Project data modelsTest Runs

Submit Test Case Result

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.

Path parameters

testCaseIdstringRequired

The test case id Confident AI sent to your AI connection as confident.testCaseId when it dispatched this golden.

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Request

actualOutputstringOptional
The actual output produced by your agent.
retrievalContextlist of stringsOptional
The retrieval context your agent used, if any.
toolsCalledlist of objectsOptional
The tools your agent called while producing the output.
expectedToolslist of objectsOptional
The tools you expected to be called for this test case.
metadatamap from strings to anyOptional
Optional additional metadata to attach to the test case.

Response

The result was accepted for evaluation.
successboolean
A boolean indicating the success or failure of the API call.
dataobject
The recorded test case id and its status.

Errors

400
Bad Request Error
404
Not Found Error
409
Conflict Error
410
Gone Error