Get Evaluation Run

Database selection

Use an evaluation-capable database registered with AgentOS or its components. The example API server registers SQLite through its agent. When several database IDs are available, supply db_id; selecting table also requires db_id. These values select registered storage, not an arbitrary database connection. Authentication and configured user scoping apply to the stored evaluation records.

Use the ID returned by evaluation execution or listing. The response describes a stored evaluation; reading it does not execute the component again.

GET/eval-runs/{eval_run_id}

Retrieve detailed results and metrics for a specific evaluation run.

Authorization

HTTPBearer
AuthorizationBearer <token>

In: header

Path Parameters

eval_run_id*Eval Run Id

Query Parameters

db_id?|

The ID of the database to use

table?|

Table to query eval run from

Response Body

application/json

application/json

application/json

application/json

application/json

application/json

curl --request GET 'https://example.com/eval-runs/string'
{  "id": "a03fa2f4-900d-482d-afe0-470d4cd8d1f4",  "agent_id": "basic-agent",  "model_id": "gpt-4o",  "model_provider": "OpenAI",  "name": "Test ",  "eval_type": "reliability",  "eval_data": {    "eval_status": "PASSED",    "failed_tool_calls": [],    "passed_tool_calls": [      "multiply"    ]  },  "eval_input": {    "expected_tool_calls": [      "multiply"    ]  },  "created_at": "2025-08-27T15:41:59Z",  "updated_at": "2025-08-27T15:41:59Z"}