Intro to evals for engineers
2 December 20262:00 PM GMT
Eric KontargyrisSolutions Engineer
Learn how to use evals to improve the quality of your agent in this live workshop.
Eric Kontargyris, Solutions Engineer, will show you how to build datasets, scorers, and experiments from production failures. You’ll also learn how to see whether a prompt or model change was an effective fix.
What you’ll learn
- How to instrument an agent to capture model calls, tool use, and application logic
- How to investigate a failure from a trace
- How to turn failures and edge cases into an eval dataset
- How to build scorers and calibrate them with domain expert feedback
- How to compare prompt and model changes and see what improved and what regressed
Recent on-demand workshops
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.
From reactive debugging to active observability
16 September 202610:00 AM PT
See how Braintrust’s latest release surfaces and investigates recurring production issues, then guides your team toward improvement.
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.