> 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-run.md).

# evals\_experiments\_run

Generate outputs or score existing outputs with explicit evaluator IDs.

**Effect:** This call executes a workflow or evaluator. Review its effects and possible usage charges before calling it.

## Inputs

| Name            | Type                  | Requirement | Description                                                                                                                               |
| --------------- | --------------------- | ----------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| `experiment_id` | string                | Required    | Experiment ID returned by experiment discovery or creation.                                                                               |
| `mode`          | `generate` or `score` | Optional    | `generate` (default) produces outputs and optionally scores them. `score` reuses existing outputs and requires at least one evaluator ID. |
| `evaluator_ids` | array of strings      | Optional    | Evaluator IDs. Supply them explicitly for each run; creation-time choices are not reused automatically.                                   |

## 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>",
  "mode": "generate",
  "evaluator_ids": [
    "<evaluator-id>"
  ]
}
```

## Result

Abbreviated result example; unshown fields are omitted for clarity.

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

## Behavior

Creation-time evaluators are never implicitly reused.

Returns accepted, job\_id, status\_url and a next\_action to poll that exact job.

May execute workflow side effects or paid judges; do not retry blindly.

## Troubleshooting

Keep the accepted `job_id` and poll that job. A timeout or status-read failure is not a reason to start another job. In score mode, provide evaluators and ensure generated outputs already exist.

## Related resources

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