Build Multi-Agent Applications - A Bootcamp
4.6 (42)
7 Weeks
·Cohort-based Course
Design, develop, deploy, and demo an LLM agent application in 7 weeks!
Build Multi-Agent Applications - A Bootcamp
4.6 (42)
7 Weeks
·Cohort-based Course
Design, develop, deploy, and demo an LLM agent application in 7 weeks!
OUR STUDENTS CAME FROM
Course overview
Mentorship Program to Help You Build an Agent-based MVP
NOTE 1: The price shown on this page is in _USD_.
NOTE 2: Check out the incentive program on this page for ways to save money.
You can book me to talk about this bootcamp or anything else AI / career / startup related:
https://calendly.com/amirfzpr/20min-ama
🟢 WHAT WILL I BE ABLE TO BUILD IN THIS BOOTCAMP?
You’ll build a functional application powered by LLM agents to automate a workflow of your choice. Along the way, you'll learn to design agent workflows, and integrate required tools. By the end of the program, you'll have a working application ready to showcase in a public demo.
You can see this playlist for examples of what previous students built: https://tinyurl.com/llm-agent-demos
🟢 HOW WILL YOU HELP ME BUILD APPS LIKE THESE IN JUST 7 WEEKS?
This program is all about learning by doing. You do a real project, applying concepts you learn about AI agents with our expert guidance. Specifically:
👨🏽🏫 1:1 sessions with the us to help you think through bigger picture questions
👨🎓 Async and sync sessions with a dedicated mentor for constant support, code reviews, and real-time feedback
We also provide the "agents playbook" a step by step guide for building agentic systems with lots of hints, tips, and resources.
🟢 OK! THAT DOES SOUND FUN, BUT HOW DO I KNOW IF I HAVE THE PRE-REQUISITES?
We will provide tutorials and curated material that can help you build regardless of how you want to approach it (coding, vibe coding, or no-code tools). So what you really need to be successful in this bootcamp is a lot of desire to build and not much else. You could also leverage our freely available playbook to prep beforehand and come ready (scroll down on this page).
🟢 HMM! SO I DON'T NEED TO BE A CODER?
If you are, then your freedom to build what you want will definitely increase. However, we have seen people do successful projects during the bootcamp using no-code tools like N8N, LangFlow, Dify etc. We have also seen folks "vibe coding" using Windsurf, Cursor, Co-pilot etc.
There are options! The question is, are you ready to build?
🟢 I SEE! SO, WHAT SHOULD I EXPECT TO HAPPEN DURING?
Think about it like this (since we're developing a product here, eh?): This is a 3-sprint product dev + 1 week of prep for the public demo.
🖌️ SPRINT 1 - DESIGN (weeks 1 & 2)
🔨 SPRINT 2 - DEVELOP (weeks 3 & 4)
🚢 SPRINT 3 - DEPLOY (weeks 5 & 6)
🎭 PUBLIC DEMO (week 7)
In each sprint, you communicate your progress or blockers on Slack, you collaborate on your designs / code on GitHub, you show up to provide weekly project updates and get feedback, and finally you do an end of sprint demo.
🟢 OK! HOW WOULD I KNOW IF I'M MOVING IN THE RIGHT DIRECTION?
You will get feedback async via Slack and other platforms we use, and also you join weekly group office hours, and when you need you can book the mentors for a 20 min 1:1 call.
In addition, each sprint will wrap up with a "sprint demo" where you can show what you've done up to that point, and your peers and the mentors will provide feedback.
🟢 WHAT IF I DON'T HAVE A PROJECT IDEA?
We provide a default project and 3 series of tutorials that provide various ways that project can be implemented using:
🤃 coding,
🤄 vibe coding, and
🤅 no-code tools.
Each series is led by one of our mentors and will meet live for an hour every week to build together and you can follow along. At the end of each session, the mentor would point out ways that you can add to the project and make it your own. If you follow through and engage it's likely that you will end up with an interesting spin on the default project that you can show off in the public demo.
🟢 COOL! I'M EXCITED TO GET STARTED, AND A DISCOUNT WOULD REALLY SWEETEN THE DEAL!
Glad to hear that! There are a few options:
🧑🏿🤝🧑🏼 You can find a buddy or colleague and sign up together. (20% off 2-9 seats | 25% off 10+ seats)
✴️ We often share discount codes with communities (including AISC members - reach out to community@ai.science if you're not part of our slack). So, check in with the communities you are part of.
📆 We regularly hold events and info sessions where we share flash sales discounts valid for a day or two. Join the mailing list on this page to receive notifications about those.
👨🏽🏫 You can apply to our Incentive Program that provides up to 75% refunds (not discounts). Apply here: https://forms.gle/YnvsoREuEX35DAxv8
This course is for you if...
01
You want to build an agentic MVP to test the feasibility of your startup idea.
02
You want to build an agentic MVP to explore the new feature you want to add to your existing product
03
You want to build an agentic MVP to demonstrate your skills for career progression purposes.
Prerequisites
Python Coding
Controlling the behavior of your agents often requires coding to include various tools, memory, or orchestration.
No-code App Building
If you don't want to code, you can use no-code agent studios. We will provide specific resources but general familiarity is useful.
Coding co-pilots
If you are planning to code (or vibe code), familiarity with one of the coding assistants (GitHub copilot, cursor, etc), is helpful.
At the end of this course you will ...
Understand and utilize the core ingredients of multi-agent LLM systems
Grasp how multiple LLMs can collaborate with each other, get feedback from or assign tasks to humans, ad use tools to tackle complex problems
Understand the role of evaluation in building a robust agentic system
So, you build a system but does it work? How can it be improved? Out of 100 things you can change, which one is more important to focus on?
Leave with a worked out muscle of experimentally developing an agentic system
Start from a workflow, design an agentic system for it, build it, evaluate it, find test cases to fix, repeat. You do this multiple times in the 7 weeks and those reps are how you build the mental muscle!
What’s included
Live sessions
Learn directly from Amir Feizpour, PhD in a real-time, interactive format.
Learn the concepts in 38 Interactive Live Sessions
Participate in lectures, tutorials, and group activities to learn the basics and build more efficiently
Build an Agentic AI App in our Structured 3-Sprint Program
Follow a clear 3-sprint structure helping you design and build, with extra dose of accountability from instructors, TAs, and peers.
Get Personalized Feedback in 1 on 1 Mentorship Sessions
Work on your project and meet with program mentors (instructor and TAs) regularly to get deeper in anything that requires clarification
Connect with Potential Collaborators & Users in Public Demo
Show off your work and connect with our community including invited guests (corporate directors, experienced founders, angel investors)
Lifetime 1 on 1 access to Amir (slack and ama calls)
Message Amir via slack with questions, or book him to talk about any topic (startups, career, AI etc) on calls even well beyond the bootcamp
Lifetime Access to Agents Playbook
Build using our playbook including resources and a step by step guide for building an agentic application. Receive version update notifs.
Lifetime Access to Community of Peers
Become part of AISC Slack community (5000+ AI researchers, engineers, and founders) for all your AI needs
Lifetime Access to Material
Go back to the recordings of the live sessions and other material whenever you need them.
Free Transfer to a Future Cohort
Use the option to re-do the bootcamp if life is getting in the way of you extracting the most out of the program
Commercialization Advice
Book Amir to discuss how you can take your product to market after the public demo, including introduction to potential customers / partners
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
Week 1
Build an Agentic Product Demo
Jul
14
Lecture: You Probably Don’t Need Multi-Agents [Leveraging 0 to 1 Agents for Well-Scoped, High-Impact Use Cases]
Jul
16
Coding Tutorial: Use Case Identification and Creating the First Evaluation Set
Jul
16
Vibe Coding Tutorial: Use Case Identification and Creating the First Evaluation Set
Jul
17
No-code Tutorial: Use Case Identification and Creating the First Evaluation Set
Jul
18
Guest Lecture - Community Event
Jul
20
Small Group Feedback on Use Case
Week 2
Jul
21
Lecture: Your Only Silver Bullet [Using Error Analysis as the Most Effective Path to Agent Refinement]
Jul
23
Coding Tutorial: Your First Agent (proof of concept) in 2 Days
Jul
23
Vibe Coding Tutorial: Your First Agent (proof of concept) in 2 Days
Jul
24
No Code Tutorial: Your First Agent (proof of concept) in 2 Days
Jul
25
Guest Lecture - Community Event
Jul
27
Sprint 1 - Demo
Week 3
Jul
28
Lecture: Architecture or Anarchy [Deriving Multi-Agent Architectures from Use Case Decomposition and Evaluation-Oriented Design]
Jul
30
Coding Tutorial: Task Decomposition, Agent Design & Implementation
Jul
30
Vibe Coding Tutorial: Task Decomposition, Agent Design & Implementation
Jul
31
No Code Tutorial: Task Decomposition, Agent Design & Implementation
Aug
1
Guest Lecture - Community Event
Aug
3
Small Group Feedback on Agent Design
Week 4
Aug
4
Lecture: Surfing on Made-Up Data [Generating Synthetic Evaluation Sets for Robustness and Failure Mode Discovery]
Aug
6
Coding Tutorial: Augmenting Your Evaluation Dataset to Improve (Multi-) Agent Performance
Aug
6
Vibe Coding Tutorial: Augmenting Your Evaluation Dataset to Improve (Multi-) Agent Performance
Aug
7
No-Code Tutorial: Augmenting Your Evaluation Dataset to Improve (Multi-) Agent Performance
Aug
8
Guest Lecture - Community Event
Aug
10
Sprint 2 - Demo
Week 5
Aug
11
Lecture: Agent Refinement at Scale [Automating Evaluation Pipelines with LLM-Assisted Scoring and Expert Review]
Aug
13
Coding Tutorial: Using LLM-as-a-Judge + Expert Feedback to Improve (Multi-) Agent Performance
Aug
13
Vibe Coding Tutorial: Using LLM-as-a-Judge + Expert Feedback to Improve (Multi-) Agent Performance
Aug
14
No-Code Tutorial: Using LLM-as-a-Judge + Expert Feedback to Improve (Multi-) Agent Performance
Aug
15
Guest Lecture - Community Event
Aug
17
Small Group Feedback on Agent Performance Evaluation
Week 6
Aug
18
Lecture: Fewer Agents, More Insight [Simplifying Agentic Workflows to Enable Scalable Observation and Evaluation]
Aug
20
Coding Tutorial: Making the Agentic System Robust by Replacing Low-performing Agents with High Quality Components
Aug
20
Vibe Coding Tutorial: Making the Agentic System Robust by Replacing Low-performing Agents with High Quality Components
Aug
21
No-Code Tutorial: Making the Agentic System Robust by Replacing Low-performing Agents with High Quality Components
Aug
22
Guest Lecture - Community Event
Aug
24
Sprint 3 - Demo
Week 7
Aug
25
Lecture: Showing Off the Controlled Chaos [Demonstrating Agent Behavior with Observable Execution, Evaluation Metrics, and Justified Outputs]
Aug
29
Public Demo Day
Post-course
Book Amir to Discuss How to Commercialize your Project after the Bootcamp
4.6 (42 ratings)
What students are saying
Agents Playbook v2506
This document serves as a guide for developing your agentic product.
It is designed to help you systematically define your product's goals, requirements, and implementation strategy.
By working through each section, you will refine your product idea, identify potential challenges, and develop a comprehensive plan for building and deploying your solution.
Get this free resource
Frequently Asked Questions
Meet your instructor
Amir Feizpour, PhD
Amir Feizpour, PhD
10 yrs in NLP, Founder of AISC - Community of 5k AI devs and founders
Amir is the founder of Aggregate Intellect, helping clients leverage LLM systems to augment their business workflows. Prior to this, Amir was an AI Product Lead at Royal Bank of Canada and built a document processing platform used by internal lines of business. Amir held a research position at University of Oxford conducting experiments on quantum computing resulting in high profile publications and patents. Amir holds a PhD in Physics from University of Toronto. Amir has also founded and grown a global community of 5000+ engineers, researchers, and founders gathered around topics in natural language processing.
Join an upcoming cohort
Build Multi-Agent Applications - A Bootcamp
Cohort-2507
$949
Dates
Payment Deadline
Course schedule
10 hours per week
Fridays & Sundays
12:00pm - 1:00pm ET
We will have guest lecturers (optional) on Fridays, and project office hours on Sundays.
1 on 1 Mentorship Sessions
30 min, Book on demand
You can book time with the mentors (business, product, implementation) to have 1 on 1 conversation about your project once or twice a week
Sprints + Public Demo
3x2-week Sprints
You demo your progress every other week as you build up towards preparing for the final public demo with invited guests (experienced founders, corporate directors, and investors)
Stay in the loop
Sign up to be the first to know about course updates.