Skip to main content
Use this pattern when a platform lead, AI architect, or transformation owner needs a broad scan of the process tree. Independent process reads can run in parallel, but the scan still needs a bounded scope, evidence threshold, and stopping condition.

​
Example prompts

  • “Find the automation opportunities with the strongest evidence and expected impact in our procure-to-pay value stream.”
  • “Where in our close cycle should we focus next?”
  • “Scan our org for duplicate invoice processing across geographies.”

​
End-to-end recipe

1

Confirm the workspace

Call list_accessible_workspaces. If the wrong workspace is active, reconnect with OAuth or use an API key created in the intended workspace before continuing.
2

Build the work queue

Call get_process_hierarchy — the whole tree, or filtered to the value stream of interest. The leaves become your work queue.
3

Fan out in parallel across leaves

For each leaf:
  • get_process_details — current version, steps, dependencies, and relevant attributes.
  • get_process_observations — a bounded set of captured runs in summary mode. Record the returned count without treating it as total process volume.
The MCP is stateless per call, so independent reads can run in parallel. Cap each batch so the scan stays within the routine’s time and output budget.
4

Find material patterns in the index

Call search directly on the index with pattern queries: “manual approval”, “duplicate entry”, “data re-keying”, “exception handling”, “swivel-chair workflow”. For each hit, fetch the process to confirm the pattern appears in the process itself rather than only in its name.
5

Check process attributes

Inspect the attributes field already returned by get_process_details — “automation status”, “system of record”, “control level”, or similar attributes that help rank candidates.
6

Confirm each top candidate

For each top candidate:
  • get_process_observations with verbosity="summary" — identify representative runs and competing evidence.
  • get_observation_citation at low or medium verbosity — inspect one activity block at a time for the material behavioral claims the brief will make.
  • Read the dependencies field already returned by get_process_details for a first cut at blast radius.
7

Synthesize a ranked candidate set

Include process identifiers, the bounded observation count, dependency depth, pattern signal, counterevidence, uncertainty, and the next validation step.

​
Sample output

The candidate set below is synthetic. Its identifiers and counts show the shape of a useful result, not customer data. The first candidate ranks highest because the repeated pattern has the broadest downstream reach. The evidence does not yet prove that an agent is the right answer. The next step is to inspect representative activity timelines, confirm the required system access, and compare a skill, a deterministic flow, and a process change.

​
What to surface in the brief

  • A ranked list of candidate processes
  • For each: bounded observation count, dependency depth, pattern signal, and counterevidence
  • Citable process resource keys and observation resource keys or timestamps
  • Gaps where the workspace doesn’t have enough evidence yet