Stanford launches CS329Z on Engineering AI Agents, taught by SWE-agent creator
stanfordnlp · x · 2026-11-03
Stanford's new fall course CS329Z 'Engineering AI Agents' is taught by Diyi Yang, Michael Ryan, and John Yang (first author of SWE-agent).
The curriculum covers the full agent engineering stack: RAG, tool use, MCP, design patterns, memory, multi-agent systems, optimization, data, evaluation, and safety. Students build RAG, tool calls, and agent loops from scratch before learning what DSPy and LangGraph abstract away.
Highlights:
- Two lectures on evaluation, two on LLM-as-Judge, two on data, plus guest talks from Terminal-Bench and SWE-bench authors
- A fireside chat with Andrew Ng
- Homework 1: build an email agent handling empty replies, format errors, truncated tool calls, and call budgets
The course is actually 19 sessions plus a Demo Day (3 guest sessions), not the rumored 22. Slide PDFs are freely downloadable from the course site.
More from coding & agent
- 10,000 AI agents burned his API credits; 500 agents in 50 waves worked — Beneficial-Cow-7408 · 2026-11-03
- Walrus MCP Server connects AI assistants to decentralized storage — modelcontextprotocol · 2026-11-03
- News Volume Trends MCP queries news volume growth for any topic — modelcontextprotocol · 2026-11-03
- Pen ships a canvas plugin for Codex, adding design powers to ChatGPT — paw_lean · 2026-11-03
- Elicit engineers all use Ramp's Inspect — a credit card company builds a top coding agent harness — jungofthewon · 2026-11-03
- VibeArmory launches macOS private beta: monitoring and firewalls for AI coding agents — agf2007 · 2026-11-03