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

# Evalit

> Prompt management, evaluation, and A/B testing for LLM apps

# Build better prompts, faster

Evalit is a lightweight Python toolkit to:

* Manage versioned prompts with an easy local store
* Run A/B tests between prompt variants
* Evaluate performance beyond simple win rates

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Install, run an experiment, and find the winning prompt.
  </Card>

  <Card title="Python SDK" icon="python" href="/sdk/python/overview">
    Explore the PromptManager, Experiment, and Evaluator APIs.
  </Card>
</CardGroup>

## What’s inside

<Columns cols={2}>
  <Card title="Prompt management" icon="list-check" href="/sdk/python/prompt-manager">
    Create, version, and activate prompts.
  </Card>

  <Card title="A/B testing" icon="chart-simple" href="/sdk/python/experiment">
    Compare variants with a controlled budget.
  </Card>

  <Card title="Evaluation model" icon="magnifying-glass-chart" href="/sdk/python/evaluator">
    IRT-inspired scoring using logistic regression.
  </Card>
</Columns>