Back to workshops
Free workshop90 minStarts 15 Oct
Eval-driven development for LLM apps
A free 90-minute live session on measuring an AI feature before you build it.
Save your seatBring a feature you are working on. We will build the harness for it live.
What we cover
- Why teams stall at the demo stage
- Assembling a golden set from bug reports
- Scoring functions you can argue with
- Wiring a regression gate into CI
Who it is for
- Engineers shipping an LLM feature this quarter
- Teams whose AI quality is currently a matter of opinion