COconfident-ai
Evaluation

Submit Test Case Result

Changed on

Submit the result for a single test case in a long-running agent evaluation. Confident AI automatically evaluates the test case and finalizes the test run once every result has been received.

Long-running mode is available for single-turn AI connection evaluations only.

post/v1/test-runs/evaluate/{testCaseId}

Request

Request body

actualOutputstring

The actual output produced by your agent.

retrievalContextstring[]

The retrieval context your agent used, if any.

metadataobject

Optional additional metadata to attach to the test case.

Response

The result was accepted for evaluation.

successboolean required

A boolean indicating the success or failure of the API call.

Changes