Stanford CS329Z assignments: build an agentic harness and novel frontier-model evals
Diyi_Yang · x · 2026-09-03
Details on Stanford's new CS329Z "Engineering AI Agents" course: lectures cover everything needed to build agents — training data, RAG, agent design patterns/harnesses, and evals. Hw1 has students build an agentic harness from scratch, Hw2 asks them to create novel evals that challenge frontier models, and the course ends with a custom agentic application project. The course site will be updated with materials.
Related event: Stanford Launches CS329Z: Engineering AI Agents from Scratch This Fall(7 posts)→
More from coding & agent
- Anthropic borrows lawyers' ethics for Claude agents that closed 186 deals with no human approval — rohanpaul_ai · 2026-10-18
- Prompt injection via email can hijack your AI agent — jev-guard adds risk-scored guards — sujingshen · 2026-10-18
- 14-Agent AI Film Pipeline on One RTX 5090: Fixing Cut Defects Between Clips — developervkmp · 2026-10-18
- Meta paper introduces "agent plasticity": best-performing agent isn't the most efficient learner — rohanpaul_ai · 2026-10-18
- Dev ships a bushfire prediction platform in a weekend with frontier models — CtrlAltDwayne · 2026-10-18
- 10 open-source GitHub repos that let AI agents control your phone, from Open-AutoGLM to mobile-use — victor_explore · 2026-10-18