Paige Bailey, ETLS Vegas (99)
summary
Gemini ingests recorded user sessions and automatically produces detailed friction logs with timestamps, quoted user actions, and classified error types, then outputs a prioritized feature list with suggested fixes and estimated impact versus effort. It scales studies that normally handle about 10–12 sessions and take months up to hundreds of sessions in days, and it demonstrably extracts actionable UX tickets from raw video using a single command like “generate a detailed friction log.”
AI-written summary · about
related talks
30mDebugging at Scale Using Elastic and Machine Learning
23mObservability for LLMs: Understanding What’s Happening Under the Hood
15mUsing Statistical Techniques to Automatically Detect Game-Breaking Issues
35mBuilding an enterprise NLSE ...
32mOpenTelemetry, databases, and machine learning
49mBehind the Streams: In Depth Look At ML&AI Powered Analysis of FPS Gameplay
05mThe Future of Evals
34mAs The World Turns