Skip to content
Lenny's PodcastLenny's Podcast

Scott Wu: Why Devin will write half of Cognition's code

Cognition's 15 engineers each run up to five Devins in parallel; a quarter of monthly PRs already ship from agents, freeing architects to scope tickets.

Scott WuguestLenny Rachitskyhost
May 4, 20251h 32mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 9:13

    Introduction to Scott Wu and Devin

  2. 9:13 – 10:23

    Scaling and future prospects

  3. 10:23 – 17:26

    Devin's origin story

  4. 17:26 – 22:19

    The idea of Devin as a person

  5. 22:19 – 25:17

    How a team of “Devins” are already producing 25% of Cognition’s pull requests

  6. 25:17 – 30:21

    Important skills in the AI era

  7. 30:21 – 34:37

    How Cognition’s engineering team works with Devin's

  8. 34:37 – 42:20

    Live demo

  9. 42:20 – 44:50

    Devin’s codebase integration

  10. 44:50 – 46:53

    Automation with Linear

  11. 46:53 – 52:56

    What Devin does best

  12. 52:56 – 57:13

    The future of AI in software engineering

  13. 57:13 – 1:01:57

    Moats and stickiness in AI

  14. 1:01:57 – 1:04:14

    The tech that enables Devin

  15. 1:04:14 – 1:07:25

    AI will be the biggest technology shift of our lives

  16. 1:07:25 – 1:15:13

    Adopting Devin in your company

  17. 1:15:13 – 1:22:32

    Startup wisdom and hiring practices

  18. 1:22:32 – 1:32:31

    Lightning round and final thoughts

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome