Stanford Launches CS329Z: Engineering AI Agents

X postMark PhelpsResource

Stanford University has released the curriculum for CS329Z ('Engineering AI Agents') for Autumn 2026. The course covers compound AI systems, building RAG and tool use from scratch, agent frameworks like DSPy, and systematic agent evaluation.

Key points

  1. The curriculum spans the full continuum from simple LLM pipelines to compound AI systems and autonomous agents.
  2. Students build core building blocks (RAG pipelines, tool execution) from scratch before exploring high-level abstractions like DSPy, LangChain, or LlamaIndex.
  3. Key topics include context engineering, Model Context Protocol (MCP), memory architectures, multi-agent coordination, and error propagation.
  4. All syllabus materials are publicly available on the course website, with lecture recordings scheduled to appear on Stanford Online's YouTube channel.
  5. Mark Phelps shared the launch, planning to document his progress publicly and sharing an integrated study plan combined with CS336.

Why it matters

Prototype agents are simple to spin up, but production-grade engineering demands rigorous problem decomposition, reliability, and robust evaluation. Stanford's open curriculum provides software engineers with an academic, principled guide to building compound AI architectures.

Analysis

The course structure underlines an industry-wide transition from single model prompts to compound systems. By requiring students to implement agent loops and retrieval mechanisms natively before turning to orchestration frameworks, the curriculum emphasises fundamentals, trade-off analysis, and quantitative evaluation over framework-dependent patterns.

Original post

Mark Phelps

@mark_a_phelps · 24 September 2026

Stanford dropped CS329Z today. Engineering AI Agents. compound systems, build RAG/tool use from scratch, then frameworks, then how you actually evaluate this stuff. gonna follow along online. looks pretty neat. t.co/7To6HNMqxu

1.2k likes9 replies2.3k bookmarks66.1k views

View on X
More posts in the thread (3)
  1. @abderrahmane_bd from one of the instructors: t.co/OsQ5OjLGKt
  2. @ikogan_ from one of the instructors: t.co/OsQ5OjMeA1
  3. ill post notes in this thread as i work through the lectures. follow along if youre taking it too. I asked Hermes to build a study plan between this course and CS336 t.co/SpjTkch4Ng if anyone wants it I can put it on GitHub
Selected replies (5)
  • @abderrahmane_bd @mark_a_phelps do they have youtube playlist ?
  • @ikogan_ @mark_a_phelps No lectures. No assignments.
  • @cristofrcharles @mark_a_phelps Very cool. Thanks for sharing.
  • @Ganeshhkumar777 @mark_a_phelps How do you actually follow it?
  • @golden_tronte @Ganeshhkumar777 @mark_a_phelps This is from one of the instructors. t.co/noChouQiek

Mentioned links

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:Diyi Yang, Michael Ryan, John Yang

    CS 329Z: Stanford Course on Engineering AI Agents

    Stanford University is running CS 329Z (Engineering AI Agents) for Fall 2026. The course explores the transition from monolithic language models to compound AI systems and autonomous agents. All lecture materials, syllabus details, and reading lists are made publicly available online.

    AI & LLMs· Resource

  • Link:Aakanksha Chowdhery, Azalia Mirhoseini

    Stanford CS329A: Self-Improving AI Agents

    Stanford University's CS329A is a graduate course dedicated to self-improving AI agents, taught by Aakanksha Chowdhery and Azalia Mirhoseini. The curriculum covers foundational and modern techniques enabling LLMs to iteratively improve via environment interaction and internal feedback.

    AI & LLMs· Resource

  • X post:0xMarioNawfal

    Anthropic Releases Free Course on Loop Engineering

    According to a post by 0xMarioNawfal, Anthropic has released a free educational course on Loop Engineering aimed at developers working with AI agents.

    AI & LLMs· Resource

  • Video

    Video:Stanford Online

    Stanford CS329A: Introduction to Self-Improving AI Agents and Scaling Trends

    In the inaugural lecture of Stanford's CS329A course, Aakanksha Chowdhery and Azalia Mirhoseini outline the evolution of large language models towards autonomous, self-improving agents. The session explores foundational scaling laws, the emergence of chain-of-thought reasoning, post-training alignment via RLHF, inference-time scaling techniques, and the architectural principles behind agentic workflows in software engineering and research.

    AI & LLMs· Talk

  • Repository:walkinglabs/learn-harness-engineering

    Learn Harness Engineering: Open-Source Course for Reliable AI Coding Agents

    The open-source project learn-harness-engineering by walkinglabs provides a project-based beginner curriculum on harness engineering for autonomous coding agents. It teaches how to build runtime environments, state management, verification routines, and control systems needed to operate AI agents reliably.

    14.8kstarsTypeScript

    AI & LLMs· Tutorial

  • X post:Swapna Kumar Panda

    Curated List of Eleven Hands-On Courses on Agentic AI and Multi-Agent Systems

    Swapna Kumar Panda has compiled eleven practical courses focused on agentic AI. The selection covers beginner-friendly tutorials as well as in-depth curricula on LangGraph, Claude Code, enterprise RAG, and multi-agent workflows.

    4.8kbookmarks167.5kviews

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.