> ## Documentation Index
> Fetch the complete documentation index at: https://docs.60db.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Simulation

> Read the progress and report of one simulation run

> [!NOTE]
>
> AI Simulation needs an active **Pro** or **Business** plan. On another plan, every simulation endpoint returns `403 POLICY_DENY`.

Read one run. While the state is `running` or `paused`, read it every 3 to 5 seconds. Stop when the state is `finished`, `cancelled` or `stopped_budget`. There is no event for a finished run.

Only `pass` and `fail` count for accuracy. `infra_error` and `simulator_error` are not the agent's fault.

## Request

### Headers

**Authorization** `string` *required*

Bearer token with your API key (scope `agents`)

### Path

**runId** `string` *required*

The simulation run `run_id` (UUID) from [Start a simulation](https://docs.60db.ai/api-reference/agents/start-simulation.md)

## Response

**200 OK**.

```json theme={null}
{
  "run_id": "6f1c1e2a-3333-4000-8000-000000000001",
  "state": "running",
  "agent_version": 7,
  "baseline_run_id": null,
  "draft_id": null,
  "total": 60, "done": 41, "queued": 12, "claimed": 7,
  "labels": { "pass": 30, "fail": 6, "infra_error": 2, "timed_out": 3 },
  "incomplete": false,
  "pass_rate": 0.8333,
  "scenarios": [{ "scenario": "caller-gives-account-number", "total": 5, "passed": 4, "failed": 1, "pass_rate": 0.8, "flaky": true }],
  "failure_groups": [{ "cause": "failed_check:contains", "calls": 4 }],
  "regressions": [{ "scenario": "caller-gives-account-number", "baseline": 1.0, "current": 0.6, "delta": -0.4 }],
  "draft_suggestion": { "published": false, "agent_version": 8, "instruction": "…" },
  "calls": [{ "call_id": "…", "state": "done", "label": "pass", "scenario": "…", "summary": "…" }]
}
```

| Field | Meaning |
| - | - |
| `state` | `running`, `paused`, `cancelled`, `finished` or `stopped_budget` |
| `pass_rate` | `null` until at least one call is judged. Show "Not enough data", not 0 |
| `incomplete` | `true` when `infra_error` is more than 5% of the finished calls. Do not trust `pass_rate` then |
| `labels` | `pass`, `fail`, `infra_error`, `simulator_error`, `timed_out`, `cancelled` |
| `failure_groups[].cause` | `fail`, `infra_error`, `failed_check:<name>`, `stalled_at:<step>` or `error:<text>` |
| `baseline_run_id` | The `run_id` of the baseline run, or `null` |

## Errors

| Status | Code | Meaning |
| - | - | - |
| 403 | `POLICY_DENY` | Your role cannot do this, the workspace is not on an active Pro or Business plan, or the API key lacks the `agents` scope |
| 404 | `RUN_NOT_FOUND` | No run with this ID in your workspace |
| 502 | `AGENTS_UPSTREAM_UNAVAILABLE` | The voice service did not answer. Try again |

## Example

```bash cURL theme={null}
curl https://api.60db.ai/agents/simulations/RUN_ID \
  -H "Authorization: Bearer your-api-key"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.