Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 224G LLMs & Agents ★★★☆☆

Core course · LLMs & Agents

Apps With LLMs Inside

中文:LLM 应用开发

LLM application development: ship apps in sprints and understand model capability boundaries and the new programming paradigm.

Draft translation: official facts are checked; wording may change after native review.

3–4 units Winter 2027 Letter (ABCD/NP) ★★★☆☆
LLMProductProject

Course positioning

CS 224G is a project course that treats the LLM as a new CPU and explores how to build applications around it. It runs in two-week sprints with industry guest lectures, and suits people who want to ship a demo quickly.

What it covers

  1. LLM capabilities and limits: hallucination, context, cost
  2. Prompting: structured prompts, few-shot, role setting
  3. Tools and retrieval: function calling, RAG, external APIs
  4. Application architecture: frontend, backend, streaming, state management
  5. Fast iteration: sprints, user feedback, metrics
  6. Project: build an LLM-native app

Prerequisites

Programming ability; basic ML/LLM awareness; no research background required.

Assessment & workload

Two-week sprint assignments plus a final project and guest lectures. Check the current syllabus for details.

Who it's for

People who want to build LLM products or startups; product managers, designers, full-stack engineers.

Study advice

It complements CS 329Z: 224G is product cadence, 329Z is systems and eval. Define the user problem before choosing a model.

Related courses

Official course description

With ChatGPT, neural networks have had their Lisp moment. Conversation has become code and the model is the CPU for this ultimate programming language. A new universe of App development has opened up, and there are no guides for it, yet. This is a project course designed to explore the space of Apps built around LLMs, starting by playing with them, learning their limitations, and then applying a set of techniques to program them efficiently and effectively. Assignments are due on a two week "sprint" cadence to mimic a startup style environment. Guest lectures by area experts provide industry perspective.