plans that exist are often just CRM fields - industry, employee count, deal stage - with no strategic depth.
PG:AI changes this by giving you the intelligence to build a real plan for any account in under an hour. And because the intelligence updates automatically, the plan stays current without manual refresh.
## Step 1: Strategic Context (10 min)
Start with **Intelligence → Strategic Insights**. You're building the "why should we be talking to this account" section of your plan.
**Strategic Priorities** - What are they focused on? List the 2-3 priorities most relevant to what you sell. For each, note:
* The priority itself (e.g. "Accelerating cloud migration across all business units")
* Why it matters for your engagement (e.g. "Creates demand for our data integration capabilities")
* Source and recency (e.g. "CEO mentioned in Q3 2025 earnings call")
**Goals** - What are they trying to achieve? Pull the measurable targets that give you specificity: revenue targets, growth milestones, cost reduction goals, market expansion plans.
**SWOT** - Scan for weaknesses and threats that your solution addresses, and opportunities that align with your value proposition.
**Division Intelligence** - For enterprise accounts, identify which business units to target. Note which divisions have priorities that align with what you sell and which don't. This prevents you wasting time on the wrong part of the organisation.
**Industry Overview** - What's happening in their industry? Are there sector-wide trends creating urgency? This gives you context for positioning.
Use **Canvas** to build your plan as you go. Open a new Canvas document and structure it with sections. Paste key points as you review each intelligence module - by the end, your plan is already half-written.
## Step 2: Stakeholder Map (10 min)
Go to **Intelligence → Contacts & Org Chart**. You're building the "who do we need to engage" section.
**Identify the buying committee:**
* **Economic buyer** - Who has budget authority? Usually a VP or C-level. Check the org chart for the senior person in the relevant division.
* **Champions** - Who would benefit most from your solution and would advocate internally? Often a director or senior manager who feels the pain daily.
* **Technical evaluators** - Who will assess the product? Look for roles like Solutions Architect, Technical Lead, or whoever runs POCs.
* **Users** - Who would actually use the product day-to-day? These are your adoption champions post-sale.
* **Blockers** - Who might object? Procurement, security, or someone who owns a competing tool internally.
For each key stakeholder, note:
* Name, title, role in the buying process
* Career history (where they came from - relevant if they've used your product or a competitor before)
* Reporting line (who do they need to convince?)
**Map relationships** using the org chart. Who reports to whom? Where are there gaps in your access? If you're engaged with a manager but the VP makes the decision, you need a plan to get to the VP.
## Step 3: Competitive Landscape (5 min)
Go to **Intelligence → Tech Stack**. You're building the "what are we up against" section.
**Current technology** - What do they use that's relevant to your space?
* **Competitors installed** - Your [favourite technologies](/configuration/favourite-technologies) are highlighted. Note which competitors they use, the confidence level, and whether adoption is growing or declining.
* **Complementary tech** - What else are they using that integrates with or adjacent to what you sell? This helps with positioning ("you already use X, and we integrate natively with it").
* **Gaps** - What are they NOT using that they probably should be? Sometimes the absence of a technology is the signal - they have a gap you can fill.
**Job posting signals** - Check **Jobs & Hiring Signals** for roles that indicate they're building a capability related to your solution. Hiring 10 people in a specific area means they're investing. That's a buying signal.
## Step 4: Opportunity Identification (5 min)
Now synthesise what you've learned. In your Canvas document, create an "Opportunities" section and answer:
* **Where is the fit?** Which strategic priorities does your solution directly address?
* **Where is the urgency?** Which goals have timelines or measurable targets that create pressure to act?
* **Where is the pain?** Which SWOT weaknesses or threats does your solution mitigate?
* **Where is the expansion?** (For existing customers) Which divisions or business units are you not engaged with that have relevant priorities?
* **What's the competitive angle?** If they're using a competitor, what's the displacement opportunity? If greenfield, what's the build-vs-buy argument?
You can also ask the **Agent** to help:
> "Based on everything you know about \[Company], where are the top 3 opportunities for us to engage? Consider their strategic priorities, technology landscape, and hiring patterns. We sell \[your product description]."
## Step 5: Engagement Strategy (5 min)
Build out the "what are we going to do" section:
**Immediate next steps:**
* Who do we contact first? (Usually the champion, not the economic buyer)
* What's our opening message? Use **Sales Engagement → Value Pyramid** for account-specific positioning.
* What discovery questions do we lead with? Use **Sales Engagement → Discovery Questions** for account-tailored questions.
**Short-term plan (next 30 days):**
* Which stakeholders do we need to engage?
* What content do we need to create? (Proposals, business cases, technical docs)
* What proof points are relevant? (Customer evidence from similar companies or industries)
**Success criteria:**
* What would "this account is progressing" look like in 30/60/90 days?
* What's the target deal size and timeline?
## Step 6: Set Up Monitoring (2 min)
Don't let the plan go stale. Go to **Monitor → Monitoring Agents** and set up alerts for this account:
* **Strategy changes** - Alert when priorities or goals shift
* **Leadership changes** - Alert when key stakeholders move roles
* **Hiring changes** - Alert when hiring patterns change significantly
* **Competitive changes** - Alert when new technologies appear or existing ones decline
This way, your plan stays current without you manually checking. When something changes, you'll know.
→ [How to set up monitoring](/playbooks/account-monitoring)
## What You Should Have Now
A Canvas document (or whatever format you prefer) containing:
1. **Strategic context** - Top priorities, goals, SWOT highlights, division analysis
2. **Stakeholder map** - Key people, their roles in the buying process, relationships, gaps
3. **Competitive landscape** - Current tech, competitors, complementary tech, gaps
4. **Opportunities** - Where you fit, where there's urgency, where the pain is
5. **Engagement strategy** - Next steps, 30-day plan, success criteria
6. **Monitoring** - Alerts set up for changes
This plan is now shareable with your team, referenceable before meetings, and automatically kept current through PG:AI's monitoring and continuous enrichment.
## Tips
* **Do this for your top 10 accounts first.** Not every account needs a full plan. Start with the ones where deep engagement matters most - strategic accounts, active deals, renewals coming up.
* **Update, don't rebuild.** Because PG:AI intelligence refreshes automatically, you don't need to redo the plan from scratch. Just review it before key meetings and update your engagement strategy.
* **Share with your SC/SE.** If you're working an account with a Solutions Consultant, share the Canvas document. Having everyone aligned on the same intelligence dramatically improves deal quality.
* **Use this for QBR prep too.** The same plan structure works for preparing QBR presentations for existing customers - just shift the emphasis from "why buy" to "what value we've delivered and where to expand."
## Related
Quick prep for a specific meeting (15-20 min)
Deep dive on the competitive landscape at an account
Prioritise which accounts to plan first
# Competitive Research
Source: https://docs.getpg.ai/playbooks/competitive-research
Understand the competitive landscape at a specific account and position effectively
Know what technology an account uses, where competitors are installed, and how to position against them - before you walk into the conversation.
**Who this is for:** AEs, SCs, BDRs preparing for competitive deals.
**Time:** 10-15 minutes per account.
**What you'll have at the end:** A clear picture of the competitive landscape at a specific account, with positioning recommendations.
## Step 1: Check the Tech Stack (3 min)
Go to **Intelligence → Tech Stack** for the account.
Your [favourite technologies](/configuration/favourite-technologies) are highlighted. Look for:
* **Direct competitors** - Are they installed? What's the confidence level? Is adoption growing or declining?
* **Adjacent technologies** - What else are they using in your space? This tells you how they've built their stack and where your product fits.
* **Trends** - Technologies appearing more frequently in recent job postings are being invested in. Declining technologies might signal a replacement window.
## Step 2: Understand Why They'd Switch (5 min)
Go to **Strategic Insights** and look for priorities that create competitive pressure:
* Are they consolidating vendors? ("Reduce tool sprawl" = opportunity to replace a competitor with your platform)
* Are they investing in a new capability? (New initiative might need a different tool than what they have)
* Are they under cost pressure? (Cheaper or more efficient alternative wins)
* Are they scaling? (The competitor might not scale with them)
Cross-reference with **Financial Intelligence** - are they growing, flat, or contracting? This affects their appetite for change.
## Step 3: Generate Competitive Positioning (5 min)
Use the **Agent**:
> "I'm going into a deal at \[Company] where they currently use \[Competitor]. Based on their strategic priorities and technology landscape, how should I position against \[Competitor]? Give me 3 key differentiation points that are specific to this account."
The agent will combine the account's strategic context with the competitive landscape to give you account-specific positioning - not generic battle card points.
## Step 4: Identify Displacement Champions
Go to **Contacts & Org Chart** and look for:
* People who recently joined from companies that use your product (they've seen the alternative)
* People in roles that would benefit from switching (power users of the competitor)
* New leaders who might bring a different technology preference
## Tips
* **Displacement is a different conversation than greenfield.** If they already use a competitor, you're asking them to switch - which is harder than buying something new. Lead with what's wrong with the status quo, not with your features.
* **Reference the competitor by name in conversation.** "I see you're using \[Competitor]" shows you've done your homework and opens the discussion naturally.
* **Watch for multi-vendor situations.** Some accounts use multiple tools in the same space. That's often a sign of organic sprawl that a platform play can consolidate.
## Related
Full meeting prep including competitive context
Build a complete plan including competitive strategy
Reference guide for the tech stack module
# Content Generation
Source: https://docs.getpg.ai/playbooks/content-generation
Create account-relevant emails, briefs, plans, and documents grounded in real intelligence
Generate content that references what the account actually cares about - not generic templates with the company name swapped in.
**Who this is for:** AEs, BDRs, SCs, anyone creating account-specific content.
**Time:** 2-5 minutes per piece of content.
## Using the Agent for Quick Content
For a single email, talking point, or question, use **Agent → Agent**:
**Cold outreach:**
> "Write a cold email to \[Name], \[Title] at \[Company]. Reference their priority around \[X]. We sell \[what you sell]. Under 100 words."
**Follow-up after a meeting:**
> "Write a follow-up email after my meeting with \[Company]. We discussed \[topic]. They're concerned about \[challenge]. Summarise what we covered and propose next steps."
**Executive summary:**
> "Write a one-paragraph executive summary of \[Company] for my manager. Focus on why they're a good fit for us and what the opportunity is."
**Discovery questions:**
> "Give me 5 discovery questions for my meeting with \[Company]'s \[Title]. They're prioritising \[X] and currently use \[competitor]. Focus on understanding their pain with the current approach."
## Using Canvas for Structured Documents
For longer or more structured content - account plans, meeting briefs, proposals - use **Agent → Canvas**:
1. Open Canvas and create a new document
2. Choose a template or start blank
3. Ask the AI to generate content with specific instructions
4. Edit, refine, and share
**Example prompts for Canvas:**
Account plan:
> "Create an account plan for \[Company]. Include strategic context, stakeholder map, competitive landscape, and engagement strategy. We sell \[what you sell]."
Meeting prep brief:
> "Create a one-page meeting prep brief for my call with \[Name] at \[Company] tomorrow. Include their top priorities, the competitive landscape, stakeholders, and 5 discovery questions."
Business case:
> "Draft a business case for \[Company] based on their strategic priorities. Frame the problem they have, the solution we provide, the expected outcomes, and the investment."
## Using Templates
If your team has configured **workflow templates** in Configuration, you can use pre-built templates that follow your team's standard format. These are especially useful for:
* Standardised email outreach sequences
* Account plan templates matching your methodology
* Meeting prep formats your team expects
* QBR decks following your company's structure
## Tips
* **The AI is only as good as the intelligence.** If an account hasn't been enriched, the content will be generic. Make sure the account is in PG:AI and enriched before generating content.
* **Edit before sending.** AI-generated content is a starting point. Add your own voice, remove anything that doesn't feel right, and make it yours.
* **Use datasets for better output.** If you've uploaded your product briefs and messaging to [Configuration → Datasets](/configuration/datasets), the AI will use your actual language and positioning.
## Related
Full prospecting workflow including content creation
Reference guide for the Canvas document workspace
Set up reusable templates for your team
# Meeting Preparation
Source: https://docs.getpg.ai/playbooks/meeting-preparation
Prepare for any customer meeting in minutes with deep account context
Walk into every meeting knowing what the account cares about, who you're talking to, what technology they use, and what to say. This playbook takes you from "I have a meeting tomorrow" to "I'm fully prepared" in about 20 minutes.
**Who this is for:** AEs, SCs, account managers, anyone with a customer or prospect meeting.
**Time:** 15-20 minutes (vs 60-90 minutes of manual research).
**What you'll have at the end:** A clear understanding of the account's priorities, the people you're meeting, their competitive landscape, and a set of informed talking points and discovery questions.
## Before You Start
Make sure the account is in PG:AI and has been enriched. If it's a new account, add it first - enrichment takes 5-10 minutes and uses 1 credit.
If the account was added a while ago, the intelligence is already up to date - PG:AI refreshes automatically. No need to re-enrich.
## Step 1: Review Strategic Priorities (3 min)
Open the account and go to **Intelligence → Strategic Insights**.
Read the **Strategic Priorities** section first. These are the top things this company is focused on right now - extracted from earnings calls, filings, press releases, and news. Each priority has a summary and source links.
**What to look for:**
* Which priorities relate to what you sell? If you're selling data infrastructure and they're prioritising "cloud migration across all business units," that's your opening.
* Are there priorities that create urgency? Things like "reduce costs by 15% in FY26" or "consolidate vendor landscape" signal budget pressure or active buying behaviour.
* Any surprises? Something you didn't know about the account that changes how you'd approach the conversation.
Then scan **Goals** - these are the measurable targets. Revenue goals, margin targets, expansion milestones. These give you the language to use in conversation: "I noticed you're targeting 30% growth in EMEA this year..."
For large enterprises, check **Division Intelligence** to make sure you're targeting the right business unit. A company might have five divisions with five different sets of priorities. Make sure you're talking about the one that matters to the person you're meeting.
## Step 2: Check the Competitive Landscape (2 min)
Go to **Intelligence → Tech Stack**.
Your [favourite technologies](/configuration/favourite-technologies) are highlighted automatically. Look for:
* **Your competitors** - are they already using a competitor product? If so, this is a displacement conversation, not a greenfield one. Adjust your approach.
* **Complementary technologies** - what else are they using that integrates with or relates to what you sell?
* **Trends** - are any technologies growing or declining in their job postings? A declining technology might signal an upcoming replacement decision.
## Step 3: Know Who You're Meeting (3 min)
Go to **Intelligence → Contacts & Org Chart**.
Find the people you're meeting. For each person, check:
* **Their role and seniority** - are you talking to the decision-maker, a champion, or an evaluator?
* **Career history** - where did they come from? If they joined from a company that uses your product, that's relevant context.
* **Reporting structure** - who do they report to? Who else is in their team? This helps you understand the buying committee.
If you're meeting someone new and don't know much about them, the org chart shows where they sit and who surrounds them.
If the person you're meeting isn't in PG:AI's contacts yet, check their LinkedIn profile directly. But the org chart context (who they report to, what division they're in) is often more valuable than their individual profile.
## Step 4: Check for Recent Changes (2 min)
Quick scan of two areas:
**Jobs & Hiring Signals** - What are they hiring for? New roles in a specific area often signal investment or a new initiative. If they're hiring 15 data engineers, they're building something. If they're hiring a new VP of Sales, there might be a GTM transformation coming.
**Financial Intelligence** (for public companies) - Any recent earnings? Revenue trajectory? Analyst commentary? This gives you the macro context for the conversation.
## Step 5: Generate Your Prep Sheet (5 min)
Now bring it all together. Go to **Agent → Agent** or **Agent → Canvas**.
**Option A: Quick prep via Agent**
Ask the agent a specific question:
> "I have a meeting tomorrow with \[Name], \[Title] at \[Company]. They're evaluating solutions for \[use case]. Based on what you know about this account, what should I focus on? Give me 3 talking points and 5 discovery questions."
The agent will draw on all the intelligence - priorities, tech stack, financials, contacts - and give you a tailored response.
**Option B: Structured prep via Canvas**
Open Canvas and create a new document. Use a meeting prep template or ask the AI to generate one:
> "Create a meeting prep brief for my call with \[Company] tomorrow. Include: their top 3 strategic priorities relevant to what we sell, the competitive landscape (what they use today), key stakeholders and their roles, 5 discovery questions, and 3 value propositions I should lead with."
Canvas produces a structured document you can reference during the meeting or share with your team.
## Step 6: Review Sales Engagement Content (3 min)
Go to **Intelligence → Sales Engagement** for ready-made content:
* **Value Pyramid** - How your solution maps to their specific priorities. Not generic - tailored to what this account cares about.
* **Discovery Questions** - Account-specific questions grouped by topic. These reference real priorities and challenges, not generic SPIN questions.
* **Custom Insights** - If your team has configured custom insight topics, check these for specific intelligence relevant to your conversation.
## What You Should Have Now
After 15-20 minutes, you should know:
* **What they care about** - their top strategic priorities and measurable goals
* **Who you're talking to** - their role, background, and where they sit in the org
* **What technology they use** - competitors installed, complementary tech, trends
* **What's changed recently** - new hires, financial shifts, strategy changes
* **What to say** - tailored talking points, discovery questions, and value propositions
## Tips
* **Don't try to use everything.** Pick the 2-3 most relevant insights and weave them into conversation naturally. "I noticed you're prioritising X - how is that going?" is more effective than reciting a briefing document.
* **Reference sources when it builds credibility.** "I saw in your last earnings call that your CEO mentioned..." shows you've done your homework.
* **Share your prep with the team.** If you're going in with an SC or another AE, share the Canvas document or talk through the key points beforehand. Consistent preparation across the team is one of the biggest advantages of using PG:AI.
* **Set up a Monitor.** After the meeting, if this is a key account, [set up a monitoring agent](/playbooks/account-monitoring) so you're alerted when something changes.
## Related
Go deeper - build a full account plan with stakeholder maps and engagement strategy
Prepare executive-ready materials for high-stakes meetings
Deep dive into the competitive landscape at a specific account
# New Territory Ramp
Source: https://docs.getpg.ai/playbooks/new-territory-ramp
Get up to speed on a new territory fast - with intelligence on every account from day one
Just got a new territory? New hire starting Monday? This playbook gets a rep productive in days instead of months by pre-loading every account with intelligence.
**Who this is for:** RevOps setting up territories for new hires, or AEs/BDRs who just received a new territory.
**Time:** 1-2 hours for setup (mostly waiting for enrichment). The rep is productive within their first day.
**What you'll have at the end:** A fully enriched, scored, and segmented territory where every account has strategic intelligence, tech stack, contacts, and a prioritisation score.
## For RevOps: Setting Up the Territory
Follow Steps 1-2 from the [Territory Planning playbook](/playbooks/territory-planning). Import the account list via CSV or CRM sync.
Enable all intelligence modules and run enrichment. For 200 accounts, this takes 30-60 minutes.
Use your existing scoring model (or build one - see [Territory Planning Step 4](/playbooks/territory-planning)). Score all accounts so the new rep immediately knows where to focus.
Configure monitoring agents across the top-tier accounts so the rep gets alerts from day one.
Add the rep to the team, assign the territory, and send them to this playbook.
## For the Rep: Your First Day
Go to **Territory**, sort by score. Your top 15-20 accounts are your Tier 1. Click into each one and spend 2 minutes scanning strategic priorities and tech stack. You're not building account plans yet - you're getting oriented.
Pick the 5 highest-scored accounts and run through the [Account Planning playbook](/playbooks/account-planning) for each. These are the accounts you'll engage first.
Across your top 10 accounts, check **Contacts & Org Chart** for each. Who are the personas you sell to? Are there existing relationships from your predecessor? Note the key names.
With intelligence on every account, you can start outreach from day one. Follow the [Prospecting & Outbound playbook](/playbooks/prospecting-outbound) using the strategic context you've just learned.
The difference: without PG:AI, a new rep spends their first 3 months Googling accounts, reading LinkedIn profiles, and slowly building a mental model of their territory. With PG:AI, every account already has full intelligence - they skip the research phase and go straight to engagement.
## Related
Full territory planning workflow including scoring model setup
Build deep account plans for your top accounts
Start outreach with account-specific intelligence
# Playbooks
Source: https://docs.getpg.ai/playbooks/overview
Step-by-step guides for common sales workflows powered by PG:AI
Playbooks show you how to use PG:AI for specific sales activities - from meeting prep to territory planning to prospecting. Each playbook walks through the workflow end-to-end, showing which PG:AI features to use and when.
Prepare for any meeting in minutes with deep account context
Build comprehensive account plans grounded in real intelligence
Prioritise and plan your territory using data-driven scoring
Identify high-potential accounts and craft personalised outreach
Understand competitive landscapes and position against alternatives
Prepare executive-ready materials for QBRs and EBCs
Get up to speed on a new territory fast
Create account-relevant content for outreach and engagement
Stay on top of changes across your accounts automatically
Run a full territory analysis project from start to finish
# Prospecting & Outbound
Source: https://docs.getpg.ai/playbooks/prospecting-outbound
Identify high-potential accounts and craft personalised outreach that converts
Turn outbound from generic to targeted. This playbook shows you how to use PG:AI to find the right accounts, identify the right contacts, and write outreach that references what the prospect actually cares about.
**Who this is for:** BDRs, SDRs, AEs doing their own prospecting.
**Time:** 5-10 minutes per account for personalised outreach (vs 30-60 minutes manually, or sending generic templates).
**What you'll have at the end:** A personalised outreach message referencing the prospect's specific priorities, sent to the right person.
## Step 1: Identify Target Accounts
If you already have a target list, skip to Step 2.
If you need to identify which accounts to prioritise, use **Territory**:
* Sort by **PG:AI Score** to see the highest-fit accounts
* Filter by **tech stack** to find accounts using competitor technology (displacement opportunities)
* Use **Custom Columns** to ask a specific question across all accounts (e.g. "Is this company actively evaluating solutions in \[your space]?")
* Check **Jobs & Hiring Signals** for accounts with hiring surges in roles relevant to your product
The accounts at the top of your scored territory, especially those with competitor technology or active hiring in your space, are your highest-probability targets.
## Step 2: Find Your Angle (2 min per account)
Open the account and go to **Strategic Insights**. Scan the priorities. You're looking for one that directly connects to what you sell.
The best outreach angle is specific and timely:
* "I noticed you're prioritising \[X]" - references a real strategic priority
* "You're hiring \[N] engineers in \[area]" - references real hiring data
* "I see you're using \[competitor]" - references tech stack intelligence
Avoid generic angles like "I help companies like yours" or "I wanted to reach out." The whole point is that you know something specific about this account.
## Step 3: Find the Right Person (2 min)
Go to **Contacts & Org Chart**. Your configured personas are at the top.
Look for:
* **The right seniority** - For outbound, aim for director/VP level. Managers are easier to reach but harder to convert.
* **Career history** - Did they come from a company that uses your product? That's a warm angle.
* **Recency** - Someone who just joined is actively building and more open to new tools.
Get their email and/or LinkedIn.
## Step 4: Craft the Message (3 min)
**Quick route - Agent:**
> "Write a cold email to \[Name], \[Title] at \[Company]. Reference their priority around \[specific priority you found in Step 2]. We sell \[what you sell] and help companies \[outcome]. Keep it under 100 words, end with a specific question."
**Structured route - Canvas:**
Use an outreach template in Canvas. The AI generates a personalised version using the account intelligence.
**Manual route:**
Write it yourself, but use the intelligence. A simple formula:
1. **Hook** - Reference something specific about their company (priority, hiring, tech)
2. **Bridge** - Connect it to what you do (1 sentence)
3. **Ask** - Specific question or CTA (not "let me know if you'd like to chat")
The single biggest mistake in outbound is making it about you. "We help companies..." = about you. "I noticed you're prioritising X and most companies in your space struggle with Y" = about them. PG:AI gives you the information to make every message about them.
## Step 5: Follow Up With Context
If they respond, you're already ahead - you know their strategic priorities, competitive landscape, and org structure. Use the [Meeting Preparation](/playbooks/meeting-preparation) playbook to prep for the call.
If they don't respond, use a different angle from the intelligence for your follow-up. Don't repeat the same message. Reference a different priority, a different signal, or a different person at the account.
## Related
Create outreach sequences and email templates at scale
They responded - now prep for the meeting
Score and prioritise which accounts to prospect first
# QBR & EBC Preparation
Source: https://docs.getpg.ai/playbooks/qbr-ebc-preparation
Prepare executive-ready materials backed by real account intelligence
Whether you're presenting to a customer's executive team (EBC) or running a Quarterly Business Review (QBR), this playbook helps you build materials grounded in real intelligence - not recycled slides and guesswork.
**Who this is for:** AEs, SCs, Customer Success managers, anyone presenting to senior stakeholders.
**Time:** 45-60 minutes for a thorough briefing document.
**What you'll have at the end:** An executive-ready brief with strategic context, relevant insights, and talking points specific to the audience and their priorities.
## For EBC Preparation
An Executive Briefing Centre presentation needs to demonstrate that you understand the customer's business at a strategic level. PG:AI gives you the depth.
**Step 1: Strategic Context (15 min)**
Open **Strategic Insights** and build your understanding of what the executive team cares about:
* **Priorities** - What's on the CEO's agenda? What did they emphasise in the last earnings call?
* **Goals** - What are the measurable targets? Revenue, margin, expansion, efficiency?
* **Division intelligence** - If you're meeting a division head, focus on their business unit's specific priorities, not the corporate overview.
**Step 2: Financial Context (10 min)**
For public companies, review **Financial Intelligence**:
* Revenue trajectory and analyst expectations
* Key metrics and how they compare to competitors
* Any recent financial events (acquisitions, restructuring, earnings surprises)
This lets you frame your presentation in their financial language: "You're targeting 20% growth in EMEA - here's how we support that."
**Step 3: Build the Brief (20 min)**
Use **Canvas** to create a structured EBC preparation document:
> "Create an EBC preparation brief for \[Company]. I'm meeting with \[Names/Titles]. Include: their top strategic priorities, financial context, division-specific intelligence for \[division], recommended talking points, and questions to ask. We sell \[what you sell]."
## For QBR Preparation
A QBR needs to show value delivered, current intelligence, and forward-looking opportunities.
**Step 1: Current Account Intelligence (10 min)**
Review the account's current state across all intelligence modules. What's changed since the last QBR? New priorities, leadership changes, technology shifts, hiring patterns.
**Step 2: Expansion Opportunities (10 min)**
Check **Division Intelligence** for business units you're not engaged with. Check **Contacts** for new stakeholders. Check **Tech Stack** for new technologies that create integration or expansion opportunities.
**Step 3: Build the QBR Deck (20 min)**
Use Canvas to generate a structured QBR brief:
> "Create a QBR brief for \[Company]. Include: summary of their current strategic priorities, what's changed since last quarter, expansion opportunities across their divisions, key stakeholders we should engage, and recommended next steps. We currently provide \[what you provide to them]."
## Tips
* **Lead with their world, not yours.** Start the EBC/QBR with their priorities and challenges, then connect to what you provide. Not "here's what we did" but "here's what you're focused on and here's how we're helping."
* **Reference specific sources.** "In your Q3 earnings call, your CEO mentioned..." builds more credibility than "we've noticed that..."
* **Prepare for questions.** Use the Agent to anticipate what the executive might ask: "What tough questions might \[Title] ask about \[topic]?"
## Related
Build a comprehensive account plan before the QBR
Quick prep for a standard meeting
Reference guide for financial data and competitor benchmarking
# Territory Analysis Project
Source: https://docs.getpg.ai/playbooks/territory-analysis-project
Run a comprehensive territory analysis - coverage, scoring, gaps, and recommendations
Run a full analysis of an existing territory - useful for annual planning, QBR preparation, territory restructuring, or just understanding the health of your book of business.
**Who this is for:** RevOps, Sales Leaders, anyone doing territory reviews or planning.
**Time:** 2-4 hours depending on territory size. Much of this is enrichment time running in the background.
**What you'll have at the end:** A complete territory health assessment with scoring validation, coverage gaps, segment analysis, and actionable recommendations.
## Step 1: Ensure Full Enrichment
Before analysing, make sure every account in the territory is enriched. Go to **Territory → Enrichment** and check for gaps. If some accounts haven't been enriched (maybe they were added recently), run enrichment to fill in the gaps.
You need consistent data across all accounts for the analysis to be meaningful.
## Step 2: Validate Your Scoring Model
Go to **Territory → Scoring Models**. Before trusting the scores, validate:
* Pull your closed-won deals from the last 6-12 months. What are their scores?
* Pull your closed-lost deals. What are their scores?
* If won deals consistently score higher than lost deals, the model is working. If not, adjust criteria and weights.
* Check the distribution: are scores spread reasonably, or is everything clustered?
## Step 3: Analyse Coverage and Distribution
Go to **Territory → Analytics** and review:
**Score distribution** - Are accounts spread across tiers, or bunched in the middle? A healthy territory has a clear top tier (accounts to invest in deeply), a middle tier (accounts to develop), and a bottom tier (accounts to monitor or deprioritise).
**Segment breakdown** - How do scores vary by industry, geography, or company size? Are there segments that consistently score high? Low? This informs focus areas.
**Enrichment coverage** - What percentage of accounts have full intelligence? Accounts without enrichment are blind spots.
## Step 4: Identify Gaps and Opportunities
Use **Custom Columns** to ask questions across the territory:
* "Is this company actively investing in \[your market]?"
* "Does this company have a team responsible for \[function you sell to]?"
* "Has this company made any acquisitions in the last 12 months?"
These ad-hoc analyses surface patterns you can't see from scores alone.
## Step 5: Run Scenarios
If you're considering territory changes (rebalancing, splitting, merging), use **Scenarios & Recommendations**:
* Model different territory assignments
* Compare score distributions across scenarios
* Get AI recommendations for optimal balance
## Step 6: Document and Share
Use **Canvas** to create a territory analysis report:
> "Create a territory analysis report. We have \[N] accounts scored across \[segments]. The scoring model uses \[criteria]. Key findings: \[top-line observations]. Recommendations: \[what should change]."
This becomes the basis for territory review meetings, QBR presentations, or planning sessions.
## Related
Build a new territory from scratch
Reference guide for building and tuning scoring models
Reference guide for territory scenario modelling
# Territory Planning & Prioritisation
Source: https://docs.getpg.ai/playbooks/territory-planning
Score, segment, and prioritise your territory based on real account signals - not spreadsheets and firmographics
Build a territory plan where every account is scored on strategic signals, not just employee count and industry code. This playbook walks you through importing accounts, enriching them, building a scoring model, and segmenting your territory so your team knows exactly where to focus.
**Who this is for:** RevOps, Sales Leaders, anyone responsible for territory design and account prioritisation.
**Time:** 2-3 hours for a full territory build. Enrichment runs in the background, so much of this is configuration and review.
**What you'll have at the end:** A scored, ranked, segmented territory with every account enriched with strategic intelligence. Exportable to your CRM or usable directly in PG:AI.
## Step 1: Create the Territory (10 min)
Go to **Territory → Territory Management** and create a new territory.
**Import accounts** via one of:
* **CSV upload** - Export from your CRM or spreadsheet. Minimum fields: company name, domain. PG:AI matches and deduplicates.
* **CRM sync** - If connected, pull accounts directly from Salesforce or HubSpot with filters (e.g. all accounts owned by a specific rep, all accounts in a specific segment).
* **Manual add** - For smaller territories, add accounts individually.
Start with a manageable size for your first territory - 100-300 accounts. Once you're confident in the enrichment and scoring, expand to the full universe.
## Step 2: Configure Enrichment (5 min)
Go to **Territory → Enrichment** and configure which intelligence modules to activate for this territory:
* **Strategic Insights Scoring** - Score accounts against strategic criteria you define (e.g. "Is this company prioritising cloud migration?")
* **Tech Stack** - Detect technologies from job postings. Essential if you want to score on technology fit.
* **Jobs & Hiring Signals** - Track hiring patterns and hiring volume by role.
* **Employee Groups** - Count employees matching specific role patterns (e.g. "How many data engineers work here?")
Enable the modules relevant to your scoring approach, then run enrichment. This processes in the background - for 200 accounts, expect 30-60 minutes.
## Step 3: Define Strategic Insight Criteria (15 min)
Go to **Territory → Strategic Insights Scoring**. This is where you define the strategic topics that matter for your business.
For each criterion, define:
* **Name** - e.g. "Cloud Migration Priority"
* **Description** - What you're looking for. The more specific, the better the scoring. E.g. "Evidence that this company is actively migrating workloads to public cloud (AWS, Azure, GCP), including infrastructure modernisation, cloud-native development, or data platform migration."
PG:AI scores every account 0-100 against each criterion based on the strategic intelligence it's gathered.
**Tips for good criteria:**
* Be specific about what you're looking for. "Digital transformation" is too vague. "Migrating on-premise databases to cloud-native data platforms" is specific enough to score accurately.
* Use 3-5 criteria. More than that dilutes the signal.
* Include at least one negative criterion if relevant (e.g. "In cost-cutting mode with hiring freeze" might be a signal to deprioritise).
## Step 4: Build the Scoring Model (10 min)
Go to **Territory → Scoring Models**. Create a model that combines your signals into a single PG:AI Score per account.
**Available signal categories:**
* Strategic Insight criteria scores (from Step 3)
* Tech stack signals (favourite technologies present/absent)
* Hiring signals (hiring volume, specific role patterns)
* Employee groups (headcount matching role patterns)
* Firmographic data (revenue, employee count, industry)
**Weight each signal** based on importance. A typical starting point:
* Strategic alignment: 40%
* Technology fit: 25%
* Hiring signals: 15%
* Firmographics: 20%
Then run the model across the territory.
## Step 5: Validate the Model (15 min)
This is the step that makes the difference between a scoring model that works and one that doesn't.
**Take your known outcomes** - closed-won deals from the last 6-12 months and closed-lost deals - and check how they score:
* Do won accounts score higher on average than lost accounts?
* Are your best customers in the top tier?
* Are accounts you know are poor fit scoring low?
If the model ranks your known good accounts higher than your known bad accounts, it's working. If not, adjust the weights and criteria.
Perfect accuracy isn't the goal. The goal is: "if a rep follows the scoring, they'll spend more time on better accounts than they would on gut feel alone." Even a model that's 70% accurate is better than no model.
## Step 6: Review and Segment (15 min)
Go to **Territory → Analytics** to see how the territory looks:
* **Score distribution** - How are accounts distributed across score tiers? You want a bell curve or pyramid, not everything clustered in the middle.
* **Segment breakdown** - If you have segments (industry, size, geography), how does scoring vary across them?
* **Coverage** - How many accounts are enriched? Any gaps?
Use this to create segments:
* **Tier 1 (top 20%)** - Deep engagement, full account plans, regular touchpoints
* **Tier 2 (next 30%)** - Active prospecting, meeting prep on demand
* **Tier 3 (bottom 50%)** - Monitoring only, engage when signals change
## Step 7: Assign and Distribute (10 min)
Use **Scenarios & Recommendations** to model different territory assignments:
* Balance by score tier (each rep gets a fair mix of Tier 1/2/3)
* Balance by geography or industry
* Balance by total account count or total score value
Review the AI recommendations, accept or adjust, and publish the assignments.
## What You Should Have Now
* Every account enriched with strategic intelligence, tech stack, hiring signals
* A validated scoring model that ranks accounts on strategic fit
* Score-based segmentation (Tier 1/2/3)
* Territory assignments balanced and published
* Analytics showing territory health and distribution
## Tips
* **Revisit scoring quarterly.** Markets change, your ICP evolves, and the model should evolve with it. Run validation against recent outcomes every quarter.
* **Use Custom Columns for ad-hoc analysis.** Need to know something specific across all accounts? Custom Columns let you ask any question and get AI-researched answers at scale.
* **Don't over-engineer.** 3-5 scoring criteria with reasonable weights beats a complex model with 15 criteria that nobody understands.
* **Export to CRM.** Push scores and key enrichment data back to Salesforce/HubSpot so reps see it in their daily workflow, not just in PG:AI.
## Related
Set up a territory for a new hire - pre-loaded with intelligence
Run a deep analysis of an existing territory
Detailed reference for building and configuring scoring models
# Alerts - Setup Guide
Source: https://docs.getpg.ai/setup/alerts
How alerts are generated and how to manage alert notifications
## How Alerts Work
No separate setup is required. Alerts are generated automatically by monitoring agents.
Alerts are generated when a monitoring agent detects a change that matches its configured rules. They appear automatically once you have at least one monitoring agent configured and active.
## Accessing Alerts
Navigate to **Monitor** in the PG:AI sidebar.
Click **Alerts** (or the alert feed will be prominent in the Monitor dashboard).
You'll see all alerts generated by your monitoring agents, newest first.
## Alert Notifications
By default, alerts appear in the Monitor dashboard. Additional notification channels may be available:
* **In-app notifications** - alert badge in the PG:AI interface
* **Email digest** - periodic email summary of new alerts (if configured by your admin)
* **Webhooks** - push alerts to external systems via the API & Integrations webhooks
To start receiving alerts, set up at least one [Monitoring Agent](/setup/monitoring-agents). Alerts flow automatically once an agent is active and detects matching changes.
# Canvas - Setup Guide
Source: https://docs.getpg.ai/setup/canvas
How to access Canvas and create your first document
## Prerequisites
Before using Canvas, ensure you have:
* A PG:AI account with **Agent access enabled**
* At least one **company** in your workspace with Intelligence data
Canvas uses Intelligence data to generate account-specific documents. Richer Intelligence profiles produce better documents.
## Accessing Canvas
Navigate to any company in your workspace.
Click the **Canvas** tab in the company view.
You'll see existing canvas documents (if any) and a button to create a new one.
## Creating a New Canvas
Click **New Canvas**.
Choose a **template** from the available options, or select **Blank** to start from scratch.
If using a template, the agent will generate an account-specific first draft using the Intelligence profile. The canvas editor opens with the generated content ready for review and editing.
### Available Templates
Templates define a document structure. The agent fills each section with account-specific content. Common templates include:
* Executive briefing / account overview
* Strategic engagement plan
* Competitive analysis
* Research report
* Value path document
* Meeting preparation brief
Your organisation may have custom templates configured. Contact your admin to request new templates.
## Canvas Editor
The canvas editor is a structured document editor. You can:
* **Edit directly** - click into any section and type.
* **AI editing** - select text and request changes: "make this more concise", "expand this section", "rewrite for a CFO audience."
* **AI Q\&A** - ask questions about the document content and get answers.
* **Propose edits** - request AI-suggested changes without applying them immediately.
# Custom Columns
Source: https://docs.getpg.ai/setup/custom-columns
How to create and configure custom columns to extend your territory data
## Prerequisites
Before setting up custom columns, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory with accounts**
## Overview
Custom Columns let you get answers to any question you want about your territory accounts. Define a column, describe what it should contain, and PG:AI can use AI to research and populate values across all your accounts.
Navigate to **Territories → Custom Columns** in the left sidebar.
Custom Columns Settings - Get answers to any question you want about your territory accounts.
## Creating a Custom Column
Go to **Territories → Custom Columns** in the left sidebar.
Click **+ New Custom Column** (top-right button).
| Field | Description | Example |
| --------------- | --------------------------------------------- | ------------------------------------------- |
| **Label** | The display name for this column | "Revenue Growth" |
| **Key** | A programmatic key (auto-generated or manual) | "revenue\_growth" |
| **Description** | What this column measures or tracks | "Measure the company's revenue growth rate" |
Choose the type of data this column stores:
| Field | Description | Options |
| ------------- | ----------------------------------- | -------------------------------------------------- |
| **Data Type** | The type of data this column stores | Number, Text, Boolean, etc. (select from dropdown) |
Click **Save**.
## How AI Enrichment Works
When you create a custom column with a description, PG:AI can use AI to research each account and populate the column value:
Use the Description and/or AI Query fields to describe the data you want.
PG:AI's AI researches each account using available data - enrichment, public information, tech stack, jobs, etc.
The AI generates a value for each account based on what it finds.
Values are stored in the custom column and appear in territory views.
The **AI Query** field (visible in the column list) shows the question PG:AI asks about each account to generate the value.
## Managing Custom Columns
The Custom Columns settings page shows all columns in a table:
| Column | Description |
| ----------- | --------------------------------------- |
| Name | The label you gave the custom column |
| Type | The data type (Number, Text, etc.) |
| Description | What this column tracks |
| AI Query | The AI question used to populate values |
| Refresh | Whether automatic refresh is enabled |
| Created at | When the column was created |
* Click any column to edit its settings.
* Use the search bar to filter columns by name.
## Refresh and Monitoring
Custom columns can be configured to automatically refresh:
* **Scheduled refresh** - re-run AI enrichment on a schedule to keep values current.
* **Change detection** - get notified when values change significantly.
* **Manual refresh** - trigger a re-enrichment on demand.
The **Refresh** column in the settings table shows the refresh status for each column.
## Common Configurations
**Financial signals:**
| Label | Type | Description |
| -------------- | ------ | -------------------------------------------------------- |
| Revenue Growth | Number | Measure the company's year-over-year revenue growth rate |
| Funding Stage | Text | Latest funding round or stage (Series A, B, C, Public) |
| M\&A Activity | Text | Recent merger or acquisition activity |
**Technical signals:**
| Label | Type | Description |
| ---------------------- | ---- | ----------------------------------------------------- |
| Primary Cloud Provider | Text | Main cloud infrastructure provider (AWS, Azure, GCP) |
| DevOps Maturity | Text | Assessment of DevOps practices maturity |
| Tech Stack Age | Text | Whether the company is on modern or legacy technology |
**Market signals:**
| Label | Type | Description |
| ------------------------ | ---- | -------------------------------------------------- |
| Expansion Markets | Text | Countries or regions the company is expanding into |
| Compliance Requirements | Text | Key regulatory frameworks (SOC2, GDPR, HIPAA) |
| Competitive Displacement | Text | Which competitor products they currently use |
## Troubleshooting
| Issue | Likely Cause | Fix |
| --------------------------------------- | ----------------------------------------------- | ----------------------------------------------------- |
| Column values are empty | AI enrichment hasn't run yet | Trigger enrichment or wait for scheduled run |
| Values seem inaccurate | AI query too vague or data insufficient | Refine the description/AI query to be more specific |
| Column not appearing in territory views | Column exists in settings but not yet populated | Run enrichment to populate values |
| Refresh not working | Refresh not enabled for this column | Check the Refresh setting in the column configuration |
# Employee Groups
Source: https://docs.getpg.ai/setup/employee-groups
How to define and configure employee groups for territory planning
## Prerequisites
Before setting up employee groups, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory created**
* **Contact and job data enriched** for your accounts (employee groups match against this data)
## Overview
Employee Groups help you find out how many employees at each account match certain keywords - whether that's job titles, technologies, or specific roles. You define groups by name and keyword, and PG:AI matches them across all contacts and job data in your territories.
Navigate to **Territories → Employee Groups** in the left sidebar.
Setting employee groups can help finding out the number of employees that match certain keywords like technologies or job roles.
## Creating an Employee Group
Go to **Territories → Employee Groups** in the left sidebar.
Click **+ New Employee Group** (top-right button).
Complete the group details:
| Field | Description | Example |
| ------------------------ | ---------------------------------------- | ------------------------------------ |
| **Employee Group Name** | A descriptive name for this group | "Enterprise Account Executive" |
| **Title Keywords** | Keywords to look for in job titles | "Account Executive", "Enterprise AE" |
| **Description Keywords** | Keywords to look for in job descriptions | "Enterprise", "Strategic accounts" |
Click **Save**. The employee group is now created and will begin matching against contact and job data across your territories.
## How Matching Works
PG:AI searches across contacts and job postings for your territory accounts, looking for matches against your title keywords and description keywords. When a match is found, that person or role is counted in the employee group for that account.
This gives you a per-account headcount for each group - e.g. "Harness has 4 Enterprise Account Executives" or "Collibra has 12 MEDDPICC-related roles."
## Managing Employee Groups
The Employee Groups settings page shows all groups in a table:
| Column | Description |
| ---------- | -------------------------------------------------------------- |
| Group Name | The name you gave the employee group |
| Job Titles | Title keywords configured for this group (shown as tags) |
| Keywords | Description keywords configured for this group (shown as tags) |
| Created at | When the group was created |
* Click any group to edit its keywords.
* Use the search bar to filter groups by name.
## Using Employee Groups in Territory Settings
Employee groups appear in your territory's **Enriched Columns** settings (Territory Settings → Enriched Columns) with the type "Employee groups". Toggle them on to include employee group data in territory views and scoring.
For example, from the enriched columns panel:
* "Pipeline Generation" - Employee groups - Included: **ON**
* "Enterprise Account Executive" - Employee groups - Included: **OFF**
Only groups toggled on will contribute data to this territory's views and scoring models.
## Using Employee Groups in Scoring Models
Employee group counts can be used as inputs to scoring model rules. For example:
* "If Pipeline Generation employee group count > 5, add 15 points"
* "Baseline rule for Pipeline Generation - Employee group" (as shown in scoring model ruleset weights)
See the [Scoring Models setup guide](/setup/scoring-models) for details.
## Common Configurations
**Buying committee groups:**
| Group Name | Title Keywords | Description Keywords |
| ---------------------------- | --------------------------------------- | ----------------------------------- |
| Enterprise Account Executive | Account Executive, AE, Enterprise Sales | Enterprise, Strategic |
| MEDDIC / MEDDPICC | MEDDPIC, MEDDPICC | Sales methodology |
| CoM & CoS | Command of the..., Command c... | Command of message, Command of sale |
**Departmental groups:**
| Group Name | Title Keywords | Description Keywords |
| ------------------- | ------------------ | ------------------------------------ |
| Pipeline Generation | Pipeline, BDR, SDR | Pipeline generation, Lead generation |
| Total Employees | (broad keywords) | (broad keywords) |
Keep group names short and descriptive. Use multiple keywords per group to catch variations (e.g. "CRO", "Chief Revenue Officer", "Chief revenue" for the same role).
## Troubleshooting
| Issue | Likely Cause | Fix |
| ------------------------------------------------- | -------------------------------------------------------- | --------------------------------------------------------------------- |
| Employee group shows 0 matches for all accounts | Keywords too specific or contact data not enriched | Broaden keywords or run contact enrichment |
| Group not appearing in territory enriched columns | Group not yet included | Go to Territory Settings → Enriched Columns and toggle the group on |
| Too many false positive matches | Keywords too broad | Narrow keywords - use exact title matches rather than generic terms |
| Employee group data not feeding into scoring | Group not enabled in enriched columns for this territory | Toggle on in Territory Settings → Enriched Columns |
# Jobs
Source: https://docs.getpg.ai/setup/jobs
How to configure job settings to surface hiring signals across your territories
## Prerequisites
Before setting up job settings, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory created**
* **Job data enrichment** enabled for your accounts
## Overview
Jobs settings let you define saved job searches - keyword-based searches that find relevant job postings across your territory accounts. Each job setting targets specific roles or functions, revealing hiring signals that tell you what accounts are investing in.
Navigate to **Territories → Jobs** in the left sidebar.
Use job titles or keywords to find relevant job postings that reveal hiring signals and make your territory planning more targeted and informed.
## Creating a Job Setting
Go to **Territories → Jobs** in the left sidebar.
Click **+ New Job Setting** (top-right button).
| Field | Description | Example |
| --------------- | -------------------------------------------- | ----------------------- |
| **Name** | A descriptive name for this saved job search | "Chief Revenue Officer" |
| **Description** | What this job search is tracking | "Chief Revenue Officer" |
| Field | Description | Example |
| ------------------------ | ---------------------------------------- | ----------------------------------------------- |
| **Job Title Keywords** | Keywords to look for in job titles | "CRO", "Chief Revenue Officer", "Chief revenue" |
| **Description Keywords** | Keywords to look for in job descriptions | "Chief revenue", "Revenue operations" |
Click **Save**.
## Managing Job Settings
The Jobs settings page shows all configured job searches in a table:
| Column | Description |
| ----------- | ---------------------------------------------------- |
| Name | The name of the job setting |
| Description | What this search tracks |
| Job Titles | Title keywords configured (shown as tags) |
| Keywords | Description keywords configured (shown as tags) |
| Max Jobs | Maximum number of job postings to return per account |
* Click any job setting to edit its keywords and configuration.
* Use the search bar to filter by name.
## How Job Matching Works
PG:AI searches job postings across your territory accounts, matching against the title and description keywords you've defined. When matches are found:
* The number of matching job postings is tracked per account.
* Job data appears in territory views and account profiles.
* Job counts feed into scoring models as rule inputs.
The **Max Jobs** field limits how many job postings are returned per account for this search (e.g. 10, 20, or 100).
## Using Jobs in Territory Settings
Job settings appear in your territory's **Enriched Columns** (Territory Settings → Enriched Columns) with the type "Jobs". Toggle them on to include job data in territory views and scoring.
For example:
* "RevOps Job Monitoring" - Jobs - Included: **ON**
* "Chief Revenue Officer" - Jobs - Included: **ON**
* "Enterprise Account Executive" - Jobs - Included: **ON**
* "Job monitoring test" - Jobs - Included: **OFF**
Only job settings toggled on will contribute to this territory's views and scoring models.
## Using Jobs in Scoring Models
Job counts can be used as inputs to scoring model rules. For example, from the scoring model interface:
* "Baseline rule for RevOps" - Jobs - weight **3**
* "Baseline rule for Chief Revenue Officer" - Jobs - weight **50**
* "Baseline rule for Enterprise Account Executive" - Jobs - weight **16**
Higher weights mean that job signal contributes more to the overall account score. See the [Scoring Models setup guide](/setup/scoring-models) for details.
## Connecting Jobs to Monitoring Agents
Job settings can also be linked to monitoring agents for real-time alerts.
From the **New Agent** form, select a **Saved Job Search** to use as the monitoring source.
Set up the **Alert Configuration**:
* **Severity** - how important this alert is
* **Alert Title** - template for the alert (supports variables like `{job_title}`, `{job_url}`, `{company_name}`)
This means you can get alerted whenever a territory account posts a new job matching your keywords. See the [Monitoring Agents setup guide](/setup/monitoring-agents) for details.
## Common Configurations
**Role-based job monitoring:**
| Name | Job Title Keywords | Description Keywords | Max Jobs |
| ---------------------------- | -------------------------------- | ---------------------------------- | -------- |
| Chief Revenue Officer | CRO, Chief Revenue Officer | Chief revenue | 20 |
| RevOps Job Monitoring | Revenue Operations, Sales Ops | Revenue opera..., Sales operations | 10 |
| Enterprise Account Executive | Account Executive, Enterprise AE | Account execut..., Enterprise | 100 |
**Function-based job monitoring:**
| Name | Job Title Keywords | Description Keywords | Max Jobs |
| -------------------- | --------------------------------- | ---------------------------------- | -------- |
| Data Engineering | Data Engineer, Analytics Engineer | Data pipeline, ETL | 20 |
| Cloud Infrastructure | Cloud Engineer, DevOps, SRE | AWS, Azure, GCP, Kubernetes | 20 |
| Security | Security Engineer, CISO | Cybersecurity, Security operations | 20 |
Use a higher Max Jobs value (50–100) for broad searches and a lower value (10–20) for specific role searches.
## Troubleshooting
| Issue | Likely Cause | Fix |
| ----------------------------------------- | ---------------------------------------------------- | -------------------------------------------------------------- |
| Job setting shows no results | Keywords too specific or job enrichment not running | Broaden keywords or trigger job enrichment |
| Too many irrelevant matches | Description keywords too broad | Use more specific keywords or rely primarily on title keywords |
| Jobs not appearing in territory views | Job setting not toggled on in enriched columns | Territory Settings → Enriched Columns → toggle Jobs items on |
| Job counts not feeding into scoring model | Jobs not enabled or no scoring rule referencing jobs | Add a scoring rule that uses job data |
# Monitoring Agents - Setup Guide
Source: https://docs.getpg.ai/setup/monitoring-agents
How to create and configure monitoring agents to watch for account changes
## Prerequisites
Before setting up monitoring agents, ensure you have:
* A PG:AI account with **Monitor access enabled**
* **Companies** in your workspace that you want to monitor
## Accessing Monitor
Navigate to **Monitor** in the PG:AI sidebar.
You'll see your existing monitoring agents (if any) and a button to create a new one.
## Creating a Monitoring Agent
Click **New Monitoring Agent**.
Give the agent a **name** (e.g. "Hiring Signals", "Competitive Tech Adoption", "Leadership Changes").
Select the **signal type** - what kind of changes this agent should watch for.
Define what constitutes a notable change (e.g. "more than 10 new job postings in a week", "new C-level hire").
Add companies to the **watchlist** - individual accounts, territory segments, or bulk import.
Save and activate the agent.
## Signal Types
| Signal Type | What It Watches | Example Rule |
| ------------------- | ---------------------------------- | ----------------------------------------------------- |
| Hiring signals | New job postings, hiring velocity | "Alert when >10 relevant roles posted in 7 days" |
| Leadership changes | New executives, departures | "Alert on any C-level or VP-level change" |
| Technology adoption | New technologies in job postings | "Alert when \[competitor tech] appears in postings" |
| Financial events | Earnings, market cap changes | "Alert on earnings release or >10% market cap change" |
| Strategic shifts | New priorities, public initiatives | "Alert on new strategic initiative announcements" |
## Managing Watchlists
* **Add individual companies** - search and add from your workspace.
* **Add from territory** - import a territory segment as the watchlist.
* **Bulk add** - paste a list of company names or IDs.
* **Remove companies** - remove individual companies or clear the watchlist.
A single monitoring agent can watch hundreds of companies. You can create multiple agents with different signal types watching different or overlapping company sets.
## Data Sources
Monitoring agents connect to multiple data sources automatically:
* Job board aggregators for hiring signals
* Financial data providers for market data
* News feeds for strategic announcements
* PG:AI's enrichment engine for technology and company changes
You don't configure data sources directly. The platform manages source connections.
# Scenarios & Recommendations
Source: https://docs.getpg.ai/setup/scenarios-recommendations
How to create scenarios and use AI-powered recommendations for territory planning
## Prerequisites
Before using scenarios and recommendations, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory with accounts** and a **published scoring model**
* Recommended: Enrichment, criteria, jobs, and employee groups configured (these feed the recommendation engine)
## Overview
Scenarios let you create what-if versions of a territory. You model changes - reassign accounts, adjust allocations - without affecting the live territory. AI-powered recommendations suggest where to focus based on scores, rep capacity, and geography.
## Creating a Scenario
Open an existing territory.
Create a new scenario from the territory (via menu or action button). The scenario inherits the territory's accounts, scores, settings, and data.
Give the scenario a descriptive name (e.g. "Q3 Rebalance - Option A", "New Rep Model").
The scenario is now a sandboxed copy you can modify freely.
## Working with Scenarios
### Override Account Assignments
Within a scenario, you can reassign specific accounts:
* Move accounts between reps
* Remove accounts from the scenario
* Add accounts that aren't in the base territory
Overrides only affect the scenario - the live territory is unchanged.
### Generate AI Recommendations
Trigger the AI recommendation engine to suggest:
* Which accounts should be prioritised
* How to rebalance account assignments across reps
* Where geographic proximity could improve coverage
Recommendations are based on:
* **Scoring model outputs** (account scores)
* **Rep capacity** (how many accounts each rep can handle)
* **Geographic distance** (proximity between rep and account locations)
* **Current coverage gaps**
### Review and Act on Recommendations
Each recommendation can be:
* **Accepted** - the suggested change is applied to the scenario
* **Declined** - the suggestion is dismissed
You can accept or decline individually, or use bulk actions to process many recommendations at once.
### Scenario Summary
Review a summary showing:
* Changes made vs. the base territory
* Recommendations accepted vs. declined
* Impact on score distribution and coverage
## Applying Scenario Changes
Once you're satisfied with a scenario:
Verify all changes and their impact.
Apply the scenario changes back to the live territory.
The live territory updates with the new assignments and settings.
This is a one-way operation - once applied, the live territory reflects the scenario. Create a new scenario if you want to continue modelling.
## Common Configurations
**Quarterly territory rebalance:**
1. Clone the current territory as a scenario
2. Generate AI recommendations
3. Review and accept/decline
4. Share scenario summary with sales leadership for approval
5. Apply to live territory
**New rep onboarding:**
1. Create a scenario to model adding a new rep
2. Let AI recommend which accounts to reassign
3. Check geographic proximity for the new rep's location
4. Apply once approved
**Annual planning:**
1. Create multiple scenarios with different allocation strategies
2. Compare scoring distributions and coverage across scenarios
3. Pick the best option and apply
## Troubleshooting
| Issue | Likely Cause | Fix |
| ----------------------------------------------- | ------------------------------------------------------------ | --------------------------------------------------------- |
| Recommendations not generating | Scoring model not published or insufficient data | Publish a scoring model and ensure enrichment is complete |
| All recommendations suggest the same changes | Limited variation in scores | Review scoring model - rules may need more signals |
| Scenario changes not applying to live territory | Confirmation step missed or insufficient permissions | Ensure you have admin access and confirm the apply action |
| Geographic recommendations seem wrong | Rep locations not configured or account locations incomplete | Check that location data is enriched for accounts |
# Scoring Models
Source: https://docs.getpg.ai/setup/scoring-models
How to create, configure, and publish scoring models for your territories
## Prerequisites
Before setting up scoring models, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory created** with accounts
* Recommended: **Strategic insight criteria**, **job settings**, and **employee groups** already configured (these provide the data that scoring rules evaluate)
## Overview
Scoring models turn your territory data - job counts, team size, criteria scores, enrichment data - into one simple score per account, so you can focus on the best leads first.
Navigate to **Territories → Scoring Models** in the left sidebar.
Scoring models help you see at a glance how well each company fits your territory by turning their data (e.g. job counts, team size, criteria scores) into one simple score so you can focus on the best leads first.
## Creating a Scoring Model
Go to **Territories → Scoring Models** in the left sidebar.
Click **+ New Scoring Model** (top-right button).
Enter a **Criteria Name** (the scoring model name) and optionally a **Description**.
Click **Save** or proceed to configure rules and thresholds.
PG:AI can also auto-generate a **Baseline Scoring Model** based on your territory settings (jobs, employee groups, insight criteria). This is the fastest way to get started.
## Configuring a Scoring Model
### Score Band Thresholds
Score bands define how account scores are categorised into traffic-light labels. Configure three thresholds:
| Band | Range | Badge Colour | Meaning |
| ------------ | --------------- | ------------ | ------------------------------------------- |
| **Negative** | ≤ 40 (default) | Low | Account is a poor fit based on current data |
| **Neutral** | 41–59 (default) | Medium | Account has moderate signals |
| **Positive** | ≥ 60 (default) | High | Account is a strong fit |
Adjust these thresholds based on your scoring distribution. If most accounts cluster around 50, consider tightening the bands.
### Ruleset Weights
Rules define what data contributes to the score and how much weight each signal carries. Each rule has:
* **Rule name** - describes what this rule evaluates (e.g. "Baseline rule for RevOps")
* **Type** - the data source: Jobs, Employee groups, Insights, etc.
* **Weight** - a number (0–100) controlling how much this rule contributes to the total score. Shown as a slider bar.
Example ruleset from a baseline model:
| Rule | Type | Weight |
| ---------------------------------------------- | -------------- | -------- |
| Baseline rule for RevOps | Jobs | 3 |
| Baseline rule for Chief Revenue Officer | Jobs | 50 |
| Baseline rule for Enterprise Account Executive | Jobs | 16 |
| Baseline rule for Pipeline Generation | Employee group | (varies) |
To edit rules, click **Edit Rules** to open the rules editor. You can add, remove, and modify individual rules.
### Preview
The scoring model editor includes a **Preview** panel on the right side. This shows:
* A list of accounts in the territory
* Each account's **PG:AI Score** (the calculated score)
* The **score badge** (High, Medium, Low) colour-coded
* The account's **domain**
Use the preview to validate your scoring model before publishing. Click **Reset** to recalculate scores.
## Publishing a Scoring Model
A scoring model must be **published** to take effect. While in draft, you can adjust rules and thresholds without affecting live scores.
Set up your rules and score band thresholds.
Review the preview to validate scoring looks right.
Click **Save** to publish the model. Published models score all accounts in the assigned territory automatically.
Scores recalculate as underlying data changes.
## Assigning a Scoring Model to a Territory
Open the territory and go to **Territory Settings** (gear icon).
Select the **Scoring Model** tab.
Choose the scoring model to assign. Once assigned, the territory's Companies view shows the PG:AI Score column with scores from this model.
## Understanding Scores in the Territory View
In the territory Companies tab, the **PG:AI Score** column shows:
* The numerical score (e.g. 99.31, 88.24, 64.95, 50.00)
* A colour-coded badge: **High** (green/purple), **Medium** (yellow), **Low** (red/grey)
* A sentiment indicator: **+ Positive**, **Neutral**, etc.
Accounts are scored from 0–100. The badge thresholds correspond to your Score Band Thresholds.
## Common Configurations
**Baseline model (quick start):**
* Let PG:AI generate a baseline model from your territory settings
* Review and adjust weights
* Good for getting started quickly
**ICP-weighted model:**
* Heavy weight on insight criteria scores (strategic fit)
* Moderate weight on jobs (hiring signals)
* Lower weight on employee groups (team composition)
* Good for prioritising strategic accounts
**Activity-weighted model:**
* Heavy weight on jobs and employee group growth
* Moderate weight on insight criteria
* Good for identifying accounts with momentum
**Multi-model comparison:**
* Create 2–3 models with different weighting strategies
* Assign each to a different territory (or clone territories)
* Compare which model best predicts success
## Troubleshooting
| Issue | Likely Cause | Fix |
| ------------------------------------------------- | ------------------------------------------ | ---------------------------------------------------------------------------- |
| All accounts score 50.00 | Model not published or no rules configured | Configure rules and publish the model |
| Scores don't update after changing data | Model needs to recalculate | Trigger a recalculation or wait for scheduled refresh |
| Preview shows unexpected scores | Rule weights need adjustment | Review individual rule weights and adjust |
| Scoring model not available in territory settings | Model not yet created or in wrong state | Check Territories → Scoring Models for the model |
| High/Medium/Low badges seem wrong | Score band thresholds need adjustment | Adjust Negative/Neutral/Positive thresholds to match your score distribution |
# Strategic Insights Scoring
Source: https://docs.getpg.ai/setup/strategic-insights-scoring
How to define insight criteria and configure strategic scoring for your territories
## Prerequisites
Before setting up strategic insights scoring, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory created**
* **Account enrichment running** (insight scores are derived from enriched data)
## Overview
Strategic Insights Scoring lets you evaluate target companies based on the strategic topics that matter to your business. You define **insight criteria** - topics like "Global Expansion", "DevOps Transformation", or "Platform Engineering Transformation" - and PG:AI scores every account against each criterion.
Navigate to **Territories → Strategic Insights Scoring** in the left sidebar to access the settings.
Strategic Insights Scoring helps you evaluate target companies based on the insights that matter most. Start by selecting keywords like "Improving Customer Experience" or "Global Expansion" to define your scoring criteria.
## Creating an Insight Criterion
Go to **Territories → Strategic Insights Scoring** in the left sidebar.
Click **+ New Insight Criteria** (top-right button).
Enter a **Criteria Name** - this should be a clear, descriptive topic or initiative name.
Click **Save**. The criterion is now created and will begin scoring accounts.
### Naming Guidance
Use names that describe a strategic theme or initiative, not a specific data point.
| Good Criteria Names | Why |
| ----------------------------------- | ------------------------------------------------------------------- |
| Global Expansion | Strategic initiative - measurable across signals |
| Continuous Delivery/Deployment | Technical focus area - shows in jobs, tech stack, hiring |
| DevOps Transformation | Industry trend - PG:AI can evaluate from multiple data sources |
| Platform Engineering Transformation | Specific enough to be meaningful, broad enough to score |
| Developer Productivity | Relevant business theme |
| Innovation & R\&D Investment | Strategic priority - visible in financials, hiring, tech adoption |
Avoid overly narrow names (e.g. "Uses Jenkins" - that's a technology, not a criterion) or overly broad names (e.g. "Good company" - not measurable).
## How Scoring Works
Once a criterion is created, PG:AI evaluates every account in your territories against that criterion. The platform analyses:
* **Job postings** - are they hiring for roles related to this topic?
* **Tech stack** - are they using technologies associated with this initiative?
* **Public intelligence** - filings, reports, news, and events that mention this topic
* **Enriched data** - any enrichment data relevant to the criterion
Each account receives a score per criterion, indicating how strongly aligned they are to that topic. These scores:
* Appear in territory views and account profiles
* Feed into scoring models as rule inputs
* Update automatically as enrichment data refreshes
## Managing Criteria
The Strategic Insights Scoring page shows all criteria in a table:
| Column | Description |
| ------------- | ------------------------------ |
| Criteria Name | The name of the criterion |
| Created at | When the criterion was created |
* Click any criterion to edit it.
* Use the search bar to filter criteria by name.
* The page shows the total count (e.g. "43 items").
## Connecting Criteria to Scoring Models
Insight criteria scores feed into scoring models. To use criteria scores in account ranking:
Define your insight criteria (this guide).
See the [Scoring Models setup guide](/setup/scoring-models).
Add rules to the scoring model that reference insight criteria scores.
Publish the scoring model to see ranked accounts.
Criteria scores also appear in territory views via the Enriched Columns settings. In **Territory Settings → Enriched Columns**, items with type "Insights" correspond to your insight criteria.
## Common Configurations
**Broad strategic scoring (executive-level):**
* 5–10 criteria covering major themes: digital transformation, cloud, AI/ML, expansion, etc.
* Useful for high-level territory prioritisation
**Focused ICP scoring (product-specific):**
* 15–30 criteria aligned to your product's value propositions
* Example: a DevOps platform might use criteria like "Continuous Delivery/Deployment", "DevOps Transformation", "Microservices/Container Strategy", "Software Delivery Acceleration"
**Industry-specific scoring:**
* Criteria tailored to vertical-specific initiatives
* Example for financial services: "Digital Banking Transformation", "Regulatory Compliance Modernisation", "Real-Time Payment Processing"
## Troubleshooting
| Issue | Likely Cause | Fix |
| ------------------------------------------------ | ---------------------------------------- | ------------------------------------------------------------------------ |
| Criteria not scoring accounts | Enrichment hasn't run yet | Trigger a territory enrichment run |
| All accounts have similar scores for a criterion | Criterion name too broad or too narrow | Refine the criterion name to be more specific and measurable |
| Criteria scores not appearing in scoring models | Criteria not connected as a scoring rule | Add a rule in the scoring model that references the insight criterion |
| Criteria scores not visible in territory view | Insights not enabled in enriched columns | Check Territory Settings → Enriched Columns and toggle Insights items on |
# Territory Analytics
Source: https://docs.getpg.ai/setup/territory-analytics
How to access and configure territory analytics and reporting
## Prerequisites
Before using territory analytics, ensure you have:
* At least one **territory with accounts**
* Recommended: **Scoring model published**, **enrichment complete** (analytics are most useful with full data)
## Overview
Territory Analytics provides built-in views for understanding territory performance - account aggregates, score distributions, geographic views, activity tracking, and exportable reports.
Analytics are accessed from within a territory view, typically via the **Overview** or **Insights** tabs at the top of the territory page.
## Territory Views
When you open a territory, the top navigation shows tabs including:
| Tab | What It Shows |
| ------------- | -------------------------------------------------------------------- |
| **Overview** | Territory summary - account count, score distribution, key metrics |
| **Companies** | Full account table with all columns, scores, and data |
| **Insights** | Insight scores and strategic criteria performance across accounts |
## Companies Table
The Companies tab is the primary analytics view. The table includes:
| Column | Description |
| -------------- | --------------------------------------------------------------- |
| Company | Company name with logo |
| Domain | Website domain |
| Industry | Industry classification |
| Country | Headquarters country |
| Employee Size | Employee count range (e.g. 1001–5000) |
| Revenue | Revenue range (e.g. $500M–$1B) |
| Territory Name | Which territory this account belongs to |
| PG:AI Score | Overall score from the scoring model (e.g. 99.31, 88.24, 50.00) |
| PG:AI Badge | Score band label (High, Medium, Low) with colour coding |
| Sentiment | Positive, Neutral, etc. |
### Customising the View
* Click column headers to sort
* Use the filter icon to apply filters
* Use the column selector to show/hide columns
* Additional columns may include enriched data, custom columns, job counts, and employee group counts
## Insights Tab
The Insights tab shows strategic insights scoring performance across territory accounts:
* Per-criterion scores across accounts
* Aggregated insight data
* Trend indicators
## Exporting Territory Data
To export territory data for offline analysis, QBRs, or sharing with stakeholders:
Open the Companies tab in your territory.
Use the export action to download territory data. Exports include all visible columns and account data.
Exports are useful for:
* Quarterly business reviews
* Sharing with leadership who don't have platform access
* Offline analysis and modelling
## Common Analytics Workflows
**Territory health check:**
1. Open territory → Overview tab
2. Review account count and score distribution
3. Check how many accounts are High vs. Medium vs. Low
4. Identify accounts that need attention (Low scores, no activity)
**Score distribution review:**
1. Open territory → Companies tab
2. Sort by PG:AI Score (descending)
3. Review the top-scoring accounts - are they the ones you'd expect?
4. Check the bottom - are there accounts that should score higher?
5. Adjust scoring model rules if the distribution doesn't match expectations
**Territory comparison:**
1. Open each territory and note key metrics
2. Compare account counts, score distributions, and coverage
3. Identify territories that are over- or under-resourced
## Troubleshooting
| Issue | Likely Cause | Fix |
| --------------------------- | ------------------------------ | ------------------------------------------ |
| All scores show 50.00 | No scoring model assigned | Assign and publish a scoring model |
| Analytics show limited data | Enrichment not complete | Run territory enrichment |
| Export missing columns | Columns hidden in the view | Unhide columns before exporting |
| Insights tab empty | No insight criteria configured | Set up Strategic Insights Scoring criteria |
# Territory Enrichment
Source: https://docs.getpg.ai/setup/territory-enrichment
How to configure and manage enrichment scoped to your territories
## Prerequisites
Before configuring territory enrichment, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **territory with accounts**
* **Enrichment credits available** in your organisation
## Overview
Territory Enrichment controls which enriched data columns are included in each territory. From the territory settings, you toggle which enrichment types - tech stack, jobs, employee groups, insights - are active for that territory.
The enrichment system runs in the background, populating data for your territory accounts based on what you've enabled.
## Configuring Enriched Columns per Territory
This is the primary enrichment configuration and is done per-territory.
Open the territory you want to configure.
Click the **gear icon** (top-right) to open **Territory Settings**.
The panel shows: *"Select the enriched columns you want to include in this territory"*
### The Enriched Columns Table
Each row represents an enriched data source:
| Column | Description |
| ----------- | ----------------------------------------------------------------------------------------- |
| Name | The name of the enriched item (e.g. "Technology Stack", "RevOps Job Monitoring") |
| Type | The data category - one of: **Tech stack**, **Jobs**, **Employee groups**, **Insights** |
| Description | What this enrichment tracks |
| Included | Toggle ON/OFF to include or exclude from this territory |
### Enrichment Types
| Type | What It Provides | Source |
| ------------------- | ----------------------------------------------- | --------------------------------------------------------------------- |
| **Tech stack** | Technologies used by each account | Technology Stack enrichment |
| **Jobs** | Job postings matching your saved job searches | Jobs settings (Territories → Jobs) |
| **Employee groups** | Employee counts matching your defined groups | Employee Groups settings (Territories → Employee Groups) |
| **Insights** | Insight scores matching your strategic criteria | Strategic Insights Scoring (Territories → Strategic Insights Scoring) |
### Toggling Enrichments
* **ON** - this enrichment data is included in territory views, feeds scoring models, and is visible in account profiles within this territory.
* **OFF** - this enrichment data is excluded from this territory. The data may still exist but won't appear in territory views or scoring.
Toggle items based on what's relevant for each territory. A focused territory might only need jobs and insights; a comprehensive enterprise territory might enable everything.
## Configuring Tech Stack Tracking
From Territory Settings, select the **Tech Stack** tab.
* Browse a card grid of technologies with logos.
* Use the **search bar** to find specific technologies.
* Click the **heart icon** to favourite/track a technology for this territory.
* Favourited technologies appear in territory views and can be used in scoring.
## Running Enrichment
Enrichment runs in the background based on:
* **Automated schedules** - enrichment tasks run continuously on a schedule
* **Batch triggers** - trigger enrichment for all accounts in a territory at once
* **On-demand** - enrich individual accounts as needed
### Monitoring Enrichment Runs
Track enrichment progress:
* View enrichment runs with status, timing, and results
* Drill into individual enrichment jobs to see successes, failures, and pending items
* Check territory enrichment coverage - what's been enriched and what's still missing
## Common Configurations
**Full enrichment (enterprise territory):**
* All enriched columns toggled ON (tech stack, all jobs, all employee groups, all insights)
* All relevant technologies favourited
* Full batch enrichment run after territory setup
**Focused enrichment (targeted territory):**
* Only the most relevant jobs and employee groups toggled ON
* 2–3 key insight criteria enabled
* Tech stack enabled for technology-specific territories
**Minimal enrichment (high-volume territory):**
* Only insight scores and one or two key job searches enabled
* Keeps credit usage low while still providing scoring data
## Troubleshooting
| Issue | Likely Cause | Fix |
| ---------------------------------------- | ------------------------------------------------ | ---------------------------------------------------------- |
| Enriched data not appearing in territory | Enriched columns toggled OFF | Territory Settings → Enriched columns → toggle items ON |
| Tech stack shows no technologies | Technologies not yet enriched | Run tech stack enrichment for territory accounts |
| Job data missing for some accounts | Job enrichment hasn't completed | Check enrichment run status and wait for completion |
| Enrichment consuming too many credits | Too many enrichment types enabled | Reduce enabled enrichment types to the most essential ones |
| Insight scores not appearing | Insights type not toggled on in enriched columns | Toggle Insights items ON in Territory Settings |
# Territory Management
Source: https://docs.getpg.ai/setup/territory-management
How to create, configure, and manage territories in PG:AI
## Prerequisites
Before setting up territories, ensure you have:
* **Admin or RevOps access** to your PG:AI organisation
* At least one **account plan created** (accounts must exist before you can add them to territories)
## Creating a Territory
Open **Territories** in the left sidebar.
Click **+ New Territory** (or the equivalent action from the territories list).
Enter a **territory name** - use a naming convention that reflects your GTM structure (e.g. "EMEA Enterprise", "US Mid-Market - West").
Configure initial territory settings (see [Territory Settings](#territory-settings) below).
Save the territory. It is now created and ready for accounts.
## Adding Accounts to a Territory
There are several ways to populate a territory with accounts:
### Manual Add
* From the territory's **Companies** tab, click to add companies.
* Search for accounts by name or domain and add them individually.
### CSV Import
Prepare a CSV file with company names, domains, or identifiers.
Use the CSV import feature to bulk-add accounts to the territory.
PG:AI validates the import before executing - review the preview for column mapping and data issues.
### Filter-Based Assignment
* Define territory filters to automatically include accounts matching certain criteria (industry, size, geography, etc.).
* Filtered accounts populate the territory automatically.
## Territory Companies View
Once accounts are added, the **Companies** tab shows a table view with the following columns:
| Column | Description |
| -------------- | ------------------------------------------- |
| Company | Company name with logo |
| Domain | Company website domain |
| Industry | Industry classification |
| Country | Headquarters country |
| Employee Size | Employee count range |
| Revenue | Revenue range |
| Territory Name | Which territory this account belongs to |
| PG:AI Score | Overall account score (from scoring models) |
You can sort, filter, and customise the column view. The table also shows score badges (High, Medium, Low) colour-coded for quick scanning.
## Territory Settings
Within a territory, access settings via the **gear icon** in the top-right. The settings panel has three tabs:
### Enriched Columns
Controls which enriched data types are included in this territory's views and scoring. Each enriched column has:
| Field | Description |
| --------------- | ----------------------------------------------------------------------------------------------- |
| **Name** | The enrichment item (e.g. "Technology Stack", "RevOps Job Monitoring", "Chief Revenue Officer") |
| **Type** | The data category (Tech stack, Jobs, Employee groups, Insights) |
| **Description** | What this enrichment tracks |
| **Included** | Toggle on/off to include or exclude from this territory |
Toggle items **on** to include their data in territory views and scoring. Toggle **off** to exclude data you don't need for this territory.
### Scoring Model
Assign a scoring model to this territory. The scoring model defines how accounts within this territory are scored and ranked. See the [Scoring Models setup guide](/setup/scoring-models) for details on creating and configuring models.
### Tech Stack
Add technologies you want to track for this territory.
* Search for technologies by name using the search bar.
* Click the heart icon to favourite technologies relevant to this territory.
* Favourited technologies surface in territory views and can be used in scoring rules.
* Technologies appear as a card grid with logos for easy browsing.
## Cloning a Territory
Open the territory you want to clone.
Use the clone action (typically via a menu or action button).
The clone copies the territory structure, settings, and account assignments. Rename the cloned territory and adjust settings as needed.
Cloning is non-destructive - the original territory is unaffected.
## Common Configurations
**Enterprise territory structure:**
* One territory per region/segment (e.g. "EMEA Enterprise", "US Enterprise - East")
* Enable all relevant enriched columns (tech stack, jobs, employee groups, insights)
* Assign a comprehensive scoring model
* Track technologies relevant to your ICP
**SMB / velocity territory:**
* Broader territories with more accounts
* Fewer enriched columns (focus on high-signal items)
* Simpler scoring models with fewer rules
* Filter-based account assignment to keep territories current
## Troubleshooting
| Issue | Likely Cause | Fix |
| ---------------------------------------- | -------------------------------------------------------- | ---------------------------------------------------------- |
| Accounts not appearing in territory | Not yet added or filter not matching | Check account assignment method - manual, CSV, or filter |
| PG:AI Score shows 50.00 for all accounts | No scoring model assigned or model not published | Assign and publish a scoring model in Territory Settings |
| Enriched data missing from views | Enriched columns toggled off | Check Territory Settings → Enriched Columns and toggle on |
| Territory clone missing some data | Clone copies structure but enrichment may need to re-run | Trigger a territory enrichment run after cloning |
# Workflows - Setup Guide
Source: https://docs.getpg.ai/setup/workflows
How to access and configure AI workflows for automated account research
## Prerequisites
Before using workflows, ensure you have:
* A PG:AI account with **Agent access** and **Workflows enabled**
* Familiarity with the **Agent** and **Canvas** (workflows build on both)
## Accessing Workflows
Workflows are accessed from the **Workflows** section in the PG:AI sidebar navigation. You'll see:
* **Available workflows** - pre-built and custom workflows ready to run
* **Workflow history** - previous runs with status and output
## Running a Pre-Built Workflow
Select a workflow from the available list.
Choose the **target**: a single account, a list of accounts, or a territory segment.
Configure any **parameters** the workflow requires (e.g. meeting date, attendee names, specific topics).
Click **Run**.
Monitor progress in the workflow history. Output appears when the workflow completes.
### Common Pre-Built Workflows
* **Meeting prep** - generates a meeting brief with strategic context, key contacts, and suggested discussion topics.
* **Account research** - runs a comprehensive research pass across all Intelligence dimensions and produces a research report.
* **Territory review** - scans accounts in a territory segment, flags changes, and produces a summary report.
* **Competitive analysis** - generates a competitive comparison for a specific account or deal.
## Building a Custom Workflow
Custom workflows are assembled from **steps**. Each step is a discrete action:
| Step Type | What It Does |
| ------------------ | ------------------------------------------------- |
| **LLM Generation** | Generate text using a prompt with account context |
| **Tool Call** | Invoke a tool (web search, contact lookup, etc.) |
| **Conditional** | Branch based on a condition |
| **Validation** | Check output against criteria |
| **Workflow Call** | Run another workflow as a sub-step |
Steps chain together to form a pipeline. Output from one step feeds as input to the next.
**Context recipes** provide reusable data-gathering configurations. A recipe defines which Intelligence data to pull and how to format it for the LLM.
**Frameworks** provide reusable workflow structures. A framework defines the step sequence; you customize the specific prompts and parameters.
## Running Workflows in Batch
Workflows can target multiple accounts. Select a territory segment or account list as the target, and the workflow runs independently for each account.
Batch runs show per-account status and output in the workflow history.
# Account Toolbar
Source: https://docs.getpg.ai/studio/account-toolbar
Search all account insights, discover jobs and contacts, and upload files - all from one toolbar in the Studio view
A unified toolbar at the top of the Studio section that gives you fast access to three essential account actions: searching across all intelligence, discovering jobs and contacts, and uploading files for the agent to reference.
## Overview
The Account Toolbar sits at the top of the Studio tab in any account view. It has three sub-sections, each accessible via a tab:
| Section | What it does |
| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Search** | Query across all account intelligence for the account - strategic priorities, tech stack, financials, contacts, jobs, and enrichment history |
| **Discover** | Focused search for jobs and contacts at the account |
| **File Uploads** | Upload documents to the account for the agent to reference |
***
## Search
Search all the insights PG:AI has about an account in one place. Instead of navigating between Strategic Priorities, Tech Stack, Financials, and Contacts individually, Search queries across every Intelligence module and returns matching results.
![Account toolbar search results]()
### How to use it
Click the **Search** tab in the Account Toolbar.
Type a keyword, phrase, or question (e.g. "cloud migration", "VP Engineering", "revenue growth").
Results appear grouped by source module - strategic priorities, contacts, tech stack, financials, jobs, and enrichment data.
Click any result to navigate to the full detail view within the relevant Intelligence module.
### Example queries
| Query | What it finds |
| --------------- | ----------------------------------------------------------------------------------------------- |
| `"AI strategy"` | Strategic priorities, job postings, and tech stack entries related to AI |
| `"CFO"` | Matching contacts and any insights that reference the CFO |
| `"AWS"` | Tech stack data, job postings mentioning AWS, and strategic insights about cloud infrastructure |
| `"Q3 earnings"` | Financial intelligence and enrichment data from earnings calls |
Use Search to quickly verify whether specific intelligence exists before asking the Agent for a deeper analysis. It's faster than navigating through each module individually.
***
## Discover
A focused search interface for exploring **jobs** and **contacts** at the account. Discover surfaces hiring activity and organisational data that help you understand the company and identify engagement opportunities.
![Account toolbar Discover enrichments]()
### Contacts
Search for people at the account by name, role, department, or seniority level.
* Filter by **department** (Engineering, Sales, Marketing, Finance, etc.)
* Filter by **seniority** (C-Suite, VP, Director, Manager)
* View role, reporting structure, and tenure
* Click a contact to open their full profile in the Contacts & Org Chart module
Discover is particularly useful for meeting prep - quickly find who you'll be meeting and what roles are being hired around them.
### Jobs
Search for job postings at the account by title, function, or keyword.
* Filter by **department**, **level**, or **posting date**
* View job descriptions, requirements, and posting source
* Use job postings to identify investment areas and strategic priorities
Job postings often signal strategic priorities before they appear in public announcements. A cluster of "AI Engineer" postings tells you something about company direction before the press release.
If Discover doesn't surface what you need, ask the Agent to research deeper - it can trigger additional enrichment beyond what's currently in the profile.
***
## File Uploads
Upload documents directly to an account. Uploaded files are indexed and become part of the account's intelligence context - available to the Agent, Canvas, and Workflows.
![Account toolbar file upload]()
### How to upload
Click the **File Uploads** tab in the Account Toolbar.
Drag and drop files into the upload area, or click to browse your computer.
Uploaded files are automatically indexed and immediately available to the agent.
### Supported formats
| Format | Extension | Max size |
| ---------- | --------- | -------- |
| PDF | `.pdf` | 50 MB |
| Word | `.docx` | 50 MB |
| Plain text | `.txt` | 10 MB |
| CSV | `.csv` | 25 MB |
| Excel | `.xlsx` | 50 MB |
| PowerPoint | `.pptx` | 50 MB |
### What to upload
| Document type | Why it's useful |
| ------------------------ | ------------------------------------------------------------------ |
| Meeting notes | Studio references your notes when preparing for follow-up meetings |
| Internal briefs | Company-specific context your team has gathered outside PG:AI |
| Competitive analyses | Studio uses these when generating competitive positioning content |
| RFP / RFI documents | Studio references requirements when generating proposals |
| Account plans | Studio aligns its output with your existing account strategy |
| Email threads (exported) | Studio uses conversation history for context |
Uploaded files are account-level - all team members with access to the account can view and use them. Files persist until deleted.
### Managing files
* View all uploaded files in the file library
* Files show upload date, uploader, and file size
* Delete files you no longer need - deleted files are removed from the agent's context
Upload before asking the agent to generate content. The more context it has - meeting notes, internal briefs, competitive research - the better the output. Meeting notes are especially high-value because they contain context no enrichment source can provide.
***
## Related modules
Ask questions about the account using intelligence data and any files you've uploaded.
Generate documents that draw from uploaded files as well as Intelligence data.
Build automated pipelines that reference uploaded account documents at scale.
# Canvas
Source: https://docs.getpg.ai/studio/canvas
Document workspace for creating executive reports, engagement plans, and sales content with AI-powered generation grounded in account intelligence
A document workspace for creating executive reports, engagement plans, competitive analyses, and sales emails with AI-powered generation grounded in account intelligence.
Instead of starting from a blank page, Canvas generates a first draft using the company's actual strategic priorities, financial data, contacts, tech stack, and competitive landscape. You review, refine, and ship - getting 80% of the way to a finished document in minutes.
## Key capabilities
* **Template-based document generation** with full account context
* **AI-powered editing** - rewrite, expand, refine, Q\&A with the agent
* **Multiple document types**: executive reports, engagement plans, emails, competitive analyses
* **Document library** per account - build a knowledge base over time
* **Full Intelligence access** for content generation
## Who it's for
| Role | How they use it |
| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| Account executives & strategic account managers | Producing polished, account-specific executive briefings, research reports, engagement plans, and proposals |
| Sales leaders | Ensuring consistent, high-quality output across the team |
| Marketing teams | Generating account-based content |
## Document types and when to use them
### Executive briefing
**When:** Preparing for a QBR, executive meeting, or board presentation about an account.
**What it includes:** Company overview, strategic priorities, financial summary, competitive landscape, key contacts, and recommended discussion topics.
Ask the agent to "tailor this for a \[CTO/CFO/CRO] audience" after generation to adjust the emphasis.
### Strategic engagement plan
**When:** Planning your approach for a new or strategic account.
**What it includes:** Account assessment, stakeholder mapping, value alignment, recommended engagement sequence, and timeline.
Feed in specific deal context after generation: "We're positioning against \[Competitor] and our champion is the VP of Engineering."
### Competitive analysis
**When:** Entering a competitive deal or preparing for a competitor displacement conversation.
**What it includes:** Competitor identification, technology comparison, financial benchmarking, strategic positioning differences, and recommended talk tracks.
### Research report
**When:** Deep-diving on an account for territory planning, deal strategy, or executive review.
**What it includes:** Comprehensive analysis across all Intelligence dimensions - strategy, technology, hiring, financials, and org structure.
## Editing with AI
After the initial generation, refine the document through conversation with the agent.
### Common editing commands
* "Make the executive summary more concise."
* "Expand the competitive section with more detail."
* "Add a section on their hiring trends."
* "Rewrite the value proposition for a technical audience."
* "Remove the financial section - this meeting is operational, not strategic."
* "Add bullet points summarising the key risks."
The agent has full access to the Intelligence profile during editing. Requests like "add their top 3 strategic priorities to the introduction" pull from live data.
## Building a document library
Canvas documents persist on the account. Over time, you build a library:
* The research report from when you first qualified the account
* The executive briefing updated before each QBR
* The competitive analysis refreshed when a new competitor entered the deal
* The engagement plan revised after the champion changed
Your team can access all documents. Previous versions are available for reference.
## Tips for better documents
Even if you plan to heavily customise, templates provide structure the agent can fill with data.
Don't try to get the perfect document on the first pass. Let the agent generate, then refine.
"Make it better" is vague. "Make the executive summary 3 sentences and add their Q3 revenue growth" is actionable.
Intelligence data updates continuously. Regenerate or ask the agent to "update this document with the latest data" before a key meeting.
## Related modules
Explore accounts conversationally before generating structured documents in Canvas.
Automate document generation across multiple accounts at scale.
Include email context when generating account documents and follow-ups.
# Studio
Source: https://docs.getpg.ai/studio/overview
The workspace where your team and the PG:AI agent get work done together
Studio is where intelligence becomes action. Every other module in PG:AI builds intelligence - Territory scores your accounts, Account gives you deep research, Contact maps the people, Monitoring watches for changes. Studio is where you use all of that to actually do something.
It's the workspace where your team converges with AI to answer questions, create polished documents, run automations, and complete work - all without leaving the context of enriched account intelligence. No jumping between tools. No copying and pasting data. Just work, grounded in truth.
## Who it's for
**Account executives & strategic account managers** - Your day-to-day workspace for research, document creation, automation, and task management. Use it to prepare for meetings, create executive deliverables, and scale your account work.
**Sales leaders & RevOps** - Oversee team productivity, enforce consistency in messaging and processes, set up automations for high-volume work, and track account progress.
**Sales enablement teams** - Build templates, playbooks, and reusable workflows that your organisation can leverage across teams and regions.
**Marketing teams** - Generate account-based content, competitive analyses, and messaging frameworks.
**Customer success teams** - Maintain engagement plans, run proactive outreach sequences, and document customer intelligence.
## What you can do in Studio
Have natural-language conversations with an agent that knows your accounts. Ask questions, request research, get answers grounded in real intelligence - not generic web search results.
Create polished documents in minutes: executive briefings, engagement plans, competitive analyses, proposals, and more. AI-generated from your account intelligence, then refined with editing.
Automate multi-step work: batch research across accounts, email sequences, lead scoring, narrative generation, and anything else you can describe.
Access quick actions, filtered intelligence, and context-aware tools without leaving your account view.
## Key benefits
The agent has full context of enriched account data. Ask questions naturally - intelligence flows in automatically.
Templates and AI generation ensure your entire team produces professional, account-specific deliverables.
Every document, conversation, and workflow builds on your prior work. Your team's institutional knowledge grows over time.
No hallucinations. Every answer and document is rooted in enriched intelligence about the account, your tech stack, and verified data.
The AI Agent completes work on your behalf - batch research, outreach sequences, task creation - triggered by your workflows.
Research conversations feed into documents. Workflows trigger tasks. Documents surface in briefings. Everything builds on everything else.
## How the pieces connect
Think of Studio as an integrated work engine:
1. **Start in Agent** - Have a conversation about an account. Ask questions, explore angles, gather research.
2. **Turn conversation into Canvas** - Take insights from your chat and spin up a polished executive briefing or engagement plan.
3. **Automate with Workflows** - Batch that process across 50 accounts. Run it weekly. Trigger it from Monitoring alerts.
4. **Quick actions in Account Toolbar** - Access everything you need without context-switching.
Every piece is optional. Use just the Agent if that's all you need. But the real power comes from combining them - intelligence → documents → automation → execution.
## Connections to other modules
Studio brings together intelligence from across PG:AI. Here's how it connects:
Canvas and Agent draw from strategic priorities, financials, tech stack, org charts, and enrichment history to produce grounded documents and answers.
Workflows surface scoring data for segment-specific work. Trigger automations based on account health scores.
Agent and Canvas pull contact data for stakeholder mapping, outreach personalisation, and engagement planning.
Workflows are triggered by Monitoring alerts. Turn signals into action automatically.
Define company personas, value propositions, and document templates that power AI generation across Canvas and Workflows.
## Get started
Begin with the **Agent** - just ask a question about an account and explore what's possible. Once you're comfortable, try generating a **Canvas document** to see how Intelligence becomes a polished deliverable. From there, **Workflows** and the **Account Toolbar** are there when you're ready to scale.
Each module is designed to work independently, but the most powerful outcomes come from using them together.
# Agent
Source: https://docs.getpg.ai/studio/the-agent
Conversational AI that knows your accounts - ask questions and get answers grounded in real intelligence data
A conversational AI that knows your accounts. Ask questions about any company and get answers grounded in real intelligence data, not generic web search.
When you open a conversation, the Agent already has access to the full Intelligence profile: strategic priorities, contacts, tech stack, financials, hiring data, enrichment history, and previous conversations. Every answer is grounded in what PG:AI knows about the account.
## Key capabilities
* **Conversational research** with full account context
* **Real-time web search** and deep research on demand
* **Source citations** for every claim
* **Conversation memory** - previous research and follow-ups are saved
* **Content streaming** for real-time responses
* **Multiple conversation threads** per account
## Who it's for
| Role | How they use it |
| ------------------ | ------------------------------------------------------------------------------------------- |
| Account executives | Preparing for meetings, investigating accounts, getting quick answers to specific questions |
| SDRs | Researching accounts for outreach |
| Sales leaders | Getting quick account summaries |
## Effective question patterns
The Agent draws from different account intelligence modules depending on what you ask. Here are the most effective patterns.
### Strategic questions
* "What are \[Company]'s top strategic priorities for this year?"
* "What challenges is \[Company] facing in their market?"
* "How does \[Company]'s strategy compare to \[Competitor]?"
* "What are the main risks to \[Company]'s business?"
These draw primarily from the **Strategic Insights** module: priorities, goals, SWOT, and division intelligence.
### People questions
* "Who leads the platform engineering function?"
* "Who reports to the CTO?"
* "Find me the VP of Sales or equivalent."
* "What's the career history of \[Contact Name]?"
These draw from **Contacts & Org Chart** data.
### Technology questions
* "What cloud technologies are they using?"
* "How does their tech stack compare to \[Competitor]?"
* "What technologies are trending in their recent job postings?"
* "Do they use \[specific technology]?"
These draw from **Tech Stack Intelligence** and **Jobs** data.
### Hiring and investment questions
* "What roles are they hiring for right now?"
* "How has their hiring changed in the last quarter?"
* "Are they investing in \[specific area]?"
* "What does their hiring pattern signal about their priorities?"
These draw from **Jobs & Hiring Signals** data.
### Financial questions
* "What's their current revenue and growth rate?"
* "How do their margins compare to competitors?"
* "What did analysts say in their last earnings call?"
* "Are they under financial pressure?"
These draw from **Financial Intelligence** data.
### Meeting preparation
* "Prepare a meeting brief for my call with \[Company] tomorrow."
* "What are 5 discovery questions I should ask based on their strategic priorities?"
* "What's the strongest value alignment between our solution and their goals?"
These synthesise across multiple data modules to produce comprehensive output.
## Tips for better responses
"What cloud technologies are they using?" is better than "tell me about their technology."
The agent knows which company you're viewing. You don't need to restate the company name in every message.
The agent remembers the conversation. "Go deeper on that" or "How does that compare to last year?" works naturally.
If the Intelligence profile doesn't have what you need, ask the agent to research it. "Research their recent partnerships" triggers a web search.
"Summarise this as bullet points" or "Format this as an email" works within the conversation.
## Limitations
* The agent's knowledge of an account is only as good as the Intelligence enrichment. Accounts with minimal enrichment produce thinner responses.
* Real-time web search may not surface very recent events (last few hours).
* The agent does not have access to your CRM data, email, or internal documents unless they've been uploaded to PG:AI.
## Related modules
Turn research conversations into polished documents - executive briefings, engagement plans, and more.
Automate multi-step research and content generation across accounts at scale.
Give the Agent access to email context for better follow-ups and responses.
# Workflows
Source: https://docs.getpg.ai/studio/workflows
Multi-step, configurable AI pipelines that run research, analysis, and content generation across accounts at scale
Multi-step, configurable AI pipelines that run research, analysis, and content generation across accounts at scale. Build once, run across your portfolio.
Workflows automate multi-step AI tasks. Instead of manually researching an account, then generating a competitive analysis, then drafting emails, then producing a meeting brief - a workflow runs the entire sequence as a single automated pipeline with consistent quality.
![Canvas template selector in Studio]()
## Key capabilities
* **Multi-step pipeline builder** with LLM generation, tool calls, conditionals, and branching
* **Batch execution** across accounts
* **Context recipes** for reusable research configurations
* **Frameworks** for reusable workflow templates
* **Workflow history** and tracking
* **Model selection per step** - choose the right LLM for each task
## Who it's for
| Role | How they use it |
| ------------------------------- | --------------------------------------------------------------------------------- |
| RevOps teams & sales operations | Build workflows once and run them at scale across many accounts |
| Account executives | Trigger pre-built workflows for specific tasks (e.g., "generate a meeting brief") |
| Sales leaders | Ensure consistent output quality across the team |
## When to use workflows vs. the Agent
| Task | Use Assistant | Use Workflow |
| ---------------------------------- | ------------- | --------------------------- |
| One-off research question | Yes | No |
| Meeting brief for one account | Either works | Yes, for repeatable process |
| Research report for 50 accounts | No | Yes |
| Exploring an account interactively | Yes | No |
| Standardised competitive analysis | No | Yes |
| Territory-wide change summary | No | Yes |
**Rule of thumb:** If you'll do the same task more than 3 times, build a workflow. If it's a one-off exploration, use the agent.
## Effective workflow patterns
### Meeting preparation pipeline
Pull strategic priorities and recent news (tool call)
Identify meeting attendees from contacts (tool call)
Generate talking points aligned to company goals (LLM generation)
Draft discovery questions based on account context (LLM generation)
Compile a one-page meeting brief (LLM generation)
**Output:** A meeting-ready document per account. Run in batch for a week's worth of meetings.
### Territory health review
For each account in segment: check for Intelligence changes since last review (tool call)
Flag accounts with significant changes (conditional)
Generate a change summary for flagged accounts (LLM generation)
Compile a territory health report (LLM generation)
**Output:** A territory-level report highlighting which accounts need attention and why.
### Account research and engagement plan
Run comprehensive Intelligence review (tool call)
Identify competitive landscape (tool call + LLM generation)
Map stakeholders and recommend contacts (LLM generation)
Generate value alignment analysis (LLM generation)
Draft engagement plan with recommended sequence (LLM generation)
Generate 3 personalised outreach emails (LLM generation)
**Output:** A complete engagement package per account.
## Tips for effective workflows
Run them as-is to understand the pattern, then customise.
Don't reinvent how Intelligence data is gathered for each workflow. Recipes standardise this.
Before running a workflow across 200 accounts, validate the output on 3–5 accounts.
Workflows produce consistent output, but consistency doesn't guarantee quality. Review and iterate.
A territory review workflow can identify accounts that need attention; an engagement plan workflow can generate plans for those accounts.
## Monitoring and troubleshooting
* **Workflow history** shows the status of every run: completed, failed, or in progress.
* **Step-level detail** shows which step failed and why.
* **Retry** is available for failed runs.
* **Output inspection** shows the generated content at each step.
## Related modules
Use the agent for one-off research and exploration before building repeatable workflows.
Workflows can generate Canvas documents as output for individual accounts.
Include email context in workflow steps for more personalised content generation.
# Custom Columns
Source: https://docs.getpg.ai/territory/custom-columns
Extend territory data with any field you need - populated manually, enriched by AI, or auto-refreshed on a schedule.
Custom Columns let you add any data field to your territory's account table. You define the question, choose a data type, and then populate it - manually, via AI enrichment, or with location data. AI enrichment researches each account using enriched data, public information, tech stack, jobs, and more to answer your question across all accounts automatically. Custom columns can be monitored and auto-refreshed to stay current as things change.
## Key Capabilities
Create custom fields on your territory account table. Define column types, names, and what they should contain. Use AI to suggest column structures based on descriptions.
Set values manually on individual accounts. Use AI enrichment to research and fill values automatically. Populate geographic data with location enrichment. Update values in bulk.
Scheduled change detection flags when values shift. Ongoing monitoring keeps custom columns current. Automatic refresh for AI-enriched columns. Value normalisation and standardisation.
## What Custom Columns Are
Custom columns are new data fields that you add to your territory account table. The key difference from standard enrichment: **you define the question, and PG:AI answers it for every account.**
Want to know each account's primary cloud provider? Their compliance posture? Whether they've been through a recent acquisition? You create a custom column, describe what you want to know, choose a data type (text, number, boolean), and PG:AI's AI researches each account and fills in the answer.
Custom columns can hold:
* **AI-researched answers** - PG:AI looks at enrichment data, public information, tech stack, jobs, and more
* **Manual values** - data you set yourself on individual accounts
* **Any data type** - text, numbers, booleans - whatever fits the question
## Viewing Custom Columns
### In the Companies Table
Custom columns appear as additional columns alongside PG:AI Score, firmographic data, and enrichment columns. Each custom column shows the AI-generated (or manually set) value for every account.
### On Account Profiles
Click into any account to see all custom column values, giving you the full picture alongside standard enrichment data.
## Common Workflows
### Getting a Specific Answer About Every Account
This is the core use case. You have a question that matters to your sales strategy, and you want the answer for every account in your territory.
Ask your admin to create a custom column (or create it yourself if you have access).
E.g., "What is this company's primary cloud infrastructure provider?"
Text for open answers, number for quantitative data, boolean for yes/no questions.
PG:AI's AI researches each account and populates the answer.
The answers appear as a column in your territory table - sortable, filterable, and ready to use.
**Examples of questions you can answer:**
| Question | Data type | Example output |
| -------------------------------------------- | --------- | ----------------------------------- |
| What is their primary cloud provider? | Text | "AWS", "Azure", "GCP" |
| Have they been through a recent acquisition? | Boolean | Yes / No |
| What compliance frameworks do they follow? | Text | "SOC2, GDPR, HIPAA" |
| How mature are their DevOps practices? | Text | "Early", "Established", "Advanced" |
| What is their estimated annual IT spend? | Number | 5000000 |
| Are they expanding internationally? | Boolean | Yes / No |
| What CRM do they use? | Text | "Salesforce", "HubSpot", "Dynamics" |
| What's their primary programming language? | Text | "Python", "Java", ".NET" |
The only limit is what you can describe clearly enough for AI to research.
### Using Custom Column Answers for Prioritisation
Once columns are populated:
Sort the territory by a custom column to see patterns - e.g., sort by "Primary Cloud Provider" to group all AWS accounts together.
Show only accounts where "Recent Acquisition" = Yes.
"Show me High-scoring accounts that use AWS and have been through a recent acquisition."
### Segmenting for Campaigns
Custom columns are powerful for campaign targeting:
Create a column like "DevOps Maturity" or "Digital Transformation Stage".
AI populates it across all accounts.
Filter your territory to accounts at the right stage for your campaign message.
"Early DevOps" gets an education-first approach, "Advanced DevOps" gets a peer comparison approach.
### Adding Your Own Context Alongside AI Answers
Some columns work best as manual additions:
* **Account tier** (Tier 1, 2, 3) - your team's strategic classification
* **Outreach status** - "Not started", "Sequenced", "Meeting booked"
* **Assigned rep** - who owns this account
* **Notes** - context that only you have
These sit alongside AI-populated columns, so your territory table combines PG:AI intelligence with your team's knowledge.
### Feeding Custom Columns into Scoring Models
Custom column values can be used as inputs to scoring models:
* If "Primary Cloud Provider = AWS" and you sell an AWS-optimised product, that should boost the score.
* If "Recent Acquisition = Yes", that might indicate budget disruption - positive or negative depending on your offering.
* If "DevOps Maturity = Advanced", that could mean they're ready for your product (or already have something similar).
Talk to your admin about which custom columns should feed into the scoring model.
## How AI Answers Stay Current
Custom columns can be configured to refresh automatically:
* **Scheduled refresh** - AI re-researches accounts periodically and updates values.
* **Change detection** - flags when an answer changes significantly (e.g., a company switches cloud providers).
* **Manual refresh** - re-run AI research on demand for specific accounts.
This means custom column data stays current without manual maintenance. A company that switches from Azure to AWS will have its "Primary Cloud Provider" column updated on the next refresh.
## Tips and Best Practices
**Be specific in your questions** - "Primary cloud provider" works better than "cloud stuff." The clearer the question, the more accurate the AI answer.
**Choose the right data type** - use boolean for yes/no questions, number for quantitative data, text for descriptive answers. The right type makes sorting and filtering work properly.
* **Start with high-value questions** - what data points, if you had them for every account, would most change how you prioritise? Start there.
* **Combine AI columns with manual columns** - AI tells you what's true about the account; manual columns track your team's decisions and status. Both are valuable.
* **Review AI answers for accuracy** - spot-check a few accounts you know well to validate that the AI is answering correctly. If not, refine the column description.
* **Don't over-create** - 5–10 well-chosen custom columns are more useful than 30 random ones. Each column should earn its place on the table.
* **Feed important columns into scoring** - if a custom column captures a signal that genuinely affects fit, make sure it's weighted in the scoring model.
## Related Modules
Custom column values can be used as scoring rule inputs.
Custom columns appear in territory account views.
AI enrichment for custom columns is part of the broader enrichment pipeline.
Custom column data surfaces in analytics.
# Employee Groups
Source: https://docs.getpg.ai/territory/employee-groups
Define which roles, departments, and employee segments at an account are relevant to your sale - so you know who to target and how the organisation is structured.
Employee Groups lets you define segments of employees based on role, title, department, or function - such as "Data Engineering", "Cloud Infrastructure", "VP+ in IT", or "Security & Compliance". The platform matches contacts and job data at every account against your definitions, showing you how many people fall into each group, what roles they hold, and how that's changing over time. This gives you a headcount and organisational view scoped to the parts of the company that matter to your sale.
## Key Capabilities
Define groups by role, title, department, function, or seniority. Build a library of employee segments relevant to your business and update as your target personas evolve.
See which employees at each account match each group. View headcount and role breakdown per group per account. Track changes over time - growing, shrinking, or stable.
## What Employee Groups Tell You
Employee groups show you the composition of people at each account. If you've defined groups like "DevOps Engineers", "C-Suite", or "Security Professionals", PG:AI matches employees at each company against those definitions and shows you the counts.
This tells you:
* Which accounts have the roles and personas you sell to
* How deep those teams are (1 DevOps engineer vs. 50)
* Whether an account has the organisational structure to be a buyer
## Viewing Employee Group Data
### In the Territory Companies Table
Employee group counts can appear as columns in the Companies table when enabled in your territory's Enriched Columns settings (type: Employee Groups). Each group becomes its own column, showing the count of matching employees per account.
### On Individual Account Profiles
Click into any account to see the full employee group breakdown. This gives you the complete picture of which groups are present and how large they are.
## Common Workflows
### Finding Accounts with the Right Personas
Navigate to your territory and go to the Companies tab.
If employee group columns are visible, sort by the group that represents your ideal buyer (e.g., "Platform Engineering" descending).
Accounts with the highest counts have the largest teams in that area - they're more likely to have budget and need.
### Qualifying an Account
When evaluating whether an account is worth pursuing:
Click into the account you're evaluating.
Do they have people in the roles you sell to? Is the team large enough to warrant an enterprise deal?
If you're selling a DevOps platform and the account has 40+ DevOps Engineers, that's a strong signal. If they have 2, it's a different conversation.
### Finding Contacts Within an Account
Employee groups aren't just counts - they're built from real employee data. Use the groups to:
See which job functions exist at the account.
Navigate to the contacts or employee data for that account.
Identify specific individuals to reach out to within each group.
### Combining Employee Groups with Other Signals
Employee groups are most useful in combination:
| Combination | What it means |
| -------------------------------------- | ------------------------------------------------------------------------- |
| **Employee groups + high PG:AI score** | Strong fit and the right people are there. |
| **Employee groups + insight scores** | They're investing in a topic AND they have the team to buy your solution. |
| **Employee groups + jobs** | They have the team AND they're hiring more - growing investment. |
## Tips and Best Practices
**Think about group size** - a large DevOps team might mean they already have tooling. A growing team (combine with Jobs data) might mean they're ready to buy.
**Groups change over time** - as PG:AI re-enriches accounts, employee group counts update. Review periodically to catch shifts.
* **Use groups for segmentation** - filter your territory to "accounts with 10+ Security Professionals" for a targeted outreach campaign.
* **Feed groups into scoring models** - employee group presence and size can be weighted in scoring models to boost accounts with the right organisational fit.
## Related Modules
Employee group data is an input to scoring rules (e.g. "score higher if 5+ people in target department").
Hiring signals complement employee groups by showing where an account is growing.
Criteria may evaluate similar themes, but employee groups focus specifically on people and roles.
Employee groups are scoped to territories.
# Jobs
Source: https://docs.getpg.ai/territory/jobs
Surface hiring signals across territory accounts - what companies are recruiting for, how that's changing, and what it tells you about their priorities.
Jobs surfaces hiring signals across all accounts in your territory. PG:AI aggregates job postings from job boards, company career pages, and enrichment sources - parsing, classifying, and linking them to technologies, titles, and functions. Job postings are one of the strongest public signals of a company's priorities: if they're hiring cloud architects, they're investing in cloud; if they're posting for data engineers, they're building a data function.
## Key Capabilities
View all job postings across territory accounts. Search by company, role, function, or keyword. See social job postings from LinkedIn and other platforms. Save and reuse search configurations.
Review job summaries per account. Spot patterns and trends across territory accounts. See which technologies are mentioned in job postings. Understand job title hierarchies and relationships.
Track hiring trends - growing, stable, or declining. Link technologies to specific job postings. Job data feeds criteria scoring and scoring models automatically.
## What Jobs Data Tells You
Job postings are one of the strongest buying signals available. When a company posts a role, it means they've secured budget, identified a need, and are actively investing.
PG:AI enriches your territory accounts with job posting data, so you can see:
* What roles each account is hiring for
* Which skills and technologies they're looking for
* How many open roles they have in relevant areas
* Whether hiring is accelerating or stable
## Viewing Jobs Data
### In the Territory Companies Table
Jobs data can appear as columns in the Companies table when enabled in your territory's Enriched Columns settings (type: Jobs). This lets you see job counts alongside other account data - score, revenue, industry, etc.
### On Individual Account Profiles
Click into any account to see the full job detail. This includes specific job titles, descriptions, locations, and posting dates - not just aggregated counts.
## Common Workflows
### Finding Accounts with Active Hiring Signals
Navigate to your territory's Companies tab.
If job count columns are visible, sort descending.
Accounts at the top are the most actively hiring in relevant areas.
These are your warmest opportunities - they have budget and need.
### Validating an Account Before Outreach
Navigate to the account and review the jobs data.
Are they hiring for roles related to what you sell?
Do they mention technologies, challenges, or initiatives that your product addresses?
If yes, you have a concrete, timely reason to reach out.
### Personalising Outreach with Job Context
Job postings give you specific talking points:
* "I noticed you're hiring 3 Senior Platform Engineers - companies at this stage often face \[problem your product solves]..."
* "Your job posting for a VP of DevOps mentions moving to Kubernetes. We help teams at that transition point..."
This is more compelling than generic outreach because it's relevant, timely, and shows you've done your homework.
### Tracking Hiring Trends Over Time
As PG:AI re-enriches accounts:
Accounts that go from 0 relevant jobs to multiple postings are ramping up.
Accounts that consistently hire in your target area are ongoing investors.
They may have filled roles - a good time to check if they need tools for the new team.
## Combining Jobs with Other Signals
Jobs data is powerful on its own, but even stronger in combination:
| Combination | What it means |
| -------------------------------------- | ------------------------------------------------------------------------------ |
| **High PG:AI Score + active jobs** | Strongest signal - fit + active investment |
| **High insight score + relevant jobs** | Strategic topic alignment + budget committed |
| **Large employee group + new jobs** | Growing team - likely buying tools to support scale |
| **High score + no jobs** | Good fit but may not be in buying mode - nurture |
| **Low score + lots of jobs** | Check the scoring model - they might be a better fit than the score suggests |
## Tips and Best Practices
**Jobs are time-sensitive** - a posting today may be filled next month. Act on strong job signals quickly.
**Look beyond titles** - the job description often contains more signal than the title. Technologies mentioned, team size, reporting structure - all useful context.
* **Feed jobs into scoring models** - job posting volume and relevance can be weighted in scoring models to boost accounts showing active demand.
* **Share with AEs weekly** - a "Top 10 accounts by new job postings" list is one of the most actionable things you can send a sales team.
* **Use jobs to validate cold accounts** - an account that's been dormant in your CRM might suddenly start hiring in your space. Jobs data catches that.
## Related Modules
Hiring-related criteria are scored using job data.
Job signals can be weighted as scoring rules.
Jobs show where an account is growing; employee groups show the current state.
Job data is part of the enrichment pipeline.
Job trends surface in analytics views.
# PG:AI Territory
Source: https://docs.getpg.ai/territory/overview
The go-to-market planning layer - define territories, score accounts, run AI scenarios, and focus your team on the best opportunities.
PG:AI Territory is the go-to-market planning layer of the PG:AI platform. It gives RevOps and sales leaders a structured, data-driven workspace to define territories, score and rank accounts, run AI-powered scenarios, and focus their teams on the opportunities that matter most.
Instead of managing territories in static spreadsheets, Territory brings together enriched account data, configurable scoring models, strategic insight criteria, and AI recommendations - all in one place.
![Territory with details sidebar and insight scores]()
## Who is Territory for?
**Primary users:**
* **RevOps leaders** - build territories, configure scoring models, run enrichment, and optimise coverage
* **Sales operations** - manage account assignments, maintain territory health, and prepare data for QBRs
**Secondary users:**
* **Sales leaders** - review territory performance, compare score distributions, and make strategic decisions
* **Account Executives** - prioritise accounts, prepare for meetings, and understand what's driving each account's score
* **SDRs/BDRs** - identify high-scoring accounts, find hiring signals, and personalise outreach
## Modules
Create, configure, and manage territories - add accounts, set enrichment preferences, and assign scoring models.
Define strategic topics and score every account against the initiatives that matter to your business.
Track how many employees at each account match specific roles, functions, or keywords.
Surface hiring signals by monitoring job postings across your territory accounts.
Combine data signals into a single account score so your team can focus on the best leads first.
Run what-if scenarios and get AI-powered recommendations to optimise territory coverage.
Ask any question about your accounts and let AI research and populate the answers at scale.
Configure which enriched data - tech stack, jobs, employee groups, insights - is active per territory.
Understand territory health, score distributions, segment breakdowns, and trends over time.
## Key Benefits
* **Score and rank every account** - turn multiple data signals (jobs, employee groups, insight criteria, tech stack) into one PG:AI Score per account
* **AI-powered scenario planning** - model territory changes before committing, with AI recommendations for rebalancing and coverage
* **Custom intelligence at scale** - ask any question about your accounts and get AI-researched answers across the entire territory
* **Always-current data** - enrichment runs continuously, keeping scores, job data, and insights fresh
* **Flexible territory structures** - support enterprise, mid-market, SMB, and velocity territories with different configurations
## How Territory Connects to the PG:AI Platform
Territory consumes enriched data from PG:AI Account - firmographic data, technographic signals, strategic insights, and contact information. Account is the data foundation that Territory scores and prioritises.
Territory's scoring and enrichment data feeds into PG:AI Studio workflows. Studio can automate follow-up actions when accounts cross score thresholds or territory composition changes.
PG:AI Monitoring tracks real-time changes across territory accounts - new job postings, score movements, enrichment updates - and surfaces alerts so your team can act on changes as they happen.
# Scenarios & Recommendations
Source: https://docs.getpg.ai/territory/scenarios-recommendations
Run AI-powered what-if territory plans - model different account assignments, get recommendations on where to focus, and accept or decline changes at scale.
Scenarios & Recommendations lets you create what-if versions of your territories and receive AI-powered suggestions for optimising coverage. A scenario inherits accounts, scores, and data from a live territory - then you make changes, model different structures, and compare outcomes without affecting anything live. The platform generates recommendations based on scoring model outputs, rep capacity, geographic proximity, and other signals.
## Key Capabilities
Create what-if scenarios from any live territory. Override account assignments, add or remove accounts, and review summaries showing changes vs. the base territory.
Generate AI-powered recommendations based on scores, capacity, and geography. Accept or decline individually or in bulk. Track recommendation acceptance rates and outcomes.
Calculate geographic proximity between reps and accounts. Model different rep allocations and capacity constraints. Apply scenario changes back to live territories when ready.
## What Scenarios and Recommendations Do
Scenarios let you ask "what if" questions about your territory:
* What if I changed the scoring model?
* What if I adjusted the weights?
* What if I added or removed accounts?
* What if I carved the territory differently?
Recommendations are AI-generated suggestions for improving your territory - accounts to add, accounts to remove, or changes that would strengthen overall coverage.
Together, they help you move from "here's my territory" to "here's the best version of my territory."
## Common Workflows
### Running a What-If Scenario
Navigate to the Scenarios section for your territory.
Choose what to adjust - scoring model, weights, account list, segmentation criteria.
Apply the change as a scenario (not permanently).
How do scores shift? Which accounts move up or down? Does the High/Medium/Low distribution improve?
If the scenario looks good, apply it permanently. If not, discard and try another.
### Reviewing AI Recommendations
Navigate to the Recommendations section.
PG:AI analyses your territory and suggests improvements based on data patterns.
Common types include:
* **Add accounts** - companies that match your territory criteria but aren't included
* **Remove accounts** - companies that score consistently low and may not be a good fit
* **Rebalance** - accounts that would perform better in a different territory or segment
* **Model adjustments** - suggestions for tweaking scoring weights based on conversion patterns
Accept, reject, or investigate further.
### Comparing Scenarios Side-by-Side
Apply one set of changes.
Apply a different set of changes.
Compare average score, score distribution, number of High accounts, coverage gaps.
Select the scenario that best aligns with your goals.
### Pre-QBR Territory Optimisation
Create a scenario with your current scoring model.
Review AI recommendations - are there obvious improvements?
Accept any recommendations that make sense.
Present the optimised territory with data backing your decisions.
## Understanding Recommendation Confidence
Recommendations may include a confidence level or strength indicator:
| Confidence | Meaning | Action |
| --------------- | ---------------------------------------------------------- | ------------------------------------------ |
| **Strong** | High-confidence suggestion backed by multiple data signals | Likely worth acting on |
| **Moderate** | Reasonable suggestion, but based on fewer signals | Review the underlying data before deciding |
| **Exploratory** | Pattern detected, but not conclusive | Worth investigating, not auto-accepting |
Always check the reasoning behind a recommendation. Understanding **why** PG:AI made the suggestion is more valuable than just following it.
## Tips and Best Practices
**Use scenarios before major changes** - before restructuring territories or changing scoring models, run a scenario first to see the projected impact.
**Don't accept all recommendations blindly** - AI sees patterns in data; you have context it doesn't (relationship history, pending deals, strategic accounts).
* **Iterate** - the best territories come from multiple rounds of scenario testing and refinement.
* **Document decisions** - when you apply a scenario or act on a recommendation, note why. This helps when reviewing performance later.
* **Review recommendations monthly** - as data changes (new enrichment, new job postings, score updates), new recommendations will surface.
## Related Modules
Scoring model outputs are a primary input to AI recommendations.
Scenarios are built from and save back to live territories.
Scenario outcomes can be compared using analytics.
Insight scores feed the recommendations engine.
# Scoring Models
Source: https://docs.getpg.ai/territory/scoring-models
Build rule-based models that combine insight scores, enrichment data, job signals, and custom criteria into a single account rank.
Scoring Models let you build rule-based models that combine insight scores, enrichment data, job signals, employee groups, financials, tech stack, and custom columns into a single composite score per account. Each rule maps a signal to a score contribution - and the model combines them into the **PG:AI Score** you see in the territory Companies table. Think of it as a recipe: each ingredient (signal) contributes a weighted amount to the final score.
![Territory scoring model]()
## Key Capabilities
Build and manage multiple scoring models per territory. Define scoring rules, weight them, and publish models to make them live. Quick-start with baseline models or build from scratch.
Create rules for any data point - criteria scores, employee groups, jobs, enrichment, financials, tech stack, custom columns. Set thresholds and weights for each rule.
Score all accounts in a territory automatically. Scores recalculate as underlying data changes. See per-account score breakdowns showing how each rule contributed.
## How Scores Are Calculated
Each scoring model is built from **criteria** - the individual data points being evaluated. Each criterion has:
* **A data source** - which signal it looks at (insight score, employee group count, job posting count, etc.)
* **A weight** - how much this criterion matters relative to others
* **Thresholds** - the boundaries that determine scoring (e.g., "5+ DevOps Engineers = high signal")
The model runs these criteria against every account in the territory and produces a normalised score (typically 0–100).
### Example Rules
* "If insight score for 'cloud transformation' > 70, add 20 points"
* "If employee group 'data engineering' has 5+ people, add 15 points"
* "If company revenue > \$100M, add 10 points"
* "If hiring for relevant roles (from Jobs), add 10 points"
## Reading Account Scores
### In the Companies Table
| Column | What it shows |
| --------------- | ------------------------------------------------------------- |
| **PG:AI Score** | The overall numerical score from the active scoring model |
| **Score badge** | High / Medium / Low - colour-coded classification |
| **Sentiment** | Positive / Neutral - directional indicator of recent change |
### Score Badge Thresholds
The score badge is determined by the thresholds configured in the scoring model:
* **High** (green) - above the upper threshold
* **Medium** (amber) - between the thresholds
* **Low** (red/grey) - below the lower threshold
The exact boundaries depend on how the model is configured. Check with your admin if you're unsure where the cutoffs are.
## Common Workflows
### Understanding Why an Account Scored High
Navigate to the account in the territory.
Look at insight scores, employee groups, jobs, firmographic data.
The account is scoring high because it performs well on the criteria that carry the most weight. For example: if the model heavily weights "DevOps Engineers" and "Cloud Transformation" insight score, an account with 50 DevOps Engineers and a 90 on Cloud Transformation will score very high - even if it's a small company.
### Questioning a Score That Seems Wrong
If an account looks like a great fit but scores low (or vice versa):
Is it looking at the right signals for your use case?
Has the account been fully enriched? Missing data leads to lower scores.
Maybe the model over-weights a criterion that doesn't apply to this account.
The model may need adjusting, or a different model may be more appropriate.
### Comparing Score Distributions
Navigate to the territory Overview for a summary of score distribution.
Look at how many accounts are High, Medium, and Low.
A healthy territory typically has a pyramid: fewer Highs, more Mediums, most Lows.
If everything is Medium, the model may need sharper differentiation (wider weight spread or stricter thresholds).
### Acting on Score Changes
Scores aren't static - they update as new data flows in (new job postings, updated enrichment, market changes).
Periodically check for accounts that moved up (Medium → High). These are emerging opportunities.
Look for accounts that dropped (High → Medium). Investigate why - did they stop hiring? Did an insight score decline?
The Sentiment column helps - Positive sentiment suggests upward movement.
## Multiple Scoring Models
Your territory may have access to more than one scoring model. Each model can be built for a different purpose:
* **ICP Model** - scores accounts against your ideal customer profile
* **Expansion Model** - scores existing customers for upsell potential
* **New Logo Model** - scores net-new accounts for acquisition fit
The active model determines the PG:AI Score shown in the Companies table. You can switch models to see the same accounts scored from different angles.
## Tips and Best Practices
**Trust the model, but verify** - scoring models surface patterns at scale. For your top accounts, always click in and understand what's driving the score.
**Don't chase the score, chase the story** - a high score gets the account onto your radar. The combination of insight scores, jobs, employee groups, and firmographic data tells you why they're a fit and how to engage.
* **Request model updates** - if the model isn't differentiating well (too many accounts at the same score), ask your admin to review the weights and criteria.
* **Use scores for prioritisation, not elimination** - a low score doesn't mean "don't engage." It means "other accounts are probably a better use of your time right now."
* **Combine model score with your own knowledge** - you know your accounts. The model knows the data. Together, you make better decisions.
## Related Modules
Insight scores are a primary input to scoring model rules.
Employee group headcounts and role data feed scoring rules.
Hiring signals are an input to scoring rules.
Custom data can be used in scoring rules.
Scoring model outputs drive AI-powered recommendations.
Scoring results surface in analytics.
# Strategic Insights Scoring
Source: https://docs.getpg.ai/territory/strategic-insights-scoring
Define the topics that matter to your business and score every account on how strongly they align - turning strategic priorities into measurable signals.
Strategic Insights Scoring lets you define **criteria** - the topics, themes, and strategic initiatives that matter to your business - and then score every account in a territory against them. A criterion might be "cloud transformation initiatives", "AI/ML adoption", or "data engineering investment". The platform scores each account using enriched data (jobs, tech stack, financials, public intelligence), producing a per-account, per-criterion **insight score** that tells you how strongly that account aligns with each topic.
![Strategic Insights Scoring in PG:AI Territory]()
## Key Capabilities
Define criteria as strategic topics, themes, or initiatives. Manage your criteria library as your strategy evolves. Describe what each criterion means in business terms.
Scores derived from enrichment data, jobs, tech stack, financials, and public intelligence. Scheduled scoring updates keep criteria current as data changes.
Configure how each criterion evaluates accounts. Group related queries together. Fine-tune which data sources and signals feed into each criterion.
## What Insight Scores Tell You
Each account in your territory has a score for every insight criterion you've defined. If you've set up criteria like "DevOps Transformation" and "Global Expansion", every account gets scored on both.
* **A high score** means the account shows strong signals related to that topic - they're hiring for it, investing in it, or publicly talking about it.
* **A low score** means little to no evidence of activity related to that topic.
## Viewing Insight Scores
### In the Territory Insights Tab
Open your territory and switch to the **Insights** tab. This shows criteria scores aggregated across all territory accounts - which strategic topics your territory is most aligned with overall.
### In the Territory Companies Table
Insight scores can appear as columns in the Companies table. If insight criteria are enabled in your territory's Enriched Columns settings (type: Insights), the scores show alongside other account data.
### On Individual Account Profiles
Click into any account to see per-criterion scores in the account profile. This shows you exactly how each account scores against each strategic topic.
## Common Workflows
### Understanding Why an Account Scores High
Navigate to the account you want to investigate.
Identify which criteria the account scores highest on.
A high score on "Platform Engineering Transformation" means the account is showing signals - hiring platform engineers, adopting relevant tech, publishing content about platform engineering.
Check Jobs data and Tech Stack to see the specific evidence driving the score.
### Comparing Accounts on a Specific Topic
Navigate to your territory's Companies tab.
If the criterion's insight score is visible as a column, sort by it.
See which accounts are strongest and weakest on that specific topic.
Prioritise accounts where your value proposition is most relevant.
### Spotting Opportunities Across Criteria
Look for territory-wide patterns across all criteria.
If "Software Delivery Acceleration" scores high across many accounts, that's a theme you can build messaging around.
If "Global Expansion" scores high for only a few accounts, those are targeted opportunities worth specific attention.
### Using Insight Scores in Conversations
Insight scores give you specifics for personalised outreach:
* "I noticed your company is investing heavily in DevOps transformation - we help companies at this stage by..."
* "Your hiring signals suggest you're accelerating platform engineering - here's how we can help..."
The score gives you confidence. The underlying data (jobs, tech stack, public intelligence) gives you the talking points.
## Interpreting Scores
| Score range | What it means | How to act |
| ----------- | ----------------------------------- | ------------------------------------------------------------------------------ |
| **80–100** | Very strong alignment to this topic | High priority - this account is actively investing in this area |
| **60–79** | Moderate-to-strong signals | Good fit - worth investigating and engaging on this topic |
| **40–59** | Some signals, not definitive | Monitor - may be early stage or the signals are indirect |
| **0–39** | Little to no alignment | This topic isn't a strong angle for this account - try a different criterion |
Scores are relative, not absolute. An 80 means strong signals compared to other accounts, not that 80% of some measure is met.
## Tips and Best Practices
**Don't rely on a single criterion** - look at the pattern across multiple criteria to build a full picture of an account.
**Cross-reference with Jobs** - if an account scores high on "AI/ML Adoption", check if they're actually hiring AI/ML roles. That's the strongest validation.
* **Use criteria scores in scoring models** - insight scores are most powerful when they feed into scoring models, where they're combined with other signals for an overall account rank.
* **Review criteria quarterly** - strategic priorities shift. Update your insight criteria to match your current GTM focus.
* **Share insights with reps** - insight scores give AEs a reason to reach out. Make sure they know how to find and interpret them.
## Related Modules
Insight scores are a primary input to scoring model rules.
Criteria are scoped to territories.
Enrichment data feeds the signals that criteria scores are derived from.
Insight scores surface in analytics views.
# Territory Analytics
Source: https://docs.getpg.ai/territory/territory-analytics
Understand territory performance at a glance - account aggregates, geographic distribution, activity tracking, insight scores, and exportable reports.
Territory Analytics provides a unified view of territory health - built directly on top of Territory Management, Scoring Models, Criteria, Enrichment, and the intelligence layer. It shows score distributions, segment breakdowns, geographic maps, activity tracking, and exportable reports. Analytics update in real time as underlying data changes, so you're always working with the latest picture.
## Key Capabilities
Territory-level analytics dashboard with key metrics. Account aggregates by industry, size, score band, and more. Insight score aggregations across territory accounts.
Map view showing account distribution by location. Spot coverage gaps and geographic concentration.
Track platform activity per territory - which accounts are being viewed and researched. Monitor active vs. inactive accounts. See which accounts have been added recently.
Detailed account-level tracking with full context. Export territory data for QBRs, leadership reviews, or offline analysis.
## What Territory Analytics Provides
Analytics gives you the big picture. While the Companies table shows account-level detail, analytics shows you patterns, distributions, and trends across the whole territory:
* How are scores distributed? Is the territory healthy or flat?
* Which industries or segments are strongest?
* How has the territory changed over time?
* Where are the gaps in coverage?
This is the view you use for territory reviews, QBRs, and strategic planning.
## Key Metrics and Views
### Score Distribution
See how accounts are spread across score bands:
* **A healthy territory** has a clear spread - some Highs, a solid middle, and a long tail of Lows.
* **A flat territory** (everything clustered at Medium) suggests the scoring model needs tuning or enrichment gaps exist.
* **A top-heavy territory** (lots of Highs) is either very well-targeted or the thresholds are too generous.
### Segment Breakdown
Analytics can break down your territory by:
* **Industry** - which industries have the best-scoring accounts?
* **Company size** - are you strongest with mid-market, enterprise, or SMB?
* **Geography** - which regions have the most opportunity?
* **Score band** - how many accounts in each tier?
### Trend Analysis
If historical data is available:
* How have scores changed over time?
* Is the territory improving (more Highs) or deteriorating (more Lows)?
* Are new accounts being added faster than old ones are declining?
## Common Workflows
### Monthly Territory Health Check
Navigate to the analytics view for your territory.
Is it broadly the same as last month, or have there been shifts?
Are you gaining or losing top-tier accounts?
Look for segments that are declining - investigate why.
Record your findings for your manager or the team.
### Preparing for a QBR
Navigate to the analytics view.
Export or screenshot the key views: score distribution, segment breakdown, trend charts.
Total accounts, % High, % Medium, top industries, top segments.
"Territory is 15% High, up from 12% last quarter. Growth driven by financial services segment."
"If we add 20 more accounts from target list, projected score distribution shifts to..."
### Identifying Coverage Gaps
Look at how accounts are distributed across industries.
If your ICP includes Healthcare but your territory has very few Healthcare accounts (or they all score Low), that's a coverage gap.
Are the right accounts in the territory? Is the scoring model configured to value Healthcare-relevant signals?
Use this insight to request territory adjustments or scoring model changes.
### Comparing Territories
If you manage multiple territories or are benchmarking:
Open analytics for each territory you want to compare.
Which territory has the best score distribution? The highest % of Highs?
Look at what's different - scoring model? Account mix? Enrichment coverage?
Apply lessons from high-performing territories to others.
## Reading Analytics Charts
### Score Distribution Chart
* **X-axis**: Score ranges (0–20, 20–40, 40–60, 60–80, 80–100)
* **Y-axis**: Number of accounts
* **Ideal shape**: Right-skewed bell curve - most accounts in the middle, a meaningful tail on the right (high scores)
* **Warning shape**: Spike at one score - usually means enrichment or scoring hasn't fully processed
### Segment Pie/Bar Charts
* Show account counts or percentages by category (industry, size, geography).
* Use these to answer: "What does my territory look like?" and "Where is it concentrated?"
## Tips and Best Practices
**Review analytics before acting, not just after** - use analytics to decide what to do, not just to report on what happened.
**Trend matters more than snapshot** - a territory with 10% Highs that was at 5% last quarter is healthier than one with 15% Highs that's declining from 20%.
* **Combine analytics with qualitative context** - the numbers say "Healthcare accounts score low." You might know that's because the scoring model doesn't weight healthcare-relevant criteria. Fix the model, don't ignore the segment.
* **Share analytics with the team** - make territory health visible. When the whole team can see the score distribution and trends, decisions are better informed.
* **Set benchmarks** - define what "good" looks like for your territory (e.g., "at least 20% High, average score above 55") and track against it.
## Related Modules
Analytics operate on the accounts and structure defined in Territory Management.
Scoring results are a primary data source for analytics.
Insight scores aggregate into analytics views.
Enrichment coverage and completeness surface in analytics.
Use analytics to guide scenario planning.
# Territory Enrichment
Source: https://docs.getpg.ai/territory/territory-enrichment
Run enrichment scoped to a territory - batch enrich all accounts against the data points you need, track every run, and see exactly what was enriched.
Territory Enrichment lets you run enrichment scoped to a specific territory. You select a territory, choose which enrichment types to run (tech stack, financials, jobs, contacts, insights), and trigger a batch run. The platform queues enrichment jobs for every account, respects rate limits and credit budgets, and processes them in the background. Enrichment results flow into every other module: insight scores recalculate, scoring models update, job data refreshes, and custom columns re-evaluate. Territory Enrichment is the engine that keeps territory data fresh.
![Territory enrichment trigger]()
## Key Capabilities
Enable or disable specific enrichment types per territory. Trigger batch enrichment across all accounts. Available types include tech stack, financials, jobs, contacts, and insights.
Track every enrichment run with status, timing, and results. Drill into individual jobs to see what succeeded, failed, or is pending. Analyse territory enrichment coverage.
Enrichment data feeds directly into account-level insights. Insights refresh automatically as enrichment completes.
## What Enrichment Does
Enrichment is the process by which PG:AI gathers external data for every account in your territory. Instead of relying only on basic firmographic data (company name, size, industry), enrichment adds layers of intelligence:
* **Insight scores** - how each account aligns to your strategic topics
* **Employee groups** - who works there and in what roles
* **Jobs** - what they're hiring for right now
* **Tech stack** - what technologies they use
* **Public intelligence** - news, funding, partnerships, and other signals
This enriched data feeds into scoring models and drives the PG:AI Score.
## How Enrichment Runs
Enrichment is configured at the territory level by your admin. Key things to know:
* **Enrichment runs automatically** - once configured, PG:AI enriches accounts on a schedule without manual intervention.
* **It's cumulative** - each enrichment run adds to and updates the existing data. It doesn't start from scratch.
* **Some data changes frequently** - job postings and news update often. Employee data and tech stack change more slowly.
* **New accounts get enriched** - when accounts are added to the territory, they're queued for enrichment.
## Viewing Enriched Data
### In the Companies Table
Enriched data appears as columns in the table. Depending on your territory's Enriched Columns configuration, you might see:
* Insight score columns (one per criterion)
* Employee group count columns (one per group)
* Job posting columns
* Tech stack and other enrichment columns
Use the column selector to show the enrichment columns most relevant to your work.
### On Account Profiles
Click into any account to see the full enrichment detail - all insight scores, all employee groups, all job postings, tech stack, and any other enriched data. This is the richest view.
## Common Workflows
### Checking Enrichment Freshness
Look at the enrichment status or last-enriched date on accounts (if visible).
Recently enriched accounts have the most current data.
If an account hasn't been enriched recently and you're about to engage, ask your admin to trigger a refresh.
### Acting on Newly Enriched Data
After an enrichment run:
Scores may have shifted - sort the Companies table to see the new ranking.
Look for accounts that moved up significantly - these are newly surfaced opportunities.
Check for accounts that dropped - investigate why (lost a key employee group? Stopped hiring?).
Check insight scores for recently added criteria.
### Understanding Data Gaps
Not every account will have complete enrichment:
* **Small companies** may have limited public data, leading to lower enrichment coverage.
* **Private companies** may have less available information than public ones.
* **New accounts** may not yet have been enriched (check the enrichment schedule).
A lower PG:AI Score might reflect incomplete data rather than poor fit. Always check what data is actually available before dismissing an account.
## Enrichment Types at a Glance
| Enrichment type | What it provides | How often it changes |
| ---------------------- | -------------------------------------------- | -------------------- |
| **Strategic insights** | Topic-based scoring from public intelligence | Weekly to monthly |
| **Employee groups** | Role and function composition | Monthly |
| **Jobs** | Active job postings and hiring signals | Weekly |
| **Tech stack** | Technologies and tools in use | Monthly to quarterly |
| **Firmographic** | Revenue, employee count, industry, location | Quarterly |
## Tips and Best Practices
**Don't wait for enrichment to engage** - if you have a meeting tomorrow, use whatever data is available. Enrichment is for systematic prioritisation, not a prerequisite for every action.
**Enrich before territory reviews** - if you're doing a QBR or territory review, ask your admin to run enrichment beforehand so you're working with the freshest data.
* **Report data quality issues** - if you see obviously wrong data (wrong industry, wildly off employee count), flag it. This helps improve the enrichment quality for everyone.
* **Combine enrichment with your own intelligence** - PG:AI enrichment is comprehensive, but you know things the platform doesn't (relationship history, verbal commitments, internal champions). Layer both.
* **Understand what drives your score** - the score is only as good as the enrichment behind it. If insight scores aren't populated (criteria not configured) or jobs aren't being tracked, the score won't reflect reality.
## Related Modules
Enrichment data feeds the signals that criteria scores are derived from.
Enrichment updates the data that scoring rules evaluate.
Job data is one of the enrichment types that territory enrichment runs.
AI enrichment for custom columns is a related enrichment path.
Enrichment status and coverage surface in analytics.
# Territory Management
Source: https://docs.getpg.ai/territory/territory-management
Create, configure, and manage territories - the containers that hold your accounts, filters, and go-to-market logic.
Territory Management is the foundation of PG:AI Territory. A territory is a first-class entity - you create it, give it a name and settings, and populate it with accounts. Each territory has its own settings, filters, and technology associations. Every other module operates on territories: scoring models score the accounts within them, insight criteria evaluate them, enrichment runs against them, and analytics report on them.
## Key Capabilities
Build territories from scratch or clone existing ones to model alternatives. Configure territory-specific settings and manage structure as your GTM strategy evolves.
Add accounts manually, in bulk, or via CSV import. Remove accounts individually or in batches. Drill into per-account details within each territory.
Define filters to automatically include accounts based on criteria. Apply dynamic filters to keep territory membership current.
Track specific technologies within a territory. Technology associations feed into scoring and enrichment rules.
## Your Territory at a Glance
When you open a territory, you land on the **Companies** tab - a table of every account in the territory. This is your primary workspace.
Each row is an account. Key columns at a glance:
| Column | What it shows |
| ----------------- | -------------------------------------------------------- |
| **PG:AI Score** | The overall account score. Higher = stronger fit. |
| **Score badge** | High / Medium / Low - colour-coded for quick scanning. |
| **Sentiment** | Positive / Neutral - directional indicator. |
| **Revenue** | Company revenue. |
| **Employee Size** | Number of employees. |
| **Industry** | Industry classification. |
| **Country** | Account location. |
Sort by PG:AI Score to see your best accounts at the top.
## Common Workflows
### Reviewing Your Territory
Navigate to the territory you want to review.
Sort descending to see the highest-scoring accounts first.
How many High vs. Medium vs. Low? This gives you a quick health check.
Click into any account for the full profile - enrichment data, contacts, insights, jobs, and more.
If most accounts show 50.00 with a Medium badge, the scoring model may not be configured yet or enrichment hasn't run. Check Territory Settings.
### Finding Accounts to Prioritise
Sort by PG:AI Score descending.
Filter by score badge = High to see only the strongest accounts.
Do the scores match your expectations?
For each high-scoring account, check what's driving the score: insight criteria, jobs, employee groups, tech stack.
### Checking What's Changed
Look at recently added accounts (sort by date if available).
Check accounts whose scores have changed - have any moved from Medium to High or dropped from High to Medium?
Check the sentiment column for directional shifts.
### Preparing for a Meeting
Open the territory and find the account you're meeting with.
Click into the account for the full view.
Check: PG:AI Score, insight scores (which strategic topics they align with), jobs (what they're hiring for), contacts (who to talk to), and any custom column data.
Use this context to prepare questions and talking points for the meeting.
## Working with the Companies Table
### Sorting and Filtering
* Click any column header to sort ascending/descending.
* Use the filter icon to narrow by industry, country, revenue range, employee size, score band, or any other column.
* Filters are useful for focusing on a segment: "Show me all High-scoring accounts in the UK with 500+ employees."
### Customising Columns
The table can show more than the default columns. Additional columns may include:
* Enriched data columns (tech stack, jobs, employee groups)
* Custom columns (any custom fields you've created)
* Insight scores (strategic criteria scores)
Use the column selector to show or hide columns based on what you need.
### Selecting and Acting on Accounts
* Select individual accounts or use bulk selection.
* Available actions may include: remove from territory, trigger enrichment, view profile, export.
## Navigating Between Territory Views
The top of the territory page has tabs:
| Tab | Use it for |
| ------------- | -------------------------------------------------------------- |
| **Overview** | Quick territory summary - key metrics and score distribution |
| **Companies** | Full account table - your main workspace |
| **Insights** | Strategic insight scores across all territory accounts |
Switch tabs depending on what you're doing:
* **Overview** for a health check.
* **Companies** for day-to-day account work.
* **Insights** for understanding which strategic themes your territory aligns with.
## Tips and Best Practices
**Check your territory weekly** - scores and enrichment data update continuously. A weekly review catches changes early.
**Use score badges for triage** - High = deep dive, Medium = watch and wait, Low = deprioritise unless something changes.
* **Combine score with context** - a high score is a signal, not a guarantee. Click into the account and understand what's driving it.
* **Export before QBRs** - download the territory data for offline review and sharing with leadership.
* **Favourite your key accounts** - bookmark or star the accounts you're actively working so they're easy to find.
## Related Modules
Evaluate accounts within a territory against defined strategic topics.
Score and rank accounts within a territory.
Run enrichment scoped to a territory's accounts.
Report on territory performance and account activity.
Use territories as the basis for AI-powered planning.
# Accounts
Source: https://docs.getpg.ai/workspace/account-library
Manage every company in your workspace from one sortable, searchable table
**Accounts** is your complete view of every company in your PG:AI workspace. It's a sortable, searchable table showing domain, industry, country, employee size, revenue, and content count for every account - the management layer for your portfolio.
![Workspace accounts list with filters]()
## What you see
Every account in your workspace appears in the table with:
* **Company name and domain**
* **Industry** - the sector classification
* **Country** - headquarters location
* **Employee count** - company size
* **Revenue** - annual revenue where available
* **Content count** - how much intelligence PG:AI has gathered for this account. Higher numbers mean deeper intelligence
All columns are sortable. Click any column header to sort ascending or descending.
## Filtering
The sidebar gives you multi-faceted filtering:
* **Country** - filter to specific geographies
* **Industry** - focus on specific sectors
* **Revenue band** - segment by company size
* **Employee size** - filter by headcount ranges
* **City and state** - drill into specific locations
* **My Accounts** - toggle to see only accounts assigned to you, or expand to the full workspace
Combine filters for precise segmentation. "All German financial services companies with 1,000+ employees" is two clicks.
## Adding companies
Search for a company by name directly from **Accounts**. When you find it:
1. Click **Add** to bring it into your workspace
2. PG:AI starts building intelligence immediately - no manual data entry, no CSV imports
3. Enrichment runs automatically across all intelligence dimensions
Content count is a quick indicator of intelligence depth. A newly added account starts at zero and climbs as enrichment runs. Accounts with high content counts have the richest intelligence available.
## How to use it
**Portfolio management:** Sort by content count to see which accounts have the deepest intelligence and which might need enrichment. Sort by revenue or employee count to segment by company size.
**Adding new accounts:** When you pick up new accounts or start a new territory, use the search to add companies one at a time. For bulk additions, use Territory import.
**Quick lookup:** Search for a specific company to jump straight to its account page. Faster than navigating through Territory.
## Related features
Territory is where you score, prioritise, and plan across accounts. Accounts is the simpler management view for the full portfolio.
Accounts shows companies. Contacts shows people across those companies. Both live in Workspace.
Accounts lists your companies. Unified Search lets you query the intelligence inside them.
# Activity Pulse
Source: https://docs.getpg.ai/workspace/activity-pulse
See what's happening across your entire book of business at a glance
Activity Pulse is the at-a-glance view of what's happening across your entire book of business. It brings together every meaningful event from every account - strategic priorities, goals and risks, hiring activity, earnings calls and investor days, news and web mentions, technology adoption, regulatory filings, and digital strategies - so you can see what needs attention today.
This is the dashboard sellers open first thing in the morning: a one-screen answer to "what's happening across my accounts that I need to act on today?"
![Activity Pulse with relevance view and details sidebar]()
## What you see
Events are shown so that the most strategically interesting moments stand out from routine noise. A new strategic priority disclosed in an earnings call reads differently from a routine job posting - you see the signal without needing to filter manually.
## Intelligent weighting
Activity Pulse is smart about volume. A company posting a thousand jobs in a week shouldn't drown out three earnings-call insights from the same week.
Built-in weighting ensures that a small number of high-signal events is just as visible as a large volume of low-signal noise:
* **High signal:** A new strategic priority, a leadership hire, a risk disclosure, an earnings call with strategic shifts, a major technology adoption
* **Moderate signal:** News mentions, web page updates, conference presentations, analyst events
* **Routine signal:** Standard job postings, minor technology mentions, routine filings
The weighting is automatic. You don't need to configure it - Activity Pulse understands which events matter most and surfaces them accordingly.
## Drilling down
From Activity Pulse, you can:
* **Open the details sidebar** - full context, related items, and source attribution for any event
* **Jump to Unified Search** - read the full record of any event, with sources and related items
* **Open the account** - click through to the full account page for deep intelligence
The transition is seamless - you never leave the Workspace to explore what Activity Pulse surfaces.
## How to use it
**Morning check-in:** Open Activity Pulse before anything else. Scan for heating accounts and unusual spikes. Prioritise your day based on what's changed.
**Weekly review:** Look at the last week's activity across your portfolio. Identify which accounts had meaningful signals and which stayed quiet. Plan your outreach accordingly.
**Pre-meeting scan:** Before a team meeting or pipeline review, check Activity Pulse to see which accounts have fresh intelligence. Walk in knowing what's changed.
**Portfolio health:** Over a longer time range, Activity Pulse shows you which accounts are consistently active (and therefore worth more attention) and which have gone dark.
## Related features
Spot something on the Pulse? Search the topic to see which other accounts have similar signals. Seamless transition between the two.
Monitoring watches for specific changes and sends alerts. Activity Pulse gives you the big-picture view that individual alerts can't provide.
Territory Analytics shows scoring and segmentation. Activity Pulse shows real-time activity. Together they give you the full picture of your portfolio.
# Contacts
Source: https://docs.getpg.ai/workspace/contact-directory
Every contact across every account, searchable and filterable in one view
**Contacts** gives you a cross-account view of every person in your PG:AI workspace. Instead of opening accounts one at a time to find people, this view shows all contacts in one searchable, filterable table.
![Workspace contacts list with filters]()
## What you see
Every contact across all your accounts appears in the table with:
* **Name and job title**
* **Persona** - the persona tag PG:AI has matched them to (e.g. "AI / ML Leaders", "VP Engineering", "CTO / CIO")
* **Company** - which account they belong to
* **Country** - their location
* **Email** - verified email address where available
* **Enrichment status** - whether the contact has been enriched with additional data
All columns are sortable. Click any column header to reorder.
## Filtering
The sidebar filters let you slice the directory:
* **Persona** - filter to specific buyer personas you've defined in Configuration
* **Country** - focus on specific geographies
* **City** - drill into specific locations
* **Company** - narrow to contacts at specific accounts
Combine filters to find exactly who you need. "All AI / ML Leaders in the UK" or "All VP-level contacts at financial services companies" are simple filter combinations.
## How to use it
**Multi-threaded prospecting:** Filter by persona across your entire portfolio to find all the right stakeholders at once. Build outreach lists without opening accounts individually.
**Event preparation:** Attending a conference or industry event? Filter by city and persona to see which contacts from your accounts might be there.
**Team handoffs:** When reassigning accounts, use the directory to quickly see all contacts associated with specific companies.
**Enrichment management:** Sort by enrichment status to see which contacts need email and phone number enrichment. Prioritise enrichment for your most important personas.
Personas are defined in Configuration. The more precisely you define your buyer personas, the more useful the persona filter becomes in **Contacts**.
## Related features
Discovery finds new contacts at target accounts. **Contacts** shows everyone you've already discovered and enriched.
Click any contact in the directory to see their full intelligence profile - career history, expertise, buying role prediction, and relevance graph.
Accounts shows companies. Contacts shows people. Both are cross-account views in Workspace.
# Workspace
Source: https://docs.getpg.ai/workspace/overview
Search across everything PG:AI knows and see what's happening across your entire book of business
Workspace is the cross-account layer of PG:AI. While Account gives you deep intelligence on a single company and Territory helps you prioritise, Workspace lets you search, explore, and monitor activity across your entire portfolio from one place.
It has two core capabilities that share the same underlying intelligence: **Unified Search** for finding anything across all your accounts, and **Activity Pulse** for seeing what's happening right now.
Unified Search and Activity Pulse share the same taxonomy of event types, relevance model, and account data. You can spot a heating account on the Pulse, click into its timeline, search across its history, and resolve any single event into full detail without ever leaving the Workspace.
Unified Search
## Who it's for
**Account executives & strategic account managers** - Open first thing in the morning to see what's changed across your accounts. Search for specific topics across your entire book to find the accounts that matter most.
**Sales leaders & RevOps** - Monitor team activity, spot heating accounts, and identify which signals deserve follow-up across the entire organisation's portfolio.
**BDRs & prospecting teams** - Search for strategic topics across all accounts to find new angles and opportunities you didn't know existed.
**Customer success teams** - Track activity across your portfolio and catch changes before they become problems.
## What you can do in Workspace
One search box for everything PG:AI knows - insights, contacts, jobs, public events, news, web pages, technologies, documents, and conversations. Semantic search that understands what you mean, not just what you type.
See what's happening across your entire book of business at a glance. Spot heating accounts, fresh signals, and what deserves your attention today.
Chronological feed of every meaningful event for an account - or activity across your book. Paginated, time-ordered, filterable.
Every company in your workspace in one sortable, searchable table. Manage your portfolio, add new companies, and see intelligence depth at a glance.
All contacts across all accounts - searchable and filterable by persona, company, country, and role. Your cross-account people view.
## Key benefits
Stop remembering which tab or system holds what. Unified Search queries insights, contacts, jobs, events, news, web pages, technologies, and documents from one box.
Activity Pulse collapses every meaningful event into a single visual. The most strategically interesting moments stand out from routine noise.
Search for a strategic topic and find accounts you didn't realise were relevant. The relevance graph shows connections you'd never find manually.
A company posting a thousand jobs in a week doesn't drown out three earnings-call insights. High-signal events stay visible above routine noise.
Timeline for what's changed, Company view for which accounts matter, Relevance Graph for how everything connects. Same data, different lenses.
Click any result to see the full record, its sources, and related items. Jump from a search result to the account page in one click.
## How the pieces connect
Workspace brings together intelligence from every other module:
1. **Start with Activity Pulse** - Open it first thing in the morning. See which accounts have new activity and which signals are worth investigating.
2. **Search to explore** - Spot something interesting on the Pulse? Search the topic across your full portfolio to see which other accounts have similar signals.
3. **Switch views** - Use Timeline to see what's recent, Company view to compare accounts, Relevance Graph to discover connections.
4. **Drill into accounts** - Click through to the full account page for deep intelligence, or open the sidebar for a quick look.
5. **Take action in Studio** - Found something worth acting on? Jump to Studio to create a briefing, trigger a workflow, or assign a task.
## Connections to other modules
Every search result links back to full account intelligence. Drill down from a search hit to strategic priorities, financials, tech stack, and more.
Territory scores and enrichment data feed into search relevance. Workspace helps you discover accounts that Territory scoring might surface differently.
Monitoring events appear in Activity Pulse and are searchable via Unified Search. Workspace gives you the big picture that individual alerts can't.
Discover something in Workspace, act on it in Studio. Search results and Activity Pulse insights feed naturally into Agent conversations and Canvas documents.
## Get started
Open **Activity Pulse** to see what's happening across your accounts right now. Then try **Unified Search** - search for a strategic topic your business cares about and see which accounts light up. From there, explore **Accounts** and **Contacts** to manage your portfolio.
# Company Timeline
Source: https://docs.getpg.ai/workspace/timeline
A chronological feed of every meaningful event for an account or across your book of business
The **Company Timeline** is a chronological view of every meaningful event we've recorded for an account - strategic priorities, goals and risks identified by AI, hiring activity, key contact changes, public events like earnings calls and investor days, and shifts in the account's territory score - all merged into a single, paginated, time-ordered feed.
Where **Unified Search** answers "what's the most relevant thing here?", the Timeline answers "what happened, in order?". It's the right view when you want to scroll through an account's recent history, build a meeting-prep narrative, or audit when a particular signal first appeared.
![Company Timeline view in search results]()
## Scope
Each request can target:
* **A specific account** - the most common use case, powering the timeline tab on a company page.
* **The current user's tracked accounts** - a personal "everything happening across my book" feed.
* **The entire organisation's accounts** - a manager- or org-wide view of activity across the full portfolio.
Only one of the three may be active per request. When a single account is requested, the Timeline includes events sourced specifically for that account; the broader scopes merge events across multiple accounts into one chronological stream.
## Filters
* **Date range** - `from_date` and `to_date` constrain the window. Defaults to the last 12 months.
* **Event kinds** - narrow the stream to specific event types (e.g. only public events and contact joiners). Omit to include everything.
* **Sort** - ascending (oldest first) or descending (newest first). Descending is the default.
* **Pagination** - `page` and `per_page` (default 50). Real pagination, not just truncation, so the Timeline supports infinite scroll on the front end.
## Event types surfaced
The Timeline is the consolidated feed for everything we know about an account's activity, including:
* **Strategic priorities, goals, risks, and digital strategies** - AI-generated insights linked to the account.
* **Public events** - earnings calls, investor days, AGMs, conferences, M\&A announcements, and other corporate-calendar items.
* **Job postings** - net-new roles posted by the company, with title, location, and posting date.
* **Contact changes** - when a tracked contact joins or leaves a role at the company.
* **Score updates** - when the account's territory or relevance score moves materially.
Each event carries the company it belongs to, the canonical event date, a display title and description, and, where relevant, source links and supporting metadata so the front end can render rich cards without further lookups.
## Performance characteristics
The Timeline reads directly from our Postgres entity tables - no vector search, no third-party API calls, no MongoDB round trip. Typical response time is about 100–300 ms for a single account over a 12-month window, scaling roughly linearly with the number of accounts in scope. It is the cheapest and fastest way to retrieve account activity in the platform, and it is fully cacheable downstream.
## Relationship to Unified Search and Activity Pulse
Three views, one underlying event model:
* **Activity Pulse** - the at-a-glance view across your book of business, optimised for spotting which accounts and signals need attention right now.
* **Unified Search** - the relevance-ranked, answer-first, query-driven view.
* **Company Timeline** - the chronological feed: narrative-first, scroll-driven.
All three speak the same canonical event vocabulary, so a user can move between them without losing context: see activity on the Pulse, drill into the **Company Timeline** to see what happened in order, then jump to **Unified Search** to find related material across the rest of the portfolio.
## Related features
Query-driven, relevance-ranked search across all intelligence. Complements the Timeline's time-ordered feed.
Portfolio-level view of what's happening now. Pairs with Timeline when you need chronology for a specific account.
# Unified Search
Source: https://docs.getpg.ai/workspace/unified-search
One search box for every piece of intelligence across all your accounts
Unified Search is the single front door to every piece of intelligence PG:AI holds on your accounts - insights, contacts, jobs, public events, news mentions, web pages, technologies, internal documents, and conversations - all queryable from one search box.
Instead of remembering which tab or system holds what, Unified Search understands the meaning of your query and ranks results by how relevant they are to what you actually asked.
![Unified Search results]()
The same Unified Search engine powers single-company timelines, dashboards, and the global search bar. One search experience, consistent everywhere in PG:AI.
## How it works
Type a natural-language query - "cloud migration strategy", "companies investing in data engineering", "recent leadership changes" - and Unified Search returns results from across every account in your portfolio, ranked by relevance.
A search for "cloud migration strategy" might return:
* The digital strategy a CTO articulated on the latest earnings call
* A new hire who just joined to lead the cloud migration project
* A news mention about the initiative that broke this morning
* The relevant technology in their stack
* An internal document you uploaded about the opportunity
All in one ranked list, strongest signals at the top.
## Search scopes
Unified Search works at three levels:
Search within one company's intelligence. Find specific insights, contacts, or events for the account you're focused on.
Search across all accounts you're tracking. See which of your accounts have the strongest signals for a given topic.
Search across every account in your organisation's PG:AI workspace. Discover accounts outside your book that other team members are tracking.
## Filters
Refine results without losing context:
**By type** - narrow to specific intelligence types: strategic priorities, goals, SWOT items, contacts, jobs, public events (earnings calls, investor days), news mentions, web pages, technologies, public filings, org documents, company documents, conversations, or content.
**By date range** - last day, last week, last month, last quarter, last year, or a custom range. Useful for "what's changed recently" queries.
**By account** - focus on specific companies or expand to the full portfolio.
Every result carries a relevance score so you can immediately see what's worth your attention.
## Three views
The same search results can be displayed in three different ways, depending on what you need:
**Chronological feed.** Results ordered by date, most recent first. Best for answering "what's changed recently?" or "what happened this quarter?"
Each entry shows the intelligence type, the account it belongs to, a relevance score, and a preview of the content. Click to expand the full record in a sidebar.
**Grouped by account.** Results clustered by company, with the strongest signals surfaced for each. Best for answering "which accounts should I focus on for this topic?"
Expand any company to see all matching results. Compare signal strength across your portfolio at a glance.
**Visual network.** A graph showing how accounts connect to your search criteria. Nodes are companies and topics, edges show connections. Best for answering "how does everything connect?" and discovering non-obvious relationships.
Useful for finding accounts you didn't know were relevant to a topic. The graph reveals clusters and patterns that a flat list can't.
## Drilling into results
Click any result to open a sidebar showing:
* The full record with all content
* Source attribution - where PG:AI found this information
* Related items - other intelligence connected to this result
* A link to the full account page for deeper exploration
![Unified Search result with job detail in the sidebar]()
## How to use it
**Morning routine:** Search for your key strategic topics to see what's new across your accounts. Check if anything changed overnight.
**Meeting prep:** Search the account name plus a topic - "Barclays AI strategy" - to pull everything PG:AI knows into one view before your call.
**Territory discovery:** Search a broad topic - "digital transformation in financial services" - across the full organisation to find accounts you should be paying attention to.
**Competitive research:** Search competitor names to see which of your accounts are mentioning them in earnings calls, news, or job postings.
**Cross-account patterns:** Search a technology or initiative to see adoption trends across your portfolio. "Kubernetes adoption" shows which accounts are hiring for it, mentioning it in strategy documents, or adding it to their stack.
## Related features
Activity Pulse shows what's happening across your portfolio at a glance. Use it alongside Unified Search for a complete cross-account view.
Every search result links to full account intelligence. Drill down from a search hit to the complete picture.
Found something interesting in search? Jump to the Agent to ask questions, create documents, or trigger workflows based on what you found.