Stanford CS329Z site is live with full syllabus on engineering agentic systems
Diyi_Yang · x · 2026-09-03
The website for Stanford's CS329Z "Engineering AI Agents" (Fall 2026, taught by Diyi Yang, Michael Ryan and John Yang) is live with a full syllabus.
- Course thesis: the shift from monolithic LLMs to compound AI systems demands engineering skills — problem decomposition, data curation, and evaluation
- Students build core components (RAG, tool use, agent loops) from scratch, then learn how frameworks like DSPy abstract these patterns
- Schedule is published week by week: week 1 covers the agentic systems landscape (with readings like Zaharia et al.'s "The Shift from Models to Compound AI Systems"), week 2 covers LLM APIs/SDKs (litellm), structured/constrained generation and decoding strategies
- Lecture materials and assignments will be released on the site.
Related event: Stanford Launches New Course CS329Z: Engineering AI Agents from Scratch(5 posts)→
More from coding & agent
- WebMCP demo shows external agents controlling embedded pages in the browser — thisiskp_ · 2026-09-03
- Podcast deep dive: 7 personal AI bots for chief-of-staff, SOC 2 monitoring, and more — lennysan · 2026-09-03
- Muse launches Spark 1.3, a proactive agentic model update, third release in three days — bowenc0221 · 2026-09-03
- text-to-cad: open-source agent skills that turn plain language into CAD models and robot URDFs — tom_doerr · 2026-09-03
- Google Cloud launches free hands-on training to build and ship production agents — leslysandra · 2026-09-03
- Memoryfields: agent memory as portable Markdown files plus an optional SQLite index — rseroter · 2026-09-03