Get Agent Test Run
Retrieve a single test run by ID. Poll this endpoint until
status reaches a terminal state (passed, failed, or error).
The result field is populated on terminal states.
Authentication
AuthorizationBearer
Enter your API key with the Bearer prefix, e.g. ‘Bearer sk_…’.
Path parameters
id
Response
The test run.
id
Prefixed wire identifier (run_<26 char Crockford base32>).
URL paths accept only this
prefixed form; legacy UUID path parameters are rejected with
404.
test_id
Prefixed wire identifier (test_<26 char Crockford base32>)
of the parent test.
agent_id
Prefixed wire identifier (agent_<26 char Crockford base32>)
of the agent this run executed against.
status
Lifecycle of a test run: queued - running - terminal.
Terminal states:
passed- the agent behaviour met the success criteria.failed- the agent behaviour did not meet the success criteria.error- the runner itself could not complete (LLM outage, network error, etc.), distinct fromfailedwhich means the agent behaviour was judged and found lacking.
created_at
started_at
completed_at
result
Populated on terminal status only.
error
Human-readable error message when status is error.
Errors
401
Unauthorized Error
404
Not Found Error