The AI Native Dev - from Copilot today to AI Native Software Development tomorrow cover image

What Holds Devs Back From Multi-Agent Thinking | Guy Podjarny

The AI Native Dev - from Copilot today to AI Native Software Development tomorrow

00:00

Scaling evals with LLM-generated tests

Guy explains generating test exercises for 270 libraries and lifting average agent success from 60% to 81%.

Play episode from 22:19
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app