AI observability and evaluation tools for Java applications, built on OpenTelemetry.

Run evals, monitor model quality, and more from your Vercel dashboard.

Introducing Braintrust's MCP server.

Which one you should ship with, and how to know for sure.

Why we built infrastructure for AI products, not just another evaluation tool.

xAI recently announced Grok 4. We put it to the ultimate test.

Run full evals directly in a powerful editor UI.

Brainstore is now the default in both our UI and API. Learn what's changing and coming next.

LLM observability, now 80x faster.

Full support for Bedrock, Vertex AI, and structured outputs in the AI proxy and playground.

The easiest way to self-host Braintrust.

Our year in review.

More visibility into performance across logs and experiments.

Faster, more efficient, and highly accurate for real-world applications.

How we used the uv library to build Python tools.

No server setup or configuration necessary.

Observability for advanced AI applications.

Introducing functions, a general-purpose primitive for building, evaluating, and observing AI products.

Create custom scorers and access them via the Braintrust UI and API.

Check out your Braintrust 2023 year in review to see how you did this year!

Introducing Braintrust's latest feature: an AI proxy that lets you use open source models like LLaMa 2 and Mistral, as well as all of OpenAI's and Anthropic's models, behind a single interface with caching, security, and API key management built in.