Skip to main content
A process performer — an AP lead, ops manager, recruiter, analyst — asks their assistant to do real work: vendor reconciliation, invoice approval, candidate screening, ERP migration prep, audit walkthrough. The assistant should pull the customer’s existing process before improvising.

​
Example prompts

  • “Walk me through how to reconcile this batch of vendor invoices.”
  • “Help me prep for tomorrow’s SOX walkthrough.”
  • “I’m onboarding a new vendor — what’s our checklist?”

​
End-to-end recipe

1

Confirm the workspace

Call list_accessible_workspaces to confirm the active workspace. If the user names a different one, they’ll need to switch workspaces — the assistant can’t change it mid-session.
2

Search for the process

Call search with the task in the user’s words (“vendor invoice reconciliation”). Iterate two to four times with refined queries — single queries rarely cover broad topics.If results are still sparse, call get_process_hierarchy to orient on the right value stream, then drill in.
3

Fetch the matched process

Use fetch to read steps, policies, inputs, outputs, and dependencies. If you need the richer nested payload (full version metadata or every dependency ID), call get_process_details directly.
4

Pull recent observations

Call get_process_observations to find emerging edge cases and exception patterns. Default verbosity="summary" is the scan; bump to "full" when you want the rich payload inline.
5

Drill into the most relevant session

Call get_observation_citation to read the exact user actions behind a deviation. This is the most “primary source” evidence the workspace has.
6

Check boundaries (optional)

If the task touches another team or system, read the dependencies field already returned by get_process_details. To go deeper on a handoff, fetch the referenced upstream or downstream process and read its steps and observations the same way.
7

Synthesize

“Here’s how your team does this. Here’s the deviation pattern from last quarter. Here’s what to watch for.”

​
Catch duplication

If the user suspects a different team already does this work, run search again with broader queries — task name, system, business outcome — across the whole workspace. If results look similar to the current process, fetch each candidate and compare steps and observations side by side. Surface the duplicate set with process IDs.