> ## Documentation Index
> Fetch the complete documentation index at: https://docs.transluce.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Primitives for evaluating AI model behavior.

**behaviors** is a Python library for building AI evaluations. It provides model adapters,
multi-turn conversations, user and tool policies, and structured conversation records.
Use it to sample a model, simulate an interaction, or ask a model to judge another model's
output.

You control the messages, tools, and stopping conditions of an interaction. behaviors handles
the conversation loop and provides configurable retries and failure recording.

behaviors works with [fxtr](/fxtr): conversation records can be stored as fxtr entities,
returned from steps, and inspected in the experiment viewer. fxtr manages the experiment's
execution, caching, and provenance.

<Columns cols={2}>
  <Card title="Calling language models" icon="comments" href="/behaviors/guides/language-models">
    Set up behaviors, run conversations, and judge their outputs in fxtr steps.
  </Card>

  <Card title="Install fxtr" icon="download" href="/fxtr/installation">
    Set up the project that runs and stores your experiments.
  </Card>
</Columns>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.