Stanford CS146S teaches AI-native engineering via open-source maintainer reviews
Original title: [One Million AI Engineer Special] How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco
Podcast with Monaco's AI lead discusses Stanford course where students review open-source code for AI agents.
In Stanford's CS146S, students learn an unfamiliar repo, propose changes, and explain patches to potential merge maintainers. Mihail Eric discusses the syllabus surviving his engineering team's input, agent workspaces, code review tools, and on-call access to Datadog and GitHub. The interview covers deciding which tools to own, making repos agent-ready, and the remaining work for developers when agents handle routine tasks.
- Students propose changes and explain patches to open-source maintainers
- Ten-week syllabus covers context engineering and diff understanding
- Monaco's team uses agent workspaces and background coding agents
- Code review becomes a bottleneck when generation outruns review
- Work left for humans includes understanding design decisions
From the original article
2 min read at latent.space
What do you assign when a coding agent can finish last year’s homework in one prompt? In the second run of Stanford’s CS146S, Mihail Eric brought open-source maintainers into the course. Students have to learn an unfamiliar repo, propose a change, and ...
By Latent.Space · latent.space
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.