# Start automated task running

Manually start an enabled scheduled automation task and create a run record.

```text
POST https://moi.matrixorigin.cn/newmoi/workspaces/{workspace_id}/agent-automation-tasks/{automation_task_id}/runs
```

## Preparation before calling

First [Query automation task details](get-task.md)Confirm that the task is enabled and obtain the task ID. Prepare a personal access token and target workspace ID that has access to the target workspace.

The example below uses:

- `$AI_STUDIO_API_KEY`: The actual personal access token, passed through the `X-API-Key` Header.
- `$WORKSPACE_ID`: Target workspace ID, passed through the `X-Workspace-ID` Header and also as `workspace_id` in the path.
- `$TASK_ID`: The automation task ID to start, as `automation_task_id` in the path.

## Request example

```bash
curl -X POST "https://moi.matrixorigin.cn/newmoi/workspaces/$WORKSPACE_ID/agent-automation-tasks/$TASK_ID/runs" \
  -H "X-API-Key: $AI_STUDIO_API_KEY" \
  -H "X-Workspace-ID: $WORKSPACE_ID" \
  -H 'Content-Type: application/json' \
  -d '{
    "payload": {
      "date": "2026-08-18"
    }
  }'
```

## Path parameters

| Parameters | Type | Is it required | Description |
| --- | --- | --- | --- |
| `workspace_id` | string | Yes | Workspace ID. |
| `automation_task_id` | string | Yes | Automation task ID. |

## Request body

| Parameters | Type | Is it required | Description |
| --- | --- | --- | --- |
| `payload` | object | No | Input data for this run. |
| `trigger_context` | object | No | Additional context for this trigger. |

## Successful response

Returns `201` on success. The fact that the request has been submitted does not mean that the agent has completed execution; please continue to query the running details or results.

```json
{
  "code": 0,
  "data": {
    "id": "run_01",
    "workspace_id": "ws_01",
    "automation_task_id": "task_01",
    "automation_task_version": 1,
    "trigger_type": "manual",
    "trigger_config_snapshot": {
      "mode": "cron"
    },
    "status": "queued",
    "created_at": "2026-08-18T04:00:00Z",
    "updated_at": "2026-08-18T04:00:00Z"
  }
}
```

The response fields are as follows.

| Field | Type | Description |
| --- | --- | --- |
| `code` | integer | `0` on success. |
| `data.id` | string | New run, workspace, and automation task identifiers. |
| `data.workspace_id` | string | New run, workspace, and automation task identifiers. |
| `data.automation_task_id` | string | New run, workspace, and automation task identifiers. |
| `data.automation_task_version` | integer | The task version used in this run. |
| `data.trigger_type` | string | Trigger type and configuration snapshot fixed to manual triggering. |
| `data.trigger_config_snapshot` | object | Trigger type and configuration snapshot fixed to manual triggering. |
| `data.status` | string | Initial running status; please refer to the subsequent query status. |
| `data.created_at` | string | Creation and last update times, using RFC 3339 format. |
| `data.updated_at` | string | Creation and last update times, using RFC 3339 format. |

## Error response

```json
{
  "code": 2,
  "message": "<错误信息>"
}
```

### Common HTTP errors

```{list-table}
:header-rows: 1
:widths: 12 22 32 34

* - HTTP status code
  - error code
  - Common causes
  - Recommended actions
* - `400`
  - `2`（`INVALID_ARGUMENT`）
  - The request body is invalid, the task is not a manually runnable enabled scheduled task, or the input does not meet the task constraints.
  - Check task status, triggering methods and inputs.
* - `401`
  - `6`（`UNAUTHENTICATED`）
  - Lack of valid identity credentials.
  - Check API Key.
* - `403`
  - `5`（`PERMISSION_DENIED`）
  - The current identity has not been verified for workspace access and valid roles.
  - Use an identity and a valid role with access to the workspace.
* - `404`
  - `3`（`NOT_FOUND`）
  - The automated task does not exist.
  - Check the task details first.
* - `409`
  - `4`（`ALREADY_EXISTS`）
  - The task has conflicting activities running, or the task status conflicts.
  - Wait for the existing run to end or refresh the task status before trying again.
* - `503`
  - `15`（`UNAVAILABLE`）
  - Run executor, input snapshot or workflow submission services are temporarily unavailable.
  - Try again later.
```

## Follow-up operations

Log `data.id`. Running a call does not mean it is finished. Use this ID to [Query automation task running details](get-run.md) to track the status; after entering the final state, [Query the results of automated task execution](get-run-result.md).