curl -X POST https://api.60db.ai/agents/AGENT_ID/evals/task_success/golden \
-H "Authorization: Bearer your-api-key"
Agent Reliability
Run Golden Eval
Measure how closely a Judge eval agrees with its golden answers
POST
/
agents
/
{agentId}
/
evals
/
{name}
/
golden
curl -X POST https://api.60db.ai/agents/AGENT_ID/evals/task_success/golden \
-H "Authorization: Bearer your-api-key"
AI Simulation needs an active Pro or Business plan. On another plan, every simulation endpoint returns
403 POLICY_DENY.Request
Headers
Path
Response
200 OK.{ "run_id": "g_1", "eval": "task_success", "agreed": 18, "examples": 20, "false_passes": 1, "false_fails": 1, "complete": true, "unreliable": false, "model": "…" }
examples the result says nothing. unreliable: true means the Judge disagrees with the golden answers too often.
Errors
| Status | Code | Meaning |
|---|---|---|
| 402 | INSUFFICIENT_CREDITS | The balance is too low to start |
| 403 | POLICY_DENY | Your role cannot run simulations, the workspace is not on an active Pro or Business plan, or the API key lacks the agents scope |
| 404 | AGENT_NOT_FOUND | No agent with this ID in your workspace |
| 429 | RATE_LIMITED | More than 3 starts a minute |
Example
curl -X POST https://api.60db.ai/agents/AGENT_ID/evals/task_success/golden \
-H "Authorization: Bearer your-api-key"