> 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/guides-and-quickstarts/evaluations-and-observability.md).

# Evaluations and Observability

Analytics explains how workflows run. Evaluations assess whether their results meet defined requirements. Use both to understand application behavior.

Use project and organization analytics to inspect activity, errors, and model usage. Open individual run details to follow inputs and outputs through the workflow.

Datasets provide inputs and reference outputs. Evaluators score results. Experiments compare results under selected conditions, while monitors assess production activity. Successful execution and a satisfactory answer are separate outcomes.

To investigate an incident, start with [Inspect project analytics](/guides-and-quickstarts/evaluations-and-observability/inspect-project-analytics.md) and [Debug a recorded run](/guides-and-quickstarts/evaluations-and-observability/debug-a-recorded-run.md). To decide whether a change is good enough to release, create a dataset, configure an evaluator, then run an experiment. After release, use production monitors to follow ongoing quality and route alerts to an owner.

### Guides in this section

* [Inspect project analytics](/guides-and-quickstarts/evaluations-and-observability/inspect-project-analytics.md)
* [Debug a recorded run](/guides-and-quickstarts/evaluations-and-observability/debug-a-recorded-run.md)
* [Organization analytics](/guides-and-quickstarts/evaluations-and-observability/organization-analytics.md)
* [Model usage analytics](/guides-and-quickstarts/evaluations-and-observability/model-usage-analytics.md)
* [Create an evaluation dataset](/guides-and-quickstarts/evaluations-and-observability/create-an-evaluation-dataset.md)
* [Configure an evaluator](/guides-and-quickstarts/evaluations-and-observability/configure-an-evaluator.md)
* [Run and inspect an experiment](/guides-and-quickstarts/evaluations-and-observability/run-and-inspect-an-experiment.md)
* [Production quality monitors](/guides-and-quickstarts/evaluations-and-observability/production-quality-monitors.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/guides-and-quickstarts/evaluations-and-observability.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.