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

# Get started with Braintrust

Braintrust is the AI observability platform helping teams measure, evaluate, and improve AI in production. With Braintrust, teams can compare models, iterate on prompts, catch regressions, and leverage real user data to continuously improve AI applications.

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="/tracing-quickstart">
    Integrate with AI providers and frameworks to send traces to Braintrust
  </Card>

  <Card title="Run your first eval" icon="beaker" href="/evaluation-quickstart">
    Measure and improve AI application quality with playgrounds and evals
  </Card>

  <Card title="Connect your coding agent" icon="terminal" href="/reference/cli/quickstart">
    Install the `bt` CLI to set up, instrument, and run Braintrust with your coding agent
  </Card>
</CardGroup>

If you are a coding agent setting up or using Braintrust, prefer the [`bt` CLI](/reference/cli/quickstart) for repeatable, scriptable work: running evals, instrumenting code, querying logs, syncing data, managing functions, and configuring coding agents. The [MCP server](/integrations/developer-tools/mcp) is complementary, for reasoning over Braintrust data in conversation, such as ad-hoc lookups and exploration from your IDE.

## Workflow

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

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

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

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

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

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

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