Agentic AI

Prospective Students

• Join the 32K+ global community of Agentic AI MOOC and sign up for the course: Signup Form
• Join our LLM Agents Discord to stay updated
• Check out the Agentic AI Summit to learn more about the latest developments in agentic AI.
• This course is built upon the fundamentals from the Fall 2024 LLM Agents MOOC and Spring 2025 Advanced LLM Agents MOOC.

Course Staff

Instructor	(Guest) Co-instructor
Dawn Song	Xinyun Chen
Professor, UC Berkeley	Research Scientist, Meta

Guest Speakers

Yann Dubois Member of Technical Staff	Yangqing Jia VP, Al System Software	Jiantao Jiao Director of Research & Distinguished Scientist
Weizhu Chen Technical Fellow & CVP	Noam Brown Research Scientist	Sida Wang Research Scientist
James Zou Professor	Clay Bavor Co-Founder	Oriol Vinyals VP, Research
Peter Stone Chief Scientist at Sony Al, Professor at UT Austin

Class Time and Location

Lecture: 3-5pm PT Monday (starts Sep 15, 2025)

Course Description

Agentic AI is the new frontier and poised to transform the future of our daily life with the support of intelligent task automation and personalization. In this course, we will first discuss fundamental concepts that are essential for Agentic AI, including the foundation of LLMs, reasonsing, planning, agentic frameworks and infrastructure. We will also cover representative agent applications, including code generation, robotics, web automation, and scientific discovery. Meanwhile, we will discuss limitations and potential risks of current LLM agents, and share insights into directions for further improvement.

Syllabus

Completion Certificate

Course completion certificates will be awarded to students based on the rules of the following tiers. All assignments are due January 31th, 2026 at 11:59PM PDT. To receive your certificate, please complete the Certificate Declaration Form by January 31st, 2026 at 11:59PM PDT.

Trailblazer Tier:

• Complete all lecture quizzes associated with each lecture
• Pass the Learning & Sharing Assignment

Mastery Tier:

• Complete all lecture quizzes associated with each lecture
• Pass the Learning & Sharing Assignment
• Submit a project to the AgentX-AgentBeats competition

Legendary Tier:

• Complete all lecture quizzes associated with each lecture
• Pass the Learning & Sharing Assignment
• Become a winner or finalist at the AgentX-AgentBeats competition

Honorary Tier:

• For the most helpful/supportive students in Discord!
• Meets all other coursework requirements of Mastery Tier

Earn Your Certificate in 3 Steps

STEP 1. Complete all of the coursework for your desired tier.

• All assignments are due January 31th, 2026 at 11:59PM PDT
• We track your progress throughout the course via your email. Please use the same email address when submitting all coursework
• All assignments should send a Google Forms confirmation email on successful submission

STEP 2. Complete the Certificate Declaration Form.

• In order to earn the certificate, all students will need to complete a Certificate Declaration Form by January 31st, 2026 at 11:59PM PDT

STEP 3. Certificates will be sent to your email in Spring 2026!

NOTE: You can only earn one certificate from this course (not counting Honorary Tier). Completing the assignments associated with this course in order to earn a Completion Certificate is completely optional. You are more than welcome to just watch the lectures and audit the course!

Coursework

All coursework will be released and submitted through the course website.

Quizzes

All quizzes are released shortly after the corresponding lecture and are graded on completion. Please remember to complete the quiz each week. Although it’s graded on completion, we encourage you to do your best. The questions are all multiple-choice and there are usually 5 per quiz. The quizzes will be posted in the Syllabus section.

Learning & Sharing Assignment

Create public social media post(s) based on your learning from the Agentic AI MOOC or your project from the AgentX-AgentBeats competition. You may choose one of the formats below. You must publish your content on one or more of the following platforms only: LinkedIn, X (Twitter), Instagram, or TikTok.

Please be sure to include a link to the MOOC website in your post, thread, or video description, use the hashtag #AgenticAIMOOC and #AgentBeats, and—if you’re posting an X/Twitter thread—please tag @BerkeleyRDI.

Deadline: January 31st, 2026 at 11:59PM PT

Submission Format Options:

Option 1: Long‑Form Article/Post

• Platform: LinkedIn
• Summarize insights from one or more lectures or write a reflective postmortem on your learning experience in the MOOC
• Alternatively, write about your AgentX-AgentBeats submission, including your motivation, technical approach, challenges, and lessons learned

Option 2: Short‑Form Social Content Bundle

• An X (Twitter) thread (minimum 5 threads) summarizing key ideas from the MOOC or your AgentX-AgentBeats project; the tweet thread needs to include at least one original infographic you created based on MOOC content (designed to be engaging and shareable on social)
• One short‑form video (30–90 seconds) posted on X, Instagram, or TikTok, explaining a concept, insight, or demo related to what you learned or built for the MOOC and/or the AgentBeats competition

This is an effort‑based assignment and will be graded Pass / No Pass (P/NP). Creativity, clarity, and thoughtful engagement with the material are encouraged.

Submit your assignment via the Learning & Sharing Assignment Submission Form.

AgentX-AgentBeats Competition

More information about the project can be found at AgentX-AgentBeats. The submission deadline is January 31th, 2026.