How Anthropic Builds: Lessons from Labs — Mike Krieger, Anthropic
Source
youtube.com
Author
AI Engineer
Date
Why it matters
The review bottleneck moves from lines of code to human comprehension: large AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →-authored PRs travel with an intent-and-tradeoffs artifact instead of line-by-line reading, inside a team structure that winds projects down on a two-week cycle.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
videoAI Security Engineer Foundations + Certificate — Micah Silverman, Snyk
videoThe SDLC You Build Yourself — Andy Wong, Andrei Bocan & Shane Wolf, Atlassian
videoAgent Speedrun — Elizabeth Fuentes Leone & Sandhya Subramani, AWS
videoCan Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
videoAnthropic's CPO on what comes next | Mike Krieger (co-founder of Instagram)Lenny's Podcast
podcastAnthropic’s first technical PM on token maxing, the jagged edge, and living in the future | Dianne PennLenny Rachitsky
videoCoding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, TesslAI Engineer