Skip to content
InfratoApp

Stanford University · Course

Engineering AI Agents (CS329Z)

Engineering AI Agents (CS329Z) on Stanford Online teaches how to build agentic systems, from simple LLM pipelines to compound AI systems to autonomous agents: choosing problems, decomposing them, selecting components, curating data and building evaluations.

Open at Stanford University ↗Common questions

Who it suits

  • Engineers with an NLP or AI background who want to design agentic systems, not just call a model.
  • Teams that need to reason about the trade-offs in building compound AI systems.

What it covers

  • The shift from monolithic language models to compound AI systems with LLMs, retrievers, tools and optimisers.
  • Picking problems to focus on, and decomposing them.
  • Selecting components, and collecting and curating data.
  • Building evaluations, and reasoning about design trade-offs.

Before you start

  • Stanford lists a conferred bachelor’s degree with an undergraduate GPA of 3.0 or better.
  • Background in natural language processing: any of CS224N, CS224V, CS336 or CS221, or equivalents.

Common questions about Engineering AI Agents (CS329Z)

How long is it?
Stanford lists 10 weeks at 9 to 15 hours a week, and 3 academic units.
What do I need first?
Any of CS224N, CS224V, CS336 or CS221, or an equivalent NLP background.
Can I enrol any time?
Enrolment is only open during set periods, and an application is needed for graduate courses, so check the page for the current dates.

More like this

Keep learning on Infrato

Where this comes from

Written from Stanford University’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Stanford University and this is not an endorsement.