Evaluating Agents With Braintrust

Evaluating Agents With Braintrust Information Guide

1. Background of Evaluating Agents With Braintrust
2. Main Features
3. Developments
4. Full Guide
5. Conclusion

Background of Evaluating Agents With Braintrust

Jason Lopatecki, Co-Founder and CEO of Arize AI, dives into the world of This hands-on workshop guides participants through the full AI In this video, we walk through the complete eval workflow, including creating datasets, prompts, and scorers. Traditional observability answers one question: is the system up? Phil Hetzel from Most teams approach evals like unit tests and try to cover every possible failure. Phil Hetzel from We've now moved on to evals for multi-turn conversations in

This video breaks down practical steps to build, measure, and scale voice

Main Features

Developments

Evaluating agents: how we built Loop, the AI assistant for evals

Intro to Evals with Braintrust

How agent o11y differs from traditional o11y — Phil Hetzel, Braintrust

Intro to Loop: the AI agent for evals and observability in Braintrust

The maturity phases of running evals — Phil Hetzel, Braintrust

Evals Course: Analyzing multi turn traces

Evals for real-world voice agents

Braintrust and Box on AI agents and the future of AI observability

Evals Course: Building a simple eval using Braintrust SDK

Full Guide

Data is compiled from public records and verified media reports.

Last Updated: June 24, 2026

Conclusion

Disclaimer: Disclaimer: Details estimates are based on publicly available data, media reports, and financial analysis. Actual numbers may vary.