Stanford University · Course
Agentic AI (CS224V)
Agentic AI (CS224V) on Stanford Online is a ten-week graduate project course, with rigorous lectures, on the principles and research behind agents powered by large language models. Students do a substantial quarter-long project, either on methodology research or on building a novel agent in a domain of their choice.
Who it suits
- Engineers with NLP or deep learning coursework who want to build or research LLM agents.
- Learners who prefer a project-driven course to lectures alone.
What it covers
- Reducing hallucination in question-answering and task-oriented agents with retrieval-augmented generation and formal task descriptions.
- Hybrid knowledge reasoning over databases, knowledge bases and unstructured text.
- AI-driven knowledge curation and discovery for scientific research.
- Improving the accuracy and efficiency of long-horizon agents, and the interpretability of decision-making agents.
Before you start
- Stanford lists a conferred bachelor’s degree with an undergraduate GPA of 3.0 or better.
- One of CS224N, CS224U, CS224S or a languages-to-information course such as LINGUIST 180/280 or CS124.
Common questions about Agentic AI (CS224V)
- How long is it?
- Stanford lists 10 weeks at 10 to 20 hours a week, for 4 academic units.
- Is there a project?
- Yes. Stanford describes a substantial quarter-long project as the core of the course.
- Is it open for enrolment?
- Stanford’s page said it was not open at the time of reading and listed it as possibly offered in autumn. Check the page for current availability.
More like this
Keep learning on Infrato
- Path: AI for software developers
- Tool: Claude Code
- More from Stanford University: all Stanford University listings in the directory
- Explore all AI courses
Where this comes from
Written from Stanford University’s own pages, read on 2026-10-14. 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.