# Braintrust Observability

Braintrust is an end-to-end platform for building AI applications. When building with the AI SDK, you can integrate Braintrust to [log](https://www.braintrust.dev/docs/guides/logging), monitor, and take action on real-world interactions.

## Setup

### OpenTelemetry

Braintrust supports [AI SDK telemetry data](/docs/ai-sdk-core/telemetry).
To set up Braintrust as an [OpenTelemetry](https://opentelemetry.io/docs/) backend, you'll need to route the traces to Braintrust's OpenTelemetry endpoint, set your API key, and specify a parent project or experiment.

Once you set up an [OpenTelemetry Protocol Exporter](https://opentelemetry.io/docs/languages/js/exporters/) (OTLP) to send traces to Braintrust, we automatically convert LLM calls into Braintrust `LLM` spans, which can be saved as [prompts](https://www.braintrust.dev/docs/guides/functions/prompts) and evaluated in the [playground](https://www.braintrust.dev/docs/guides/playground).

To use the AI SDK to send telemetry data to Braintrust, set these environment variables in your Next.js app's `.env` file:

```bash
OTEL_EXPORTER_OTLP_ENDPOINT=https://api.braintrust.dev/otel
OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer <Your API Key>, x-bt-parent=project_id:<Your Project ID>"
```

You can then use the `experimental_telemetry` option to enable telemetry on supported AI SDK function calls:

```typescript
import { createOpenAI } from '@ai-sdk/openai';
import { generateText } from 'ai';

const openai = createOpenAI();

async function main() {
  const result = await generateText({
    model: openai('gpt-4o-mini'),
    prompt: 'What is 2 + 2?',
    experimental_telemetry: {
      isEnabled: true,
      metadata: {
        query: 'weather',
        location: 'San Francisco',
      },
    },
  });
  console.log(result);
}

main();
```

Traced LLM calls will appear under the Braintrust project or experiment provided in the `x-bt-parent` header.

### Model Wrapping

You can wrap AI SDK models in Braintrust to automatically log your requests.

```typescript
import { initLogger, wrapAISDKModel } from 'braintrust';
import { openai } from '@ai-sdk/openai';

const logger = initLogger({
  projectName: 'My Project',
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const model = wrapAISDKModel(openai.chat('gpt-3.5-turbo'));

async function main() {
  // This will automatically log the request, response, and metrics to Braintrust
  const response = await model.doGenerate({
    inputFormat: 'messages',
    mode: {
      type: 'regular',
    },
    prompt: [
      {
        role: 'user',
        content: [{ type: 'text', text: 'What is the capital of France?' }],
      },
    ],
  });
  console.log(response);
}

main();
```

## Resources

To see a step-by-step example, check out the Braintrust [cookbook](https://www.braintrust.dev/docs/cookbook/recipes/OTEL-logging).

After you log your application in Braintrust, explore other workflows like:

- Adding [tools](https://www.braintrust.dev/docs/guides/functions/tools) to your library and using them in [experiments](https://www.braintrust.dev/docs/guides/evals) and the [playground](https://www.braintrust.dev/docs/guides/playground)
- Creating [custom scorers](https://www.braintrust.dev/docs/guides/functions/scorers) to assess the quality of your LLM calls
- Adding your logs to a [dataset](https://www.braintrust.dev/docs/guides/datasets) and running evaluations comparing models and prompts


## Navigation

- [Braintrust](/v4/providers/observability/braintrust)
- [Helicone](/v4/providers/observability/helicone)
- [Laminar](/v4/providers/observability/laminar)
- [Langfuse](/v4/providers/observability/langfuse)
- [LangSmith](/v4/providers/observability/langsmith)
- [LangWatch](/v4/providers/observability/langwatch)
- [Patronus](/v4/providers/observability/patronus)
- [Traceloop](/v4/providers/observability/traceloop)
- [Weave](/v4/providers/observability/weave)


[Full Sitemap](/sitemap.md)