Stanford CS146S “The Modern Software Developer”: a course on building software with AI
TL;DR
CS146S (3–4 units) covers AI tools in IDEs, terminals, code review and testing, combined with complex-system design principles, a team project and real engineering tasks. Lecture materials and assignments are widely shared and translated by the community — a solid self-study resource for developers and tech leads.
Main topics
| Topic | Practical meaning |
|---|---|
| AI in IDEs and terminals | Coding agents, context, prompting on real codebases |
| AI-assisted review, debugging, testing | AI as a second reviewer, test generation, bug finding |
| AI workflows across the SDLC | From spec → code → deploy → operations |
| When to trust AI | Evaluation, verification, model limits |
| Team project | Coordinating humans + agents in a team |
Suggested 4-week self-study path
- Week 1: read the coding-agent material, install Claude Code or an equivalent tool.
- Week 2: redo the context/prompting assignments on a personal repo.
- Week 3: practice AI review + testing, log the mistakes AI tends to make.
- Week 4: a 2–3 person mini project where each person “manages” an agent.
References: Stanford Bulletin — CS146S