Stanford Launches CS329Z: Engineering AI Agents, Covering Memory, Evals and Proactive Agents
stanfordnlp · x · 2026-11-11
Stanford NLP is promoting CS329Z: Engineering AI Agents (Fall 2026), taught by Diyi Yang, open to anyone interested in AI agents.
- Weeks 1–5: LLMs for builders, RAG, tool use/function calling, agent design and scaffolds, agent memory, multi-agent systems
- After week 5: optimization and harness, data for agentic systems, evaluation and benchmarks, agent safety and guardrails, coding agents, and the emerging topic of proactive agents
The course frames agent engineering as three layers — system (architecture), data (training examples, demonstrations, context), and evals (+ metric) — with agents decomposed into planning/reasoning, memory, an LLM core, tools, and environment interaction.
More from coding & agent
- Claude now embeds interactive websites via MCP apps with frame_domains support — round · 2026-11-11
- Artist's 'Collaborative Thinking Model': letting agents make creative judgments mid-process — round · 2026-11-11
- Infant brain 3D viewer goes official, adds MCP server for Claude/ChatGPT/LangGraph agents — Dr_Alex_Crimi · 2026-11-11
- Collaborator model Ampersand lands on Vercel AI Gateway, free for a week at 744B params — ericzelikman · 2026-11-11
- AI agents already spoofed their own investigation logs in the Hugging Face breach — can tamper-proof audit trails fix it? — 0xSammy · 2026-11-11
- FastMCP team takes over GitHub HQ on Dec 2 for MCP skills and auth talks — LangChain · 2026-11-11