> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-status.md).

# evals\_experiments\_status

Poll one accepted job with its experiment\_id and job\_id from evals\_experiments\_run, or omit job\_id to inspect the experiment's latest job with cumulative row counts and aggregate cards.

**Effect:** This call reads data and does not run or change a project.

## Inputs

| Name            | Type   | Requirement | Description                                                                                                                           |
| --------------- | ------ | ----------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| `experiment_id` | string | Required    | Experiment ID returned by experiment discovery or creation.                                                                           |
| `job_id`        | string | Optional    | Accepted job ID returned by `evals_experiments_run`. Omit only to inspect the latest job, not when following a specific accepted job. |

## Example

These are MCP tool arguments, not an HTTP request body. Replace bracketed IDs with values returned from your account.

```json
{
  "experiment_id": "<experiment-id>",
  "job_id": "<job-id>"
}
```

## Result

Abbreviated result example; unshown fields are omitted for clarity.

```json
{
  "experiment_id": "<experiment-id>",
  "job_id": "<job-id>",
  "job_status_available": true,
  "status": "completed",
  "error": null
}
```

## Behavior

Returns that job's lifecycle, final error and next\_action.

No job returns status=null.

Unavailable job health returns job\_status\_available=false and status=null, or a 503 for exact-job reads: retry the status read, do not start another experiment job.

Poll only queued/running states, keeping both IDs unchanged for exact-job polling. completed, completed\_with\_failures, failed and cancelled are terminal; inspect errors and all row pages before another job.

Row counts never establish job completion.

## Troubleshooting

If `job_status_available=false`, `status=null`, or an exact-job read returns 503, retry the status read for the same IDs. Do not infer completion from row counts.

## Related resources

[Evaluations and monitoring](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring.md)

[Evaluate a project before rollout](https://docs.stackai.com/stackai-mcp/workflow-recipes/evaluate-a-project-before-rollout.md)

[Connection, permissions, pagination, and recovery](https://docs.stackai.com/stackai-mcp/best-practices-and-troubleshooting.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-status.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
