Stanford to launch CS329Z: a full course on engineering AI agents for Fall 2026
stanfordnlp · x · 2026-09-09
Stanford will offer CS329Z "Engineering AI Agents" in Fall 2026, taught by Diyi Yang, Michael Ryan and John Yang, treating agents as a full engineering discipline rather than an extension of LLM capabilities.
- Scope: the spectrum from monolithic models to compound AI systems to autonomous agents; three core challenges are decomposition, data, and evaluation
- Hands-on: students build RAG, tool use and agent loops from scratch, then learn how frameworks like DSPy, LangGraph and MCP abstract these patterns
- Engineering tradeoffs: context engineering, model selection by accuracy × cost × latency, memory and multi-agent systems
- Evaluation-centric: eval design, LLM-as-a-Judge, error analysis, synthetic data, adversarial testing, isolation, permissions, and human oversight
Related event: Stanford to Launch CS329Z Course on Engineering AI Agents(2 posts)→
More from coding & agent
- Econometrician: every agent-driven econometrics task still needs manual standard-error fixes — danielrock · 2026-09-09
- Meta's Muse AI agent can now search, compare and book travel via Duffel connector — chetanp · 2026-09-09
- OpenAI's Navier–Stokes run: train-while-deploying and 10,000 coordinated agents — DataLearnerAI · 2026-09-09
- Hermes Agent adds Perplexity Search integration, tapping an index of 400B+ URLs — Teknium · 2026-09-09
- Dev open-sources contextwise: BM25-routed MCP wrapper cuts 40k tokens to 7k — b-dub-d · 2026-09-09
- OpenAI's Codex lead praises Ant's new coding agent for matching Codex background computer use — soumitrashukla9 · 2026-09-09