斯坦福 CS146S 课程：让学生向开源维护者提交真实补丁
斯坦福 CS146S 课程在编码智能体可一键完成作业的背景下，改为让学生学习陌生开源仓库、提出修改并向可能合并补丁的维护者解释方案。授课人 Mihail Eric 同时负责 Monaco 的 AI 工作，他在访谈中展示了课程大纲，并分享了团队自建智能体工作区、采购代码审查工具、让值班智能体接入 Datadog 与 GitHub 的实践取舍。
报道正文
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 explain the patch to the person who might merge it.
We invited Mihail, who teaches The Modern Software Developer at Stanford and leads AI at Monaco, to celebrate one million subscribers on the AI Engineer YouTube channel. He opens up the course syllabus and shows us which lessons survived contact with his own engineering team. Monaco built its agent workspaces, bought its code review tools, and gave an on-call agent access to Datadog and GitHub. We ask how he decides which tools his team needs to own.
Watch the full interview and screenshares on YouTube.
Show notes
- Stanford CS146S — The ten-week syllabus and assignments.
- The Emperor Has No Clothes — Mihail builds a coding agent from scratch.
- Demystifying Claude Code — Mihail traces a real agent harness.
- Monaco’s agent workspaces — How the team sets up a workspace for each agent.
- How to Kill the Code Review — Our essay on what happens when code generation outruns review.
- Basis’s Authority Map — How agents distinguish current behavior from earlier design decisions.
- Stripe’s Minions — A look inside Stripe’s background coding agents.
- AI Engineer CODE Summit — The conference mentioned in the opening.
Timestamps
0 One million AI Engineer subscribers and the CODE Summit 0 Mihail Eric and Stanford CS146S 5 What junior engineers need to learn now 10 Open-source maintainers review the students’ code 15 A tour of the ten-week syllabus 24 The loop, tools and harness inside a coding agent 32 Context engineering for a large codebase 38 Skills that make you understand the diff 46 The Monaco.com dispute and the airplane banner 50 What Monaco does for sales teams 59 Inside Monaco’s engineering team 1:01 1:05 Making repos agent-ready and closing the on-call loop 1:12 When code review becomes the bottleneck 1:20 Security, dependencies and permissions 1:30 Background agents and Stripe’s Minions 1:34 MCP portals and why infrastructure converges 1:41 Building the software factory 1:45 What work is left for developers? 1:52 From personal adoption to team autonomy
Opening excerpt from The Thinking Mode, EO Studio.