• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Stanford Launches CS329Z Course on Engineering AI Agents

    Diyi Yang, John Yang, and Michael Ryan will teach CS329Z this fall with lectures available online.

    DY
    AC
    JY
    16 Sources, 28d ago, first seen 28d ago

    TLDR

    Stanford computer science faculty Diyi Yang along with John Yang and Michael Ryan announced a new fall course called CS329Z: Engineering AI Agents. The class will cover building AI agents from scratch. The instructors posted that millions of users already interact with AI agents daily. Lectures will be offered online. Diyi Yang shared the official site cs329z.stanford.edu and said it will stay updated with assignments and lectures. The site lists schedule, deadlines, coursework, project details, and logistics.

    Combined views

    856.9K

    16 Sources, first seen 28d ago

    Combined views

    856.9K

    16 Sources, first seen 28d ago

    8.9K likes
    8.9K likes
    353 comments
    11.4K saves
    1.9K reposts
    353 comments
    11.4K saves
    1.9K reposts

    Sentiment

    Positive96.7%3.3%Negative

    Summary

    Sentiment

    Positive96.7%3.3%Negative

    Many accounts welcomed Stanford’s new CS329Z course on Engineering AI Agents because it teaches advanced topics like building agents from scratch, RAG, tool use, and multi-agent systems.

    Based on 64 sentiment-bearing replies from 60 accounts across 4 conversations.

    Summary

    Many accounts welcomed Stanford’s new CS329Z course on Engineering AI Agents because it teaches advanced topics like building agents from scratch, RAG, tool use, and multi-agent systems.

    Based on 64 sentiment-bearing replies from 60 accounts across 4 conversations.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    16 Sources

    @Diyi_YangThis fall @michaelryan207 @jyangballin and I are teaching a new course CS329Z "Engineering AI Agents" on how to build AI Agents from scratch. Come join us and learn how to build them 🤖
    @WilliamBarrHeldBiased take: If I had to pick a list of people who maximized the product of "Deep Expertise on Agents" and "Kind and Patient Teachers", I'd probably list these 3 people
    @michaelryan207🚨 New Course Announcement! This Fall @Diyi_Yang @jyangballin and I are teaching a BRAND NEW Stanford course on how to build AI Agents from scratch! Millions of users interact with AI Agents every day. Come join us and learn how to build them! 🧵 (1/5)
    @jyangballinRT @michaelryan207: 🚨 New Course Announcement! This Fall @Diyi_Yang @jyangballin and I are teaching a BRAND NEW Stanford course on how to…
    @achowdhery@Diyi_Yang Fun to see something quite like CS329A! Very cool!
    @StanfordAILabIf you want to learn how to engineer AI agents, these are the people you’d want to learn it from. They know the space inside and out and couldn’t be more excited to teach it. First time it’s running at Stanford this fall. @Diyi_Yang, @michaelryan207, @jyangballin
    @liweijianglwRT @Diyi_Yang: This fall @michaelryan207 @jyangballin and I are teaching a new course CS329Z "Engineering AI Agents" on how to build AI Ag…
    @Xudong07452910今天已经看到不少人在分享 Stanford 新开的 CS329Z: Engineering AI Agents。 不想再重复介绍课程，我反而更好奇： Stanford 到底把什么算作 2026 年的「Agent Engineering」？ 看完整 syllabus，RAG、Tool Use、MCP、Agent Framework 基本都放在前半程，更像 Agent 的基础能力。 真正让我注意的是后半段。 第一节课就把 Agent Engineering 的核心工程问题概括成： Decomposition、Data、Evaluation。 后面的课程也沿着这条线展开，从 Agent Data、Trajectory、Memory、Optimization，一直讲到 Evaluation、Coding Agent、Long-running Agent 和 Reliability。 作业设计也很值得关注。 第一个作业让学生从零搭 Agent；第二个直接变成 Evaluate an Agent：自己设计 benchmark、grader、LLM-as-Judge 和 error analysis。 Evaluation 甚至连续讲了两周。 一个很有意思的细节，是课程专门讲 pass@k 和 pass^k：前者看「多试几次能不能成功一次」，后者看「连续跑很多次能不能都成功」。 对 Agent 来说，这其实对应两种完全不同的可靠性。 Multi-Agent 那一节也挺克制。 一边讲 orchestration、handoff 和 collaboration，一边专门讨论协调失败和错误传播，reading 里甚至放了一篇： 《Don't Sleep on Single-agent Systems》 至少从这份 syllabus 看，「更多 Agent」并没有被默认等同于更好的系统。 所以我更愿意把这门课看成 Stanford 对 2026 年 Agent 技术栈的一次切片。 RAG、工具调用这些能力正在变成底座，后面更值得继续往下挖的，是 数据怎么来、系统怎么评、Agent 怎么优化，以及它能不能在复杂、长时间的真实环境里稳定跑下去。 这几个问题，感觉也会是接下来一两年 Agent 研究持续关注的方向。 https://cs329z.stanford.edu/
    @astaxie真的很感慨，斯坦福的课程更新速度太快了。 CS329Z 已经在教 AI Agent：RAG、Tool Use、MCP、Memory、Multi-Agent、Eval、Coding Agent…… 再看看很多大学生还在学习上一个时代、甚至已经被淘汰的东西。 强烈建议身边的大学生都去学学这门课，真的很值得。 https://cs329z.stanford.edu/
    @code_hiyougaIf you already know how to call models, connect tools, and build agents, Stanford’s new CS329Z: Engineering AI Agents is a useful place to check what you should learn next. Especially if your system runs and keeps gaining features, but you struggle to tell whether each change actually makes it better. The course starts with RAG, tool use, MCP, and agent frameworks, then covers memory, multi-agent systems, optimization, agent data, and evaluation. It also addresses safety and the reliability of agents running over extended periods. The assignments make this concrete: first, build a research-paper QA agent from scratch. Then design an evaluation suite for an existing agent, including benchmark tasks, code-based graders, an LLM-as-judge, and error analysis. I think this structure is particularly useful for people learning to build agents on their own. It’s easy to work through a feature checklist: connect more tools, add memory, try multiple agents. But every new component also introduces more ways the system can fail. Take a research assistant that gives the wrong answer. It might have failed to retrieve a key paper, misunderstood a paper it found, or dropped important evidence while composing its response. Each failure calls for a different fix. Looking only at the final answer makes it hard to know where to intervene. That’s why I’m interested in the connection between execution traces, error analysis, and evaluation. Recording what the agent did, identifying where it failed, and testing changes against a consistent set of tasks gives you a basis for judging whether your fixes work. This also shapes how I think about the order in which to learn agent engineering. Before trying another framework, it may be worth building an evaluation suite for the project you already have. Turn the failures you’ve encountered into test cases. Track what each change fixes and what it breaks. Read the CS329Z syllabus with those questions in mind, and its topics become concrete work you can apply to your own project. https://cs329z.stanford.edu/

    16 Sources

    @Diyi_YangThis fall @michaelryan207 @jyangballin and I are teaching a new course CS329Z "Engineering AI Agents" on how to build AI Agents from scratch. Come join us and learn how to build them 🤖
    @WilliamBarrHeldBiased take: If I had to pick a list of people who maximized the product of "Deep Expertise on Agents" and "Kind and Patient Teachers", I'd probably list these 3 people
    @michaelryan207🚨 New Course Announcement! This Fall @Diyi_Yang @jyangballin and I are teaching a BRAND NEW Stanford course on how to build AI Agents from scratch! Millions of users interact with AI Agents every day. Come join us and learn how to build them! 🧵 (1/5)
    @jyangballinRT @michaelryan207: 🚨 New Course Announcement! This Fall @Diyi_Yang @jyangballin and I are teaching a BRAND NEW Stanford course on how to…
    @achowdhery@Diyi_Yang Fun to see something quite like CS329A! Very cool!
    @StanfordAILabIf you want to learn how to engineer AI agents, these are the people you’d want to learn it from. They know the space inside and out and couldn’t be more excited to teach it. First time it’s running at Stanford this fall. @Diyi_Yang, @michaelryan207, @jyangballin
    @liweijianglwRT @Diyi_Yang: This fall @michaelryan207 @jyangballin and I are teaching a new course CS329Z "Engineering AI Agents" on how to build AI Ag…
    @Xudong07452910今天已经看到不少人在分享 Stanford 新开的 CS329Z: Engineering AI Agents。 不想再重复介绍课程，我反而更好奇： Stanford 到底把什么算作 2026 年的「Agent Engineering」？ 看完整 syllabus，RAG、Tool Use、MCP、Agent Framework 基本都放在前半程，更像 Agent 的基础能力。 真正让我注意的是后半段。 第一节课就把 Agent Engineering 的核心工程问题概括成： Decomposition、Data、Evaluation。 后面的课程也沿着这条线展开，从 Agent Data、Trajectory、Memory、Optimization，一直讲到 Evaluation、Coding Agent、Long-running Agent 和 Reliability。 作业设计也很值得关注。 第一个作业让学生从零搭 Agent；第二个直接变成 Evaluate an Agent：自己设计 benchmark、grader、LLM-as-Judge 和 error analysis。 Evaluation 甚至连续讲了两周。 一个很有意思的细节，是课程专门讲 pass@k 和 pass^k：前者看「多试几次能不能成功一次」，后者看「连续跑很多次能不能都成功」。 对 Agent 来说，这其实对应两种完全不同的可靠性。 Multi-Agent 那一节也挺克制。 一边讲 orchestration、handoff 和 collaboration，一边专门讨论协调失败和错误传播，reading 里甚至放了一篇： 《Don't Sleep on Single-agent Systems》 至少从这份 syllabus 看，「更多 Agent」并没有被默认等同于更好的系统。 所以我更愿意把这门课看成 Stanford 对 2026 年 Agent 技术栈的一次切片。 RAG、工具调用这些能力正在变成底座，后面更值得继续往下挖的，是 数据怎么来、系统怎么评、Agent 怎么优化，以及它能不能在复杂、长时间的真实环境里稳定跑下去。 这几个问题，感觉也会是接下来一两年 Agent 研究持续关注的方向。 https://cs329z.stanford.edu/
    @astaxie真的很感慨，斯坦福的课程更新速度太快了。 CS329Z 已经在教 AI Agent：RAG、Tool Use、MCP、Memory、Multi-Agent、Eval、Coding Agent…… 再看看很多大学生还在学习上一个时代、甚至已经被淘汰的东西。 强烈建议身边的大学生都去学学这门课，真的很值得。 https://cs329z.stanford.edu/
    @code_hiyougaIf you already know how to call models, connect tools, and build agents, Stanford’s new CS329Z: Engineering AI Agents is a useful place to check what you should learn next. Especially if your system runs and keeps gaining features, but you struggle to tell whether each change actually makes it better. The course starts with RAG, tool use, MCP, and agent frameworks, then covers memory, multi-agent systems, optimization, agent data, and evaluation. It also addresses safety and the reliability of agents running over extended periods. The assignments make this concrete: first, build a research-paper QA agent from scratch. Then design an evaluation suite for an existing agent, including benchmark tasks, code-based graders, an LLM-as-judge, and error analysis. I think this structure is particularly useful for people learning to build agents on their own. It’s easy to work through a feature checklist: connect more tools, add memory, try multiple agents. But every new component also introduces more ways the system can fail. Take a research assistant that gives the wrong answer. It might have failed to retrieve a key paper, misunderstood a paper it found, or dropped important evidence while composing its response. Each failure calls for a different fix. Looking only at the final answer makes it hard to know where to intervene. That’s why I’m interested in the connection between execution traces, error analysis, and evaluation. Recording what the agent did, identifying where it failed, and testing changes against a consistent set of tasks gives you a basis for judging whether your fixes work. This also shapes how I think about the order in which to learn agent engineering. Before trying another framework, it may be worth building an evaluation suite for the project you already have. Turn the failures you’ve encountered into test cases. Track what each change fixes and what it breaks. Read the CS329Z syllabus with those questions in mind, and its topics become concrete work you can apply to your own project. https://cs329z.stanford.edu/