← back
The Making of Devin by Cognition AI: Scott Wu
Takeaway
Devin demonstrates that autonomous software engineers using human tooling (terminal, git, PRs) are the next phase beyond code-completion.
Summary
- Scott Wu shows Devin building a 'name game' web app for the conference from a TSV of speakers, with autonomous planning, React scaffolding, deployment, and plain-English iteration.
- Devin uses the same tools a human engineer has — terminal, editor, browser, git — and works inside repository snapshots with playbooks that encode repo conventions.
- In Cognition's own codebase Devin built features like the Devin sessions search bar end-to-end via PR review (visible Bryce↔Devin PR exchange).
- Wu argues the next wave is agents (autonomous decision-making) following the text-completion wave (ChatGPT, Copilot, Cursor); code is ideal because much of engineering is research/debugging not typing.
- Cognition started in November 2023 in hacker houses, alternating Bay/NYC, with Devin building parts of itself.
devinautonomous-agentscoding-agents
Original description
Meet Devin, a state-of-the-art AI software agent that helps developers save time and achieve more. Scott Wu, co-founder and CEO of Cognition AI, demos its capabilities and shares some of the lessons that he and his team have learned while building Devin. Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at https://www.ai.engineer/worldsfair/2024/schedule & join us at the AI Engineer World's Fair in 2025! Get your tickets today at https://ai.engineer/2025 About Scott Scott is the co-founder and CEO of Cognition AI. He previously competed in international programming competitions (3x IOI gold medalist) and co-founded Lunchclub, an AI-powered professional networking platform. Scott grew up in Louisiana and attended Harvard University.