Stanford Root

Schedule

Stanford Root

Schedule

CS 329Z

Engineering AI Agents

UNITS:3
GRADING:Letter or Credit/No Credit
LEVEL:Graduate
GER:—

The shift from monolithic language models to compound AI systems - systems with multiple interacting components including LLMs, retrievers, tools, and optimizers -n represents a fundamental change in how AI applications are built for people. This course teaches students how to engineer agentic systems: the full spectrum from simple LLM pipelines to compound AI systems to autonomous agents. Students will learn to pick what types of problems to focus on, decompose problems, select appropriate components, collect and curate data, build evaluations, and reason about the design tradeoffs that arise when building these systems in practice. Students first build core components (RAG, tool use, agent loops) from scratch, then learn how frameworks like DSPy abstract these patterns. Through three fully applied homework assignments and a quarter-long project, students will gain hands-on experience building, optimizing, and evaluating agentic systems.

Syllabus for selected term:
View Autumn 2026 Syllabus

Sections

1 Term
Lecture 1Open
ID: 27855
0 / 70 enrolled
DAYS:Monday, Wednesday
TIME:1:30 PM – 2:50 PM
LOCATION:Packrd101
INSTRUCTOR:
Yang, Diyi, Ryan, Michael
3units

CS 329Z: Engineering AI Agents

3 units · Letter or Credit/No Credit

The shift from monolithic language models to compound AI systems - systems with multiple interacting components including LLMs, retrievers, tools, and optimizers -n represents a fundamental change in how AI applications are built for people. This course teaches students how to engineer agentic systems: the full spectrum from simple LLM pipelines to compound AI systems to autonomous agents. Students will learn to pick what types of problems to focus on, decompose problems, select appropriate components, collect and curate data, build evaluations, and reason about the design tradeoffs that arise when building these systems in practice. Students first build core components (RAG, tool use, agent loops) from scratch, then learn how frameworks like DSPy abstract these patterns. Through three fully applied homework assignments and a quarter-long project, students will gain hands-on experience building, optimizing, and evaluating agentic systems.

Offered in Autumn 2026 at Stanford University.

Autumn 2026 sections

  • Lecture — Monday Wednesday 1:30 PM – 2:50 PM — Packrd101 — Yang, Diyi, Ryan, Michael (Graduate)

More CS courses

  • CS 329H: Machine Learning from Human Preferences
  • CS 329M: Machine Programming
  • CS 329R: Race and Natural Language Processing (CSRE 329R, LINGUIST 281A, PSYCH 257A)
  • CS 329S: Machine Learning Systems Design
  • CS 329T: Trustworthy Machine Learning: Building and evaluating agentic systems
  • CS 329X: Human Centered NLP (CS 129X)
  • CS 331X: AI for Algorithmic Reasoning and Optimization (MS&E 331)
  • CS 333: Algorithms for Interactive Robotics
  • CS 334: Robots and Arts: Creative Applications and Projects (TAPS 334R)
  • CS 336: Language Modeling from Scratch
  • CS 337: AI-Assisted Care (BIOE 277, MED 277, PSYC 278)
  • CS 338: Aligning Superintelligence (MS&E 338)

All CS courses · All departments