About this session

Your AI is in production, but is it actually good? In this hands-on workshop, you'll learn how to uncover patterns in your production traces using Braintrust Topics, build custom scorers to target real issues, and systematically improve your agent. By the end, you'll have a repeatable eval workflow and trace-backed evidence that your AI is actually doing what you think it is. What You'll Build: 1. A quality analysis using Topics 2. Custom scorers targeting specific issues 3. An optimized agent with traces to prove improvements A hands-on workflow for going from "I think my agent is working" to trace-backed evidence that it actually is.

Speaker

Doug Guthrie

Solutions Engineer · Braintrust