> 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/starter-prompts/run-an-approved-experiment.md).

# Run an approved experiment

Execute a reviewed set of cases against a selected published version.

## Prompt

> Use dataset \[name] and published project version \[number] for \[project name]. Find compatible evaluators and use \[evaluator names]. Create an experiment, then generate and score with those evaluator IDs explicitly supplied. Run each job once and check the returned job ID until it completes, fails or is cancelled. Inspect every result page and report failures, quality scores and representative examples. Do not publish workflow changes or create a production monitor.

Uses evaluation list/get tools, `evals_experiments_create`, `evals_experiments_run`, `evals_experiments_status`, `evals_experiments_get`. Generation can execute workflow integrations; use this after reviewing the workflow’s effects and cost.

## Check the result

Completed job status, scores, failed cases, and representative output examples. If the assistant cannot complete the task, ask for the missing access, connection, or input rather than accepting a guessed result.

## Tool reference

* [evals\_experiments\_get](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-get.md)
* [evals\_experiments\_create](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-create.md)
* [evals\_experiments\_run](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-run.md)
* [evals\_experiments\_status](https://docs.stackai.com/stackai-mcp/tool-reference/evaluations-and-monitoring/evals-experiments-status.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/starter-prompts/run-an-approved-experiment.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.
