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

# Launch a run

> Name the agent in a prepared run and start the audit.

```http theme={null}
POST https://api.humalike.com/v1/social-observability/actions/audit_launch
```

Tell the API which speaker in a prepared run is your agent, and start the
audit. The call returns as soon as the run is accepted — the audit itself takes
minutes and runs in the background. Collect the result with
[`audit-run`](/api-reference/audit/run).

This is the call that makes a run real. Before it, the run is parked and
unbilled; after it, the audit executes whether or not you stay connected.

## Authorization

<ParamField header="Authorization" type="string" required>
  Your bearer token: `Bearer <token>`. See [Authentication](/authentication).
</ParamField>

## Request body

<ParamField body="run_id" type="string" required>
  The run to launch, from [`audit_prepare`](/api-reference/audit/prepare).
</ParamField>

<ParamField body="agent_name" type="string" required>
  Which speaker is your agent. Must be one of the `participants` returned by
  `audit_prepare`, spelled identically. 1–255 characters.
</ParamField>

## Request

```bash theme={null}
curl https://api.humalike.com/v1/social-observability/actions/audit_launch \
  -H "Authorization: Bearer $HUMALIKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "run_id": "9f8b1c04-6d2a-4f31-9c77-2b1d0e5a8c43",
    "agent_name": "support_bot"
  }'
```

## Response

```json theme={null}
{
  "run_id": "9f8b1c04-6d2a-4f31-9c77-2b1d0e5a8c43",
  "agent_name": "support_bot",
  "status": "queued"
}
```

<ResponseField name="run_id" type="string">
  The run that was launched.
</ResponseField>

<ResponseField name="agent_name" type="string">
  The agent the audit will review. On a repeat call this is the name the
  **first** launch set, which may differ from the one you just sent.
</ResponseField>

<ResponseField name="status" type="string">
  `queued` while the audit is still running, `completed` once it has finished.
  A first launch is always `queued`.
</ResponseField>

## Retrying is safe

Launching the same run twice is a no-op success, not an error. If you lose the
first response to a timeout, call again: you get `200`, the audit is not
restarted, not billed twice, and the agent is not changed underneath a review
already in progress. The `status` field tells you where the run actually got
to, so a retry after a long silence is also a way to check whether it finished.

## Errors

| Status | Code               | Cause                                                                                                                                                  |
| ------ | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `400`  | `VALIDATION_ERROR` | `agent_name` never speaks in the transcript, or the name is shared by more than one participant. The run stays prepared — fix the name and call again. |
| `400`  | `VALIDATION_ERROR` | The run does not exist, or does not belong to you.                                                                                                     |
| `401`  | `UNAUTHORIZED`     | Missing or invalid bearer token.                                                                                                                       |

A name that does not appear in the transcript is refused rather than guessed
at, so you are never billed for a review of a speaker who does not exist:

```json theme={null}
{
  "error": {
    "code": "VALIDATION_ERROR",
    "message": "agent_name must be one of the transcript's speakers",
    "details": [{ "field": "agent_name", "message": "'suport_bot' never speaks" }]
  }
}
```

Next: [Get a run](/api-reference/audit/run).