Run Agent
Run an agent.
Use wait=true to block until the workflow completes (201 Created). Default (wait=false) returns immediately with 202 Accepted.
Path parameters
Query parameters
Headers
Bearer authentication
Request body
Agent IDs to execute. Resolved to agent names server-side.
Terminology domain IDs.
Caller-provided document identifier for tracking across scans.
Document URL.
Document name or title.
Style guide ID to check the document against. target_id is a deprecated alias for this field; send exactly one of the two names.
Language-service content profile ID for style checking.
Document goal for agent recommendation.
Agent configuration UUID for persona selection. Used by: persona. Retrieve valid IDs from GET /personas.
Agent configuration UUID for brand voice profile selection. Used by: brand_voice. Retrieve valid IDs from GET /brand-voice-profiles.
Optional webhook URL for async result delivery.
Document text to analyze.
Response
Successful Response
Workflow ID for tracking
Request tracking ID
Status of a workflow execution.
Caller-provided document identifier.
How a content check should be counted.
The type fixes two things about a result: its priority (is someone waiting?) and its attribution (does it count as authoring activity for a person?).
- INTERACTIVE: a writer checking content as they work — high priority, assigned.
- AUTOMATED: a save/update check credited to the last editor — assigned.
- BATCH: a bulk check of content you own — assigned to the content's author.
- BASELINE: a check of content you do NOT own — a measurement, not authoring, so it is not assigned to anyone.
Whether the check counts as authoring activity for an author.
Owning batch id (agbw_<nanoid>); null unless this is a batch check.
Execution result (if completed)
Workflow start time
Workflow completion time
Execution duration