Building reliable AI agents AI Search Bar An agent that runs OpenAPI commands How Zapier uses assertions to evaluate tool usage in chatbots Classifying news articles Coda's Help Desk with and without RAG Evaluating a chat assistant Improving Github issue titles using their contents Generating beautiful HTML components Tool calls in LLaMa 3.1 Comparing evals across multiple AI models Using OpenTelemetry for LLM observability Using PDF attachments in playgrounds Evaluating the precision and recall of an emotion classifier Evaluating a prompt chaining agent Detecting Prompt Injections Prompt versioning and deployment Benchmarking inference providers Evaluating audio with the OpenAI Realtime API Evaluating multimodal receipt extraction Generating release notes and hill-climbing to improve them Evaluating SimpleQA Optimizing Ragas to evaluate a RAG pipeline Classifying spam using structured outputs Text-to-SQL LLM Eval For Text2SQL Using Python functions to extract text from images Using functions to build a RAG agent Unreleased AI: A full stack Next.js app for generating changelogs Tracing Vercel AI SDK applications Evaluating video QA Evaluating video QA with Twelve Labs Evaluating a voice agent Evaluating a web agent

Cookbook

This cookbook, inspired by OpenAI's cookbook, is a collection of recipes for common use cases of Braintrust. Each recipe is an open source self-contained example, hosted on GitHub. We welcome community contributions and aspire for the cookbook to be a collaborative, living, breathing collection of best practices for building high quality AI products.

Loading cookbook filter...

Home
Docs
Pricing
Blog
Careers
Chat with us
Discord
Changelog
Status
Trust center
Privacy
Terms

Cookbook - Docs - Braintrust