> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getpg.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# 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.

{/* IMAGE PLACEHOLDER: Screenshot of Scenarios & Recommendations main view */}

## Key Capabilities

<CardGroup cols={2}>
  <Card title="Scenario Management" icon="code-branch">
    Create what-if scenarios from any live territory. Override account assignments, add or remove accounts, and review summaries showing changes vs. the base territory.
  </Card>

  <Card title="AI Recommendations" icon="robot">
    Generate AI-powered recommendations based on scores, capacity, and geography. Accept or decline individually or in bulk. Track recommendation acceptance rates and outcomes.
  </Card>

  <Card title="Planning Tools" icon="compass-drafting">
    Calculate geographic proximity between reps and accounts. Model different rep allocations and capacity constraints. Apply scenario changes back to live territories when ready.
  </Card>
</CardGroup>

## 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

<Steps>
  <Step title="Open Scenarios">
    Navigate to the Scenarios section for your territory.
  </Step>

  <Step title="Select a parameter to change">
    Choose what to adjust  -  scoring model, weights, account list, segmentation criteria.
  </Step>

  <Step title="Apply as a scenario">
    Apply the change as a scenario (not permanently).
  </Step>

  <Step title="Review projected impact">
    How do scores shift? Which accounts move up or down? Does the High/Medium/Low distribution improve?
  </Step>

  <Step title="Decide">
    If the scenario looks good, apply it permanently. If not, discard and try another.
  </Step>
</Steps>

### Reviewing AI Recommendations

<Steps>
  <Step title="Open Recommendations">
    Navigate to the Recommendations section.
  </Step>

  <Step title="Review AI suggestions">
    PG:AI analyses your territory and suggests improvements based on data patterns.
  </Step>

  <Step title="Understand recommendation types">
    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
  </Step>

  <Step title="Act on each recommendation">
    Accept, reject, or investigate further.
  </Step>
</Steps>

### Comparing Scenarios Side-by-Side

<Steps>
  <Step title="Create Scenario A">
    Apply one set of changes.
  </Step>

  <Step title="Create Scenario B">
    Apply a different set of changes.
  </Step>

  <Step title="Compare key metrics">
    Compare average score, score distribution, number of High accounts, coverage gaps.
  </Step>

  <Step title="Choose the best approach">
    Select the scenario that best aligns with your goals.
  </Step>
</Steps>

### Pre-QBR Territory Optimisation

<Steps>
  <Step title="Run a scenario">
    Create a scenario with your current scoring model.
  </Step>

  <Step title="Check recommendations">
    Review AI recommendations  -  are there obvious improvements?
  </Step>

  <Step title="Apply improvements">
    Accept any recommendations that make sense.
  </Step>

  <Step title="Present with confidence">
    Present the optimised territory with data backing your decisions.
  </Step>
</Steps>

## 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    |

<Warning>Always check the reasoning behind a recommendation. Understanding **why** PG:AI made the suggestion is more valuable than just following it.</Warning>

## Tips and Best Practices

<Tip>**Use scenarios before major changes**  -  before restructuring territories or changing scoring models, run a scenario first to see the projected impact.</Tip>

<Note>**Don't accept all recommendations blindly**  -  AI sees patterns in data; you have context it doesn't (relationship history, pending deals, strategic accounts).</Note>

* **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

<CardGroup cols={3}>
  <Card title="Scoring Models" icon="chart-simple" href="/territory/scoring-models">
    Scoring model outputs are a primary input to AI recommendations.
  </Card>

  <Card title="Territory Management" icon="layer-group" href="/territory/territory-management">
    Scenarios are built from and save back to live territories.
  </Card>

  <Card title="Territory Analytics" icon="chart-pie" href="/territory/territory-analytics">
    Scenario outcomes can be compared using analytics.
  </Card>

  <Card title="Strategic Insights Scoring" icon="lightbulb" href="/territory/strategic-insights-scoring">
    Insight scores feed the recommendations engine.
  </Card>
</CardGroup>