R087 · AI education › Learning paths for AI engineers

Stanford CS329Z: Engineering AI Agents, a free course map

Read the original

educationagent-architectureevaluationragtool-useteaching

Source: the CS329Z course site (cs329z.stanford.edu), Stanford, Fall 2026. Instructors Diyi Yang, Michael Ryan and John Yang. Surfaced by Hao Hoang's LinkedIn post.

What it is

A graduate course on building agentic systems across the whole range from simple LLM pipelines to compound AI systems to autonomous agents. Students build the core pieces (RAG, tool use, agent loops) from scratch first, then see how frameworks such as DSPy abstract them. Coursework is two applied homeworks and a quarter-long project. Slides and readings are on the site; lecture videos are being posted as the quarter runs (eight video links were live on 15 November).

Syllabus at a glance

BlockLectures
FoundationsWhat agentic systems are (history, anatomy, compound systems vs agents); LLMs for builders (decoding, attention and context length, post-training, test-time scaling)
Building blocksRAG end to end (chunking, hybrid search, reranking, ColBERT, agentic RAG); tool use (Toolformer, Gorilla, function calling, MCP, BFCL and tau-bench)
Frameworks and designFrameworks and orchestration; design patterns (workflows vs agents, ReAct, CodeAct, scaffolds)
Memory and multi-agentMemory architectures; when to use one agent or many
OptimizationContext and prompt optimization and when it pays off
Data for agentsWhat data agents need (traces, demonstrations, feedback); data selection and quality
EvaluationBenchmark design; LLM-as-judge and evaluation infrastructure
GuestsTerminal-Bench and SWE-bench teams; a fireside chat with Andrew Ng
Safety and applicationsAgent safety and guardrails (tool-access privacy, prompt injection); coding agents; personal agents

Why it is worth a staff engineer's time

Gaps to fill elsewhere

How to use it

  1. Watch lectures 1 to 4 and build a minimal agent with one chat-completion call and your own tool loop.

  2. Use the design-patterns and memory lectures as a vocabulary check for your team.

  3. Take the data and evaluation block as the template for your own agent evals.

  4. Pair with an open harness-engineering course for production concerns.

R023 (building a coding agent from scratch), R022 (AI engineering reading list), R081 (LLM engineering toolkit), R086 (agents on long-horizon benchmarks), R064 (measuring whether a skill helps).

Connections

See R087 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.