> ## 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.

# Observe

> See what your LLM traffic is actually doing, organized by Application and Intent, down to a single request.

**Observe** is where you watch real traffic flow through Maitai. Once you're sending requests
(see [Quickstart](/get_started/quickstart)), Maitai organizes them into a hierarchy you can browse
, **Application > Intent**: and lets you drill all the way down to one request to see exactly what
happened.

Come here when you want to answer: *"What is my app doing in production, and why did this specific
response come out the way it did?"*

## Start with the structure

Maitai groups traffic so you can navigate by product area rather than scrolling a raw log.

<CardGroup cols={3}>
  <Card title="Applications" icon="grid-2" href="/observe/resources/applications">
    The top-level container for a product or service, its traffic, intents, and config.
  </Card>

  <Card title="Intents" icon="bullseye" href="/observe/resources/intents">
    Action types within an Application (also called `action_type`).
  </Card>

  <Card title="Intent Groups" icon="layer-group" href="/observe/resources/intent_groups">
    A cross-application layer for shared monitoring, testing, and datasets.
  </Card>
</CardGroup>

## Then drill into the traffic

<CardGroup cols={2}>
  <Card title="Sessions" icon="comments" href="/observe/agent_sessions">
    Debug multi-turn behavior (including agent runs) via session timelines and task details.
  </Card>

  <Card title="Request Overview" icon="magnifying-glass" href="/observe/request_overview">
    Inspect a single request, create reruns, and compare prompt/model changes.
  </Card>
</CardGroup>

## Watch quality on live traffic

Two tools continuously judge real production traffic as it flows through Maitai:

<CardGroup cols={2}>
  <Card title="Sentinels" icon="shield-check" href="/observe/sentinels/overview">
    Intent-group-level watchers that evaluate each request and flag faults.
  </Card>

  <Card title="Monitors" icon="magnifying-glass-chart" href="/observe/monitors/overview">
    Sample live traffic, judge it against configurable rules, and store verdicts over time.
  </Card>
</CardGroup>

<Note>
  New to the Maitai object model? [Core Concepts](/get_started/core_concepts) explains
  Company > Application > Intent, plus Sessions and Intent Groups, in one page.
</Note>

## Where to go next

Once you can see a failure, the [Test](/test/overview) pillar is how you catch it before shipping,
curate a test set and prove your fix. For a guided end-to-end path, see the
[Quality Loop](/examples/quality_loop) recipe.