Evals & ObservabilityTalk (25 min)Beginner
Regression Testing for LLM Features
Monday, October 12 · 2:00 PM to 2:25 PM PDT · Golden Gate Ballroom
Your prompt changed and something broke three weeks later. A practical eval harness you can add to CI this afternoon.
- Track
- Evals & Observability
- Format
- Talk (25 min)
- Level
- Beginner
- Room
- Golden Gate Ballroom
Speaker
- Founder, EvalKit
Maja started EvalKit after watching three teams ship LLM features with no regression testing at all.