Linking Results To Runs

Evaluation results may include draftRunId and publishedRunId.

Those ids reference underlying skill-run records.

What to use publicly

  • the evaluation result object itself
  • diagnosticSummary
  • GET /api/skill-runs/:id when you need public beta skill-run detail
  • the stable agent runtime when you need stable persisted run-detail APIs

See also

Was this page helpful?