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

# Get started with Braintrust

Braintrust is the active observability platform for instrumenting, understanding, and improving agents. By actively applying intelligence to agent traces and automatically surfacing the most critical patterns, Braintrust gives teams the visibility to understand how agents behave in production and the tools to improve them.

To get started, [create a Braintrust account](https://www.braintrust.dev/signup).

## Quickstarts

<CardGroup cols={3}>
  <Card title="Log your first trace" icon="activity" href="/docs/tracing-quickstart">
    Send traces from your AI application to Braintrust
  </Card>

  <Card title="Run your first eval" icon="beaker" href="/docs/evaluation-quickstart">
    Compare prompts and models to improve AI quality
  </Card>

  <Card title="Discover Patterns" icon="scan-search" href="/docs/observe/patterns/enable">
    Find recurring trace problems and suggested fixes
  </Card>

  <Card title="Investigate with Loop" icon="blend" href="/docs/loop">
    Ask Braintrust's AI agent to analyze data and build evals
  </Card>

  <Card title="Connect with MCP" icon="plug" href="/docs/integrations/developer-tools/mcp">
    Connect your AI tools to Braintrust data and actions
  </Card>

  <Card title="Get started with the CLI" icon="terminal" href="/docs/reference/cli/quickstart">
    Instrument apps and run evals with the `bt` CLI
  </Card>
</CardGroup>

## Workflow

Follow Braintrust's structured [workflow](/docs/workflow) to build, evaluate, and improve AI applications:

<CardGroup cols={2}>
  <Card title="Instrument" icon="code" href="/docs/instrument">
    Capture traces from your AI application
  </Card>

  <Card title="Observe" icon="activity" href="/docs/observe">
    Analyze logs and identify patterns
  </Card>

  <Card title="Annotate" icon="list-checks" href="/docs/annotate">
    Add human feedback and build datasets
  </Card>

  <Card title="Evaluate" icon="beaker" href="/docs/evaluate">
    Test changes with experiments
  </Card>

  <Card title="Deploy" icon="rocket" href="/docs/deploy">
    Ship changes and monitor production
  </Card>

  <Card title="Admin" icon="shield" href="/docs/admin">
    Manage organizations, projects, and access control
  </Card>
</CardGroup>


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