Skip to main content
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

​
When to use workflows vs. the Agent

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

1

Pull account data

Pull strategic priorities and recent news (tool call)
2

Identify attendees

Identify meeting attendees from contacts (tool call)
3

Generate talking points

Generate talking points aligned to company goals (LLM generation)
4

Draft discovery questions

Draft discovery questions based on account context (LLM generation)
5

Produce meeting brief

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

1

Check for changes

For each account in segment: check for Intelligence changes since last review (tool call)
2

Flag accounts

Flag accounts with significant changes (conditional)
3

Generate summaries

Generate a change summary for flagged accounts (LLM generation)
4

Compile report

Compile a territory health report (LLM generation)
Output: A territory-level report highlighting which accounts need attention and why.

​
Account research and engagement plan

1

Run Intelligence review

Run comprehensive Intelligence review (tool call)
2

Identify competitive landscape

Identify competitive landscape (tool call + LLM generation)
3

Map stakeholders

Map stakeholders and recommend contacts (LLM generation)
4

Generate value alignment

Generate value alignment analysis (LLM generation)
5

Draft engagement plan

Draft engagement plan with recommended sequence (LLM generation)
6

Generate outreach emails

Generate 3 personalised outreach emails (LLM generation)
Output: A complete engagement package per account.

​
Tips for effective workflows

1

Start with pre-built workflows

Run them as-is to understand the pattern, then customise.
2

Use context recipes

Don’t reinvent how Intelligence data is gathered for each workflow. Recipes standardise this.
3

Test on a small sample first

Before running a workflow across 200 accounts, validate the output on 3–5 accounts.
4

Review output quality

Workflows produce consistent output, but consistency doesn’t guarantee quality. Review and iterate.
5

Chain workflows

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.

Agent

Use the agent for one-off research and exploration before building repeatable workflows.

Canvas

Workflows can generate Canvas documents as output for individual accounts.

StudioMail

Include email context in workflow steps for more personalised content generation.