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

# Introduction

> What Maitai is, and the fastest way to get value

Maitai is a platform for **building, testing, and observing** LLM-powered applications. Route your
LLM requests through Maitai (recommended), or keep your own client and send Maitai the
request/response. Either way, Maitai organizes every call by **Application** and **Intent**, runs
**Sentinels** to catch quality problems, and gives you the tooling to fine-tune models and ship
changes with confidence.

## Get started in minutes

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/get_started/quickstart">
    Install the CLI, log in, and prompt your coding agent to wire Maitai in.
  </Card>

  <Card title="Base URL integration" icon="plug" href="/get_started/base_url">
    Already on an OpenAI-compatible SDK? Point it at Maitai in one line.
  </Card>

  <Card title="Core Concepts" icon="sitemap" href="/get_started/core_concepts">
    The mental model: Company > Application > Intent, plus Sessions and Sentinels.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Prefer raw REST? Every resource, documented.
  </Card>
</CardGroup>

## Navigate by what you want to achieve

Everything in Maitai maps to one of three goals. Start wherever your problem is, you can always
move to the next pillar as your needs grow.

<CardGroup cols={3}>
  <Card title="Build" icon="wrench" href="/build/overview">
    Improve the model and orchestrate work with fine-tunes, agents, and workflows.
  </Card>

  <Card title="Test" icon="vial" href="/test/overview">
    Catch quality problems and prevent regressions with test sets, runs, and criteria.
  </Card>

  <Card title="Observe" icon="chart-line" href="/observe/overview">
    See what your traffic is doing across applications, intents, sessions, and single requests.
  </Card>
</CardGroup>

Start wherever your problem is; you don't have to go in order. Many teams **observe** production
traffic first, then **test** it for quality, then **build** fine-tunes and agents on top. Others
come to Maitai specifically to build. For complete, end-to-end recipes, see the
[Examples](/examples/quality_loop).