TALK-005Long-running agentsHarness designClaude CodeAgent evaluation
Anthropic engineers just showed how they build a full app from scratch, using a loop of agents.
Ash, Andrew
Talks worth your time · AI News & Podcast · 2026-09-29 · 40 min · 11 pages
Anthropic engineers just showed how they build a full app from scratch, using a loop of agents 40 minutes from the team behind Claude Code they used three agents: one to plan, one to build, one to judge, cycling until the app actually works the winners won't have the smartest model, they'll have the best loop watch it, then read the full guide on how to actually use loops below
Generated automatically from the recording's transcript. It's meant to replace re-watching, not the recording itself — verify against the video at the timestamp before quoting formally. Slides belong to the speakers and organisers. Produced with recording-to-pdf.