> For the complete documentation index, see [llms.txt](https://docs.zenml.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zenml.io/kitaru/guides.md).

# Guides

- [Complete returns agent tutorial](https://docs.zenml.io/kitaru/guides/returns-agent.md): Investigate supplied returns agent traces and test one evidence-led improvement.
- [1. Observe the recorded behavior](https://docs.zenml.io/kitaru/guides/returns-agent/observe.md): Verify the prepared returns evidence and select a bounded worklist for human review.
- [2. Judge the selected behavior](https://docs.zenml.io/kitaru/guides/returns-agent/judge.md): Create an investigation and store human judgments against exact trace evidence.
- [3. Define one behavior to test](https://docs.zenml.io/kitaru/guides/returns-agent/define.md): Turn accepted human evidence into one frozen cohort and evaluator version.
- [4. Replay one bounded change](https://docs.zenml.io/kitaru/guides/returns-agent/replay.md): Register one investigation-derived candidate and replay the frozen cohort safely.
- [5. Compare the paired evidence](https://docs.zenml.io/kitaru/guides/returns-agent/compare.md): Compare baseline and replay evidence and state the result at the size the cohort supports.
- [Replay a failure and fork it](https://docs.zenml.io/kitaru/guides/replay-and-overrides.md): Reproduce a recorded session, fork it with an override, and compare the two, so you can debug a failure or test a change before shipping it.
- [Build a regression suite from production](https://docs.zenml.io/kitaru/guides/regression-suite.md): Freeze a cohort of recorded runs, replay it against a change, and use the results in CI.
- [Write an evaluator](https://docs.zenml.io/kitaru/guides/write-an-evaluator.md): Turn your domain expert's criteria into a versioned evaluator: code checks, LLM judges, human calibration, and backfilling your history.
- [Deterministic evaluations](https://docs.zenml.io/kitaru/guides/deterministic-evaluations.md): Run Kitaru's offline deterministic evaluators over recorded and imported sessions
- [Tool policies](https://docs.zenml.io/kitaru/guides/tool-policies.md): Choose whether replayed tool calls use recorded results, static results, live tools, or model-generated responses.
- [Track cost and model usage](https://docs.zenml.io/kitaru/guides/llm-calls.md): Every model call recorded: tokens, cost, and call counts on every session, and how to total them across cohorts and experiments.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.zenml.io/kitaru/guides.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.