AI Agent Design
4.8 (77)
3 Weeks
·Cohort-based Course
Agents are transforming AI… and work itself. Start understanding and building with them now and get ahead. No coding required.
AI Agent Design
4.8 (77)
3 Weeks
·Cohort-based Course
Agents are transforming AI… and work itself. Start understanding and building with them now and get ahead. No coding required.
Previous clients include
Course overview
Innovate and Automate with the Power of AI Agents
In the next 12 months, AI agents will start to completely transform the workforce. AI models won’t just write things for us — they will make decisions for us, perform entire projects in our browsers, and handle our communications.
Agents will shift everything we thought we knew about how AI works — again. We’ve been working with generative AI since 2019, and this is the biggest shift we’ve seen since the original GPT-3 was released in 2020.
This course will keep you relevant in this new world by developing evergreen practices working with and designing with agentic patterns, frameworks, and tools like ReAct loops, multi-agent systems, graph-based methods and beyond.
We will teach you principles to guide you in targeting most promising agentic applications and provide direct practice building actions into existing AI frameworks, based on our first-hand experience building early versions of these tools in production. And we will be joined by CEOs of AI Agent services MultiOn and Promptly.
You will walk away understanding how the AI ecosystem will evolve, with applications to different industries and use cases. You'll also be able to demonstrate your competency through hands-on demos you will build with no-code tools.
Along with live class sessions, the course includes 1:1 coaching sessions and flexible office hours to ensure each student gets deeply personalized support in designing their agentic applications.
Who is this course for
01
Innovation and Strategy Leads who need think outside the box and push the boundaries of your organization's strategy.
02
Product Managers who need to lead and collaborate with technical teams on generative and agentic products and features.
03
Designers who need to understand what users will expect from generative and agentic products.
What you’ll get out of this course
Master design patterns for AI agents:
Make key decisions in designing your AI agent application based on emerging patterns like ReAct loops, multi-agent systems, graph-based methods, and more.
Forecast the AI agent landscape:
Gain a clear understanding of the current capabilities of AI agents and how they will evolve in your industry.
Build your own agents:
Create an on-rails agent pulling insights from your data and learn how to integrate function calling and outside workflows using state-of-the-art no-code methods.
Create a truly unique innovation portfolio:
You'll leave with a huge toolkit of new capabilities and targeted resources you can start using immediately, with proof that you can leverage them.
Access a treasure trove of resources:
Gain access to step-by-step instructions, async lectures, training guides and decision-making worksheets to continue growing your expertise long after the end of the course.
What’s included
Live sessions
Learn directly from Jeremy Kirshbaum & Lev Gorelov in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
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
21 lessons • 3 projects
Week 1
Week 1: The Landscape: The Present and Near Future of AI Agents
Async: Creating first automated content generator in Promptly
Week 2
Week 2: The Agent Stack: Tool Use, Memory, Routing, and Beyond
Async: Hands-on practice implementing function calling and outside workflows
Week 3
Week 3: Design Patterns For AI Agent Applications
Async: Building a workflow with AI agents
Bonus
Glossary
Hire us to bring your project idea to life!
4.8 (77 ratings)
What students are saying
Meet your instructor
Jeremy Kirshbaum
Jeremy Kirshbaum
Founder of generative AI consultancy Handshake. Develops AI systems for corporates, governments, and non-profits (give.org) and research groups (iftf.org). Has worked with executive teams and boards at companies like Walmart, Kellogg Company, Deloitte, and many others to help them understand the future of generative AI and emerging technologies. He is writing a book about senior leadership and generative AI agents with Bob Johansen, on shelves Q2 2025 through Berrett Koehler Publishers. He loves poetry (the art form, because it is beautiful) and the Poetry the package manager (for Python, because it actually does dependency resolution).
Lev Gorelov
Lev Gorelov
Research Director at Handshake, consultant and generative AI educator working globally in Moldova, Nigeria, the US, and beyond to help organizations and individuals upskill in generative AI. No-code software ninja, master in Science of Social Work and academic studying the intersection of computational philosophy and social theory.
Course schedule
3-5 hours per week
Tuesday
9:00 A.M. - 10:30 A.M. PT
Synchronous zoom lecture on Tuesday, focusing on the conceptual backbone of AI agent functionality and applications. Recordings of class will be available soon after its completion.
Weekly projects (async)
3 hours per week
An async walkthrough will guide you in building functional prototypes of AI Agents. You will get to shape the project deliverable. Lecturers will be available by email, during office hours and via one-on-one sessions throughout the week for questions and support.
Tuesday & Thursday
10:30 A.M. - 11:30 P.M. PT
Optional office hours where you can ask questions and receive personal guidance on developing your AI applications.
1:1 Coaching
Up to three sessions
Schedule 1:1 coaching time with instructors for individualized help with your hands-on projects, privately thinking through a use-case, or whatever else you need.
Frequently Asked Questions
Join the waitlist
And receive exclusive screenshot instructions on creating cryptocurrency and AI apps
