Skip to main content
Instrumentation captures detailed traces from your AI application, recording inputs, outputs, model parameters, latency, token usage, and metadata for every request. This gives you visibility into:
  • How your application behaves with real user inputs
  • Where failures and edge cases occur
  • Performance bottlenecks and token usage
  • Data for building evaluation datasets
Braintrust makes instrumentation simple with automatic wrappers for popular AI providers and frameworks, or manual tracing for custom workflows.

​
Anatomy of a trace

A trace represents a single request or interaction in your application. Each trace contains one or more spans. Anatomy of a trace A span represents a unit of work with a start and end time. Common examples include:
  • LLM API calls
  • Vector database searches
  • Tool or function invocations
  • Agent reasoning steps
  • Scoring functions
Each span captures:
  • Input: The data sent to this step
  • Output: The result produced
  • Metadata: Model parameters, tags, custom data
  • Metrics: Latency, token counts, costs
  • Scores: Quality metrics (added later)
Spans nest inside each other to represent your application’s execution flow. Well-designed traces make it easy to understand what happened and debug issues.

​
How to instrument

Braintrust provides three approaches to instrumentation, from simple to advanced:

Wrap AI providers

Automatically log all LLM calls

Integrate frameworks

Use existing framework integrations

Custom tracing

Manually instrument your code

​
What gets captured

Every instrumented request automatically captures:
  • Request inputs and outputs
  • Model parameters (model name, temperature, etc.)
  • Timing information (start time, duration)
  • Token usage and costs
  • Nested function calls and tool invocations
  • Errors and exceptions
  • Custom metadata you add
This data flows directly to Braintrust, where you can view it in real time, filter and search, add human feedback, and build evaluation datasets.

​
Provider and framework support

Braintrust integrates with all major AI providers and frameworks:
  • AI Providers: OpenAI, Anthropic, Gemini, AWS Bedrock, Azure, Mistral, Together, Groq, and many more
  • Frameworks: LangChain, LangGraph, OpenTelemetry, Vercel AI SDK, LlamaIndex, DSPy, Pydantic AI, and many more
Browse the complete integrations directory to find setup guides for your stack.

​
Next steps

Get started instrumenting your application: