Stanford Launches CS329Z: Engineering AI Agents, Taught by DSPy and SWE-bench Authors
stanfordnlp · x · 2026-11-13
Stanford's new fall course CS329Z "Engineering AI Agents", led by Diyi Yang with co-instructors Michael Ryan (DSPy team, MIPROv2/GEPA) and John Yang (SWE-bench, SWE-agent), teaches agents as engineering systems rather than framework tutorials.
Students first build core components (RAG, tool use, agent loops) from scratch, then learn how frameworks like DSPy abstract these patterns, with two applied homeworks and a quarter-long project.
The syllabus covers four blocks:
- Building blocks: RAG, tool use, MCP
- Design: design patterns, memory, multi-agent, context management
- Data & optimization: trajectory data, data flywheels, prompt optimization, RL
- Evaluation & safety: eval frameworks, LLM-as-judge, prompt injection, sandboxing
Evaluation spans three lectures featuring Terminal-Bench and SWE-bench authors. Slides and reading lists are already public on the course site.
Related event: Stanford Open-Sources CS329Z Engineering AI Agents Course(2 posts)→
More from coding & agent
- Cloudflare's AI Bets: Small-Model Wager Missed, Edge Compute Wins as Latency Returns — michellechen · 2026-11-13
- Burkov roasts Codex: nudging it repeatedly just to get from 15% to 26% done — burkov · 2026-11-13
- lclip CLI turns Liveclip tables into a Redis-style key-value store with a built-in web admin — firasd · 2026-11-13
- Founder vibe-codes a Calendly clone and shares the result — kylegawley · 2026-11-13
- HeyGen shares its MCP prompts for free, again — HeyGen · 2026-11-13
- Orchestrator rolls out to Pro subs, pairing Hydrogen and Argon to save quota — clmt · 2026-11-13