Tools

get_test_runs

Retrieves test run results for an AI Agent. Use this to review pass/fail status, evaluation criteria outcomes, and rationale after triggering a test_run via propose_change.

Example prompts

  • “Show me the latest test run results for each of my test cases.”
  • “Which test cases failed in the last run, and why?”
  • “Get the full details for test run abc123.”

Parameters

ParameterTypeDescription
test_run_idstringOptional. Return full details for a single test run.
status_filterstringOptional. Limit to runs with a specific status (for example, passed, failed).
test_case_idsarrayOptional. Restrict results to runs for specific test case IDs.
latest_per_test_casebooleanOptional. When true, returns only the most recent run per test case.
cursorstringOptional. Pagination cursor for historical run listings.

Response

Returns per-run results including:

  • Test run ID and test case ID.
  • Overall pass/fail status.
  • Per-evaluation-criterion outcomes and rationale.
  • The simulated conversation transcript the evaluation was based on.
  • Timestamps and the user who triggered the run.