Evals

List Eval Runs

GET/v2/agents/{agent_id}/eval-runs

Verdicts (eval_runs) for an agent, newest-first. Optional ``task_id`` narrows to one thread. Same agent-ownership gate as the CRUD routes.

Path Parameters

agent_idstring · uuidrequired

Query Parameters

task_idobjectoptional

limitintegeroptional

Request

curl --request GET \
  --url https://api.brainbaselabs.com/v2/agents/{agent_id}/eval-runs \
  --header 'Authorization: Bearer YOUR_API_KEY'

Response

json

{
  "items": [
    {
      "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
      "eval_id": "b7fe92ca-3c59-4b75-8341-1d28fad399a5",
      "task_id": "736fde4d-9029-4915-8189-01353d6982cb",
      "turn_id": "2df5d97e-1e68-4315-ace5-61a464d94d93",
      "status": "string",
      "passed": true,
      "rating": 0,
      "category": "string",
      "reasoning": "string",
      "cites": [
        {}
      ],
      "judge_model": "string",
      "error": "string",
      "triggered_by": "string",
      "judge_task_id": "2d7ec96d-ffa8-4cc7-b49c-cc742d68c9d1",
      "created_at": "2019-08-24T14:15:22Z",
      "completed_at": "2019-08-24T14:15:22Z"
    }
  ]
}