Stanford launches CS329Z, a new course on engineering AI agents from scratch
Diyi_Yang · x · 2026-09-03
Stanford's Diyi Yang, Michael Ryan and John Yang are teaching CS329Z "Engineering AI Agents" this fall, covering the full stack of agent building: training data, RAG, agent design patterns/harnesses, and evals.
Hands-on assignments include building an agentic harness from scratch (Hw1) and creating novel evals that challenge frontier models (Hw2), capped by a custom agentic application project. The course site will be updated with lectures and assignments.
Related event: Stanford launches CS329Z: Engineering AI Agents this fall(4 posts)→
More from coding & agent
- Agno 3.0 ships with 100% ARC-AGI-3, persistent Python kernel and durable background runs — pritisinghhhh · 2026-09-03
- Hand Codex a Video URL and It Analyzes Weird Flowing-Water Harmonics — johnowhitaker · 2026-09-03
- Devnexus, largest US Java conference, retools 2027 around AI with 10 tracks — mkheck · 2026-09-03
- Auth0Lab opens up: first public look at how it does 0-to-1 products — yenkel · 2026-09-03
- Notch says AI coding turns a 10x engineer into 100x after Fable 5.1 flow session — majidmanzarpour · 2026-09-03
- Harvard Proposes Agentic Data Cracking, Cuts Unstructured QA Cost 53% on FanOutQA — Harvard · 2026-09-03