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

# Python SDK quickstart

> Install the Braintrust Python SDK, instrument your application, and verify that traces appear in Braintrust.

## Setup

In your project directory, run the agent-assisted (Requires Claude Code or Codex installed locally.) setup script:

```bash theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
curl -fsSL https://braintrust.dev/wizard/setup.sh | sh -s -- --from docs_python_quickstart
```

It uses your installed coding agent to install the Braintrust SDK, inspect your project, and configure tracing.

No coding agent installed? [Install and instrument manually](https://docs.braintrust.dev/sdks/python/install-and-instrument.md).

## Verify tracing

Run your app and make an AI call. A trace will show up in your [Braintrust Logs](https://www.braintrust.dev/app/~/logs), usually within seconds.

> [!TIP]
>
> If traces appear in Braintrust, you've successfully set up the SDK.

If your traces don't appear in Braintrust, see [Troubleshooting](https://docs.braintrust.dev/sdks/python/troubleshooting.md).

## Enable Patterns

Enable [** Patterns**](https://www.braintrust.dev/app/~/patterns) to have Loop find recurring problems and trends in your traces, with evidence and suggested fixes. See the [setup guide](https://docs.braintrust.dev/observe/patterns/enable.md) for details.

## Next steps

Learn more about using the SDK to observe, evaluate, and improve your AI application:

* [Instrument](https://docs.braintrust.dev/instrument.md) — trace LLM calls and application logic
* [Observe](https://docs.braintrust.dev/observe.md) — search and analyze production traces
* [Annotate](https://docs.braintrust.dev/annotate.md) — label traces and build datasets
* [Evaluate](https://docs.braintrust.dev/evaluate.md) — measure quality and catch regressions
* [Deploy](https://docs.braintrust.dev/deploy.md) — ship to production with the AI gateway


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