NYU CDS · FALL 2026
Agentic AI Workshop
Build an agent you can explain.
Watch an agent choose a tool and see what runs it. Then build one around a problem you care about!
Register by Monday, October 5 at 5 PM ET.
Looking for last year’s workshop? Explore 2025THE COURSE
Build your own agent over four Thursdays.
From the first tool call to a project you can share. Sessions 1–3 are required. Demo Day is highly encouraged, even if you don’t present.
- THURSDAY
SESSION 1 Required
Agents and harnesses
What an agent is, when to use one, and the machinery that runs its tools, context, and decisions.
5:30–7 PM ET - THURSDAY
SESSION 2 Required
Agents beyond chat
Give an agent an interactive surface. Explore generated interfaces, typed decisions, and experiments with feedback.
5:30–7 PM ET - THURSDAY
SESSION 3 Required
Multi-agent systems
Decide when to divide work, what each agent needs to know, and how to coordinate handoffs and review.
5:30–7 PM ET - THURSDAY
SESSION 4 Highly encouraged
Demo Day
Show what you built. Discuss your project with classmates and industry guests, and learn from their questions.
5:30–7 PM ET
HOW WE LEARN
Follow the agent’s decisions in class.
Keep your laptop closed and ask questions as we predict what happens next. Build your own between sessions.
Slides and starter code support your project. You’ll be encouraged to share your agent through the class app store.
60 minutes of material + 30 minutes of Q&A
Technical storytelling through slides, live demonstrations, and conversation.
About 1–2 hours of development each week
Start with a research question, a recurring task, or a personal workflow. Make a small version that works, then develop it each week.
Friday office hours
Bring a broken tool call, a confusing code path, or an idea that feels too big. We’ll help you find the next step. Joining details will be shared with registered students.
YOUR BUILDING MATERIALS
Starter materials for your own project.
The public course repository, slides, and starter code are coming soon. Their links will appear here when available.
2026 public repository
The home for this year’s course materials.
Session slides
The explanations and visuals from class.
Starter code
Code to run, inspect, and make your own.
Class app store
Publish your project and explore what others in the workshop build.
SHOW WHAT YOU BUILT
Meet other builders through your project.
Share your work with classmates and industry professionals from OpenRouter, Amazon, Google, and startups.
Judges will select students whose demos they like for coffee chats. Come to show your project, give feedback, or see what everyone made.
FROM THE 2025 CLASS
Get a feel for the room.
Last year, we built a personalized newspaper with MCP. These highlights offer a look at the examples, questions, and discussions.
YOUR INSTRUCTOR
Adi Singhal
Former CDS student and founder of the NYU Data Science Club. Adi teaches through examples, demonstrations, and plenty of questions.
Connect on LinkedInBefore you join
Who is the workshop for?
Members of the CDS community, including students and alumni. Undergraduates should have completed DS-UA 112. Attend the first three sessions and plan for weekly project work.
Where do we meet?
CDS 7th Floor Open Space, 60 5th Ave, between 12th and 13th Streets, New York City. Thursdays, 5:30–7:00 PM ET.
The workshop is in person. Contact the organizer about individual attendance questions.
What will I need?
Time to build between sessions and curiosity in the room. Slides and starter code are coming soon. Registered students will receive inference access through OpenRouter.
How do I register or ask a question?
Register by Monday, October 5 at 5 PM ET. The registration form requires Google sign-in.
Contact the workshop organizer about form access, attendance, or other questions.
FROM THE REGISTRATION FORM
Who signed up?
133 responses as of October 1, 2026.
39EmberAPI tinkerersMy first model call works. Once I add tools and state, I want to understand how the whole agent fits together.
What excites me
Turning an API experiment into something another person can use.
What worries me
Losing the thread when the system grows or an API fails.
What I want to leave with
A useful agent I can explain from the first request to the final result.
37PatchCopilot buildersA coding assistant can help me build fast. I want to understand the decisions behind what it built.
What excites me
Making a project of my own and seeing what other builders try.
What worries me
Having a working demo I cannot explain when someone asks how it works.
What I want to leave with
Confidence showing what I changed, why I changed it, and what happened.
16SprigCurious explorersI use AI through chat. Show me the moment it takes an action, and I can start to imagine building my own.
What excites me
Watching a small tool call become a result I can actually use.
What worries me
Getting lost when the vocabulary moves faster than the example.
What I want to leave with
A first working agent and a clear idea of what to learn next.
15NimbusWorkflow dreamersI have a list of tasks I would love to hand off. I need help choosing one I can finish.
What excites me
Turning an everyday routine into a useful application.
What worries me
Starting too big and spending my time on setup instead of the idea.
What I want to leave with
One purposeful project I can keep improving after class.
14SocketTool connectorsI have connected tools with MCP. Now I want to see what makes them part of a complete agent.
What excites me
Following a tool result through the next decision in a real workflow.
What worries me
Knowing the pieces without understanding how they work together.
What I want to leave with
A complete system whose design choices I can explain.
12ChorusSystem orchestratorsI have had agents working together. I want to know when the extra coordination is worth it.
What excites me
Looking closely at a handoff and seeing what it improves.
What worries me
Adding another agent because it sounds impressive, even when it makes the task harder.
What I want to leave with
A way to judge when several agents help and when one is enough.
NYU CDS · AGENTIC AI WORKSHOP 2026
Bring your curiosity and build an agent of your own.
Register by Monday, October 5 at 5 PM ET.