Agentic AI for Product Teams: Build Workflows & Agents You Can Trust
John Whalen, PhD
Founder | Builds Agentic AI Systems
This course is popular
5 people enrolled last week.
Move Beyond Prompting. Build AI Systems You Can Trust.
In this course, you'll build AI systems around the work you actually do—systems you can inspect, improve, and trust.
Make sense of customer feedback. Explore product ideas with synthetic users and experts. Prepare recommendations grounded in evidence. Build workflows that follow your process and apply your standards.
You'll use AI as your personal tutor, your expert co-builder, and the engine that runs your workflows. Start with working examples and 40+ guides, then use your AI to understand, adapt, and build systems for your own work.
Trust comes from knowing how the work gets done. You'll learn to see what the AI did at each step, catch mistakes before they spread, and trace conclusions back to the interviews, documents, and data they came from. When something breaks, you'll know where to look.
You’ll develop systems thinking: break work into steps, connect them, and decide what to delegate, how to check results, and where your judgment belongs.
You'll be programming with words: describing what you need, then working with AI to build, test, and improve it. No programming background required.
Join a live cohort or learn at your own pace.
What you’ll learn
Build AI workflows around your work, test their reliability, and develop the judgment to know what to delegate and when to step in.
Use the guides and your AI tutor to develop systems thinking: define each step’s inputs, outputs, and checks, then connect the steps.
Co-build a workflow with AI, adapting working examples to your own process and standards.
Run your workflow with AI and inspect each step’s output to find problems and improve the system.
Create evaluations that check completeness, accuracy, and the standards your work requires.
Trace conclusions back to their sources so you can check the evidence behind a recommendation.
Add review steps that let AI check its work and bring you in when judgment is needed.
Decide when to use a skill, a single agent, or several specialized agents.
Design handoffs that give each agent the context it needs and pass usable work to the next.
Recognize when adding agents improves the result and when it adds unnecessary complexity.
Use synthetic users and experts to surface questions, challenge assumptions, and explore alternatives.
Evaluate where simulated perspectives are useful and where you need evidence from real customers.
Adapt a working example to your product, then apply its patterns to other workflows.
Identify work worth delegating and decisions that need human judgment.
Build a practical governance framework for quality, privacy, bias, and accountability.
Make the case to leadership using evidence from your workflows: time saved, quality improved, and capacity gained.
Learn directly from John
See all products from John
Who this course is for
Product managers and designers ready to move beyond prompting and start building AI workflows around their own work.
Researchers and insights professionals getting started with agentic workflows who want findings they can trace to the evidence.
Leaders and founders new to agentic AI who want to build workflows themselves and bring practical skills to their teams.
Prerequisites
Comfortable with AI basics
You use ChatGPT, Claude, or Copilot regularly at work. You write clear prompts and know what AI does well and where it fails.
Paid access to a supported AI tool
You'll need paid access to Claude, Codex, GitHub Copilot, Gemini, or OpenRouter. Our Getting Started guide helps you choose.
Be ready to learn a new working interface
You'll work in one of: ChatGPT app, the Claude app, VS Code, or Cursor. Allow time to learn your chosen tool; setup guidance is included.
What's included
Live sessions
Learn directly from John Whalen, PhD in a real-time, interactive format.
Live Interactive Sessions
Five 2-hour sessions where you build agents, design multi-agent workflows, and get feedback from John as you work. Bring your questions and learn alongside your peers.
Your Cohort’s Session Recordings
Catch up when you miss a session, or revisit the demonstrations, discussions, and feedback from your own cohort as you build.
1:1 Session with John (30 Minutes)
Get personalized guidance on your workflow, a build-or-buy decision, or how to bring what you’ve learned back to your team.
40+ In-Depth Guides
Load the guides into your AI assistant to use it as a personal tutor and expert co-builder. Get explanations tailored to your questions and help adapting examples, designing workflows, and troubleshooting. Topics include agent design, reliability, multi-agent systems, governance, and more.
Working Workflows You Can Customize
Run working examples with AI, inspect how each step works, and adapt them to your own inputs and standards. Then use the same principles to build new systems for your work.
Focused Lessons + Live Session Library
Learn through short, focused lessons that fit into your workday. Draw on recordings from past live sessions when you need a fuller explanation or demonstration.
Weekly Office Hours with John
Bring your projects, questions, and sticking points to John. Included throughout your live cohort, or for one month from enrollment with self-paced access.
Community of Agentic AI Builders
Connect with product managers, designers, researchers, leaders, and founders building AI systems. Share your workflows, learn from others, and exchange ideas.
Lifetime Access to Course Materials
Return to recorded lessons, past live sessions, projects, guides, and templates whenever you need them.
Maven Certificate of Completion
Share your achievement on LinkedIn or with your employer with a Maven-issued certificate of completion.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
9 live sessions • 21 lessons • 4 projects
Week 1
Session 1. Foundations & Tool-Based Agents
Nov
5
Session 1: Foundations & First Agent
Week 2
Session 2. Agents & Synthetic Users
Nov
12
Session 2: Building Agents That Work
Nov
11
Optional: Office Hour 1
Free resource
Beyond Prompting: Agentic AI for Customer Research
Understand the Shift from Prompting to Agentic Workflows
See how agentic AI can change the role of the researcher—from writing prompts to orchestrating autonomous research work.
Design AI Agents for Real Research Tasks
See how to structure and sequence agent behaviors to collect, synthesize, and analyze customer insights efficiently.
Identify High-Impact Use Cases for Your Team
Discover where agentic AI adds the most value for accelerating research and insight generation.
Schedule
Live sessions
2 hrs / week
Join a two-hour session each week to build with John and your peers. See workflows take shape, try the techniques yourself, and get feedback as you work through questions and problems.
Thu, Nov 5
5:00 PM—7:00 PM (UTC)
Wed, Nov 11
5:00 PM—6:00 PM (UTC)
Thu, Nov 12
5:00 PM—7:00 PM (UTC)
Projects
2-3 hrs / week
Start with a working example and adapt it to your own inputs and standards. Use AI as your co-builder to design and troubleshoot, then run the workflow and inspect the results. Extend your project as far as your goals and available time allow.
Focused Lessons and Guides
1-2 hrs / week
Use focused recorded lessons to prepare for sessions. Draw on the 40+ in-depth guides when they help your project, using your AI tutor for tailored explanations. Explore further as your goals and time allow.
Testimonials
John Whalen's Agentic AI for Research course is outstanding. My team and I took it to quickly upskill our entire practice and grasp what is possible with AI today. In a landscape where so many teams feel overwhelmed and anxious about AI adoption, John's incredibly thorough, practically applicable, and inspiring content left us feeling deeply empowered. The impact on our daily workflow has already been substantial. We are finalizing pipelines for primary and desk research, have rethought how we craft and deploy synthetic users, and recently started tinkering with strategic foresight tools. If you want to move your team past basic prompting into true agentic workflow orchestration, this is the course to take.
Sofia Linse Videla
Senior UX Research Manager at BrazeJohn is thoughtful about the pros, cons, benefits & limitations of AI. You'll learn about the potential of AI across the research cycle without being forced to drink the kool-aid. The course is wonderfully paced and worth every penny.
Julie Francis
Founder, BellaVia ResearchI can't recommend John's Maven courses enough. He teaches you how to be a true builder—someone who can design and implement AI-native tools and workflows into everyday UXR practice. I've completed both of his courses and regularly recommend them to peers because you genuinely level up your skills while learning practical, high-quality content you can apply immediately.
Ross Lordon, PhD
Staff UX Researcher, Microsoft AzureJohn is one of the most approachable instructors I have had. The volume of material is genuinely deep, and everything is loaded into NotebookLM, so you keep access even after the course ends—that noise reduction alone is worth the price. The biggest shift for me was structural. I came in with some Claude skills and systems already built, but week by week I realized how many of my approaches were wrong because I did not actually understand how LLMs worked under the hood. After the course, I have rebuilt most of my workflows. I now know how to break a task into discrete steps, check the output at each stage, and pinpoint exactly where things fail. This course got me to work like an architect instead of building on vibes.
Kenny Mathew
Principal UX Researcher at PrintifyBest course on AI implications for consumer and market research. You get useful learnings and tools you can use right away while experiencing, first hand, the future that is already here.
Esteban Ribero
Research Leader at TikTokThis course has (more than anything I've done or learned) completely changed the way I interact with AI. I cannot recommend this course enough to anyone. John teaches things very simply through first principles, has incredibly clean curriculum, and spends time with the students to make sure we completely understand material before moving on. I feel like I've learned more in 4 weeks than the last 2 years about how to use AI, and feel wildly optimistic about using it moving forward as a Product Designer!
Albert Packer
Product Design Manager, MasterControl
Earn Your Maven Certificate of Completion
Share your achievement—and the AI workflows you've learned to build.
Complete Agentic AI for Product Teams, live or self-paced, to earn your Maven certificate of completion. Share it on LinkedIn or with your employer alongside examples of the workflows you've built.
Go Further: Become a Certified Agentic Research Specialist
Combine practical AI research skills with the ability to build custom agentic workflows.
Earn our Certified Agentic Research Specialist (CARS) credential by completing both courses:
Agentic AI for Product Teams: Design, build, and evaluate custom agentic workflows tailored to your work.
AI for Customer Research: Evaluate and use AI research platforms, with the judgment to know where they help and when human involvement is essential.
This course stands on its own. Together, the courses develop your ability to choose existing tools, build custom workflows, and evaluate the results. Take them in either order.
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$1,199
USD