Observability for production agents with zyBooks
9 December 202610:00 AM PT

Gabe BealAI Platform Lead, zyBooks

Nick SlavinSolutions Engineer, Braintrust
Most teams find agent issues by reviewing traces by hand, writing evals for problems they already know about, and waiting for support tickets when something breaks. Patterns investigates recurring behaviors, verifies each finding with evidence, explains the impact, and recommends a next step.
In this live session, Braintrust’s Nick Slavin sits down with Gabe Beal, AI platform lead at zyBooks, to talk about how his team uses Patterns to find recurring agent issues, decide which ones matter most, and confirm their fixes are improving quality.
What you’ll learn
- How zyBooks uses agent traces to guide investigations and solve customer issues
- How to connect production data to evals in a continuous feedback process
- How Patterns investigates and identifies recurring agent behaviors and recommends a solution
Recent on-demand workshops
Eval foundations: Answering questions about your agent
4 November 202610:00 AM PT
In this live workshop, Jess will share example evals developed at Braintrust for three different use cases. Testing an agent workflow, choosing a model judge, and comparing models.
Eval foundations
7 October 202610:00 AM PT
Designed for new Braintrust users, this workshop will cover the core foundations of evals and how to get started with Braintrust.
Put the workshop into practice
Start using Braintrust to trace what ships, score it against real data, and turn every regression into an eval you can rerun.