Braintrust Weekly Update

It’s been a busy week for us at Braintrust. Here’s some of the new features we shipped this week:

Tracing: log and visualize complex LLM chains and executions.

We built a new feature to help you debug and observe your LLM app. Add two lines of code to log a function call and get useful traces in the Braintrust UI. Investigate each step of your LLM pipeline, see how long it took, and debug the context. You can also log metadata like token usage, errors, and more. Try it out and learn more on our Tracing docs .

Experiment dashboard customization

We made the experiment dashboard customizable. Click on the settings button next to the summary title to select which charts you’d like to see for the experiment.

Release notes:

• Added a new “text-block” prompt type in the playground that just returns a string or variable back without a LLM call (useful for chaining prompts and debugging)
• Increased default # of rows per page from 10 to 100 for experiments
• Updated evals documentation
• UI fixes and improvements for the side panel and tooltips
• Launched new tracing feature: log and visualize complex LLM chains and executions.
• The experiment dashboard can be customized to show the most relevant charts

Braintrust is the enterprise-grade stack for building AI products. From evaluations, to prompt playground, to data management, we take uncertainty and tedium out of incorporating AI into your business.

Sign up now, or check out our pricing page for more details.