Staging environment

Agentic AI for Research: Build Custom Workflows & Synthetic Users

John Whalen

AI Research Expert | Johns Hopkins PhD

Move Beyond Prompting. Build Agentic Research Systems.

You've been prompting ChatGPT and Claude. Maybe you've also used Listen Labs, or Marvin. But you've hit two ceilings: prompting stops when the prompt does, and SaaS is built for typical cases — it doesn't bend to your team's methodology or your industry's specifics.

This course is what comes next.

You'll build custom agents that read transcripts the way you would, every time. Assembly lines where one agent extracts themes, another flags contradictions, a third drafts synthesis. Synthetic experts and users informed by your real research data — not someone else's training set.

The shift is from AI user to AI system designer. From researcher to research orchestrator.

You'll build research systems with validation, traceability, and systematic evaluation. You'll learn when to trust autonomous execution — and when to keep humans in the loop. You'll deploy synthetic users with scientific rigor, not vibes. All using Claude Code or Codex: coding with words.

No programming background required. Just willingness to think in systems.

Course 2 of the Certified Agentic Research Specialist (CARS) credential. Take it alone, or pair with AI for Customer Research for the full designation.

What you’ll learn

Learn to build AI agents and workflows—developing judgment for what works, what doesn't, and how to adapt as capabilities evolve.

  • Build specialized agents for recruitment, interviewing, analysis, and synthesis—understanding their limits.

  • Learn when to trust autonomous execution versus when human oversight is essential.

  • Understand agent fundamentals to harness new agentic features as they emerge.

  • Build synthetic users incorporating patterns and behaviors from actual research data—not generic personas.

  • Learn when synthetic users deliver trustworthy insights versus when human participants are essential.

  • Create guardrails so stakeholders understand appropriate use cases and limitations.

  • Design custom agents with specific research specialties - interviewer, analysis, synthesis.

  • Experiment with multi-agent collaboration, learning when it adds value versus complexity.

  • Create custom skills encoding your methods and develop judgment for what to automate.

  • Get comfortable with IDE and terminal through onboarding designed for non-technical researchers.

  • Unlock agentic AI capabilities using Claude Code or Codex for extended reasoning and autonomy.

  • Automate without coding using n8n's visual workflow builder to create research systems.

  • Map your research process to identify where workflows save time versus add complexity.

  • Develop judgment for when to use SaaS tools versus custom agents.

  • Learn which questions benefit from automation versus traditional methods.

  • Show stakeholders how autonomous workflows scale research capacity without proportional budget increases.

  • Teach your team how to move from prompting to orchestrating AI agents.

  • Join a community deploying cutting-edge techniques with early access to emerging capabilities.

Learn directly from John

John Whalen

John Whalen

AI Research Expert | Johns Hopkins PhD

Consulted for
Google
PayPal
Bloomberg
Capital One
GSK
See all products from John

Who this course is for

  • Alumni from "AI for Customer Research" ready to build autonomous agents, synthetic users, and workflows that work independently.

  • Experienced researchers wanting to explore frontier capabilities—building agents, deploying synthetic users, and pushing beyond limits.

  • Product managers and designers ready to harness agentic AI for research—no coding background required, just curiosity to learn.

Prerequisites

  • Recommended: Completion of "AI for Customer Research"

    While not strictly required, Course 1 provides a strong foundation. You should be experienced with prompting AI and evaluating AI outputs.

  • Required: Claude Pro or ChatGPT Plus subscription

    Some agentic capabilities need Claude Code or Codex ($20/month). We'll guide you through setup.

  • Willingness to learn new technical interfaces

    You'll work with an IDE, terminal, and automation platforms. We provide onboarding for non-technical researchers. New to me too! --John

What's included

John Whalen

Live sessions

Learn directly from John Whalen in a real-time, interactive format.

Live Interactive Sessions

Real-time sessions where you'll build agents, create workflows, test multi-agent systems, and get questions answered.

All Session Recordings

Can't make a live session? Access recordings to learn at your own pace and revisit content whenever needed.

Hands-On Projects Building Real Systems

Build agentic workflows, create synthetic users from your research data, and develop multi-agent systems you can adapt for work.

Step-by-Step Setup Guides & Templates

Guides for setting up Claude Code/Codex, n8n workflows, custom agents, and skills—plus common automation patterns.

1:1 Session with John (30 Minutes)

Get guidance on troubleshooting workflows, deciding when to build vs. buy, applying techniques to your context, or career strategy.

Guest Session with Synthetic User Expert

Learn from a platform founder about what's possible with synthetic users, validation frameworks, and emerging best practices.

Community of peers

Stay accountable and share insights with like-minded professionals.

Community of Advanced Practitioners

Connect with researchers, designers, and PMs pushing AI research boundaries—sharing what works and exploring frontier capabilities.

Lifetime access

Go back to course content and recordings whenever you need to.

Certificate of completion

Share your new skills with your employer or on LinkedIn.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Course syllabus

5 live sessions • 26 lessons • 4 projects

Week 1

Jun 4—Jun 7

    Session 1. Foundations & Tool-Based Agents

    8 items

    Jun

    4

    Session 1: Foundations & First Agent

    Thu 6/44:00 PM—6:00 PM (UTC)

Week 2

Jun 8—Jun 14

    Session 2. Agents & Synthetic Users

    5 items

    Jun

    11

    Session 2: Building Agents That Work

    Thu 6/114:00 PM—6:00 PM (UTC)

Free resource

Beyond Prompting: Agentic AI for Customer Research cover image

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

Weekly 2-hour interactive sessions where you'll build AI agents live, set up automation workflows, troubleshoot with peers, and get expert feedback. Designed for hands-on building, not passive lectures.

    • Thu, Jun 4

      4:00 PM—6:00 PM (UTC)

    • Thu, Jun 11

      4:00 PM—6:00 PM (UTC)

    • Thu, Jun 18

      4:00 PM—6:00 PM (UTC)

Projects

1-2 hrs / week

Build actual agentic systems each week. You'll create custom AI agents, set up n8n workflows, develop synthetic users informed by your research data, and experiment with multi-agent systems. These aren't demos—you'll build systems you can adapt for your work, with setup guides, troubleshooting support, and peer feedback as you tinker and refine.

Async content

1 hr / week

Access step-by-step setup guides for Claude Code/Codex, n8n workflows, and custom agents between sessions. Watch build demonstrations, review automation patterns, and explore examples from real research applications. All resources are yours to keep—use them during the course and reference them as you continue building and adapting systems.

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.

    Testimonial author image

    Sofia Linse Videla

    Senior UX Research Manager at Braze
  • John 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.

    Testimonial author image

    Julie Francis

    Founder, BellaVia Research
  • I 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.

    Testimonial author image

    Ross Lordon, PhD

    Staff UX Researcher, Microsoft Azure
  • John 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.

    Testimonial author image

    Kenny Mathew

    Principal UX Researcher at Printify
  • Best 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.

    Testimonial author image

    Esteban Ribero

    Research Leader at TikTok
  • This 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!

    Testimonial author image

    Albert Packer

    Product Design Manager, MasterControl

Frequently asked questions

Maven for Teams

Reimbursement

Get your company to pay

Everything L&D needs: email template, receipts, and certificate of completion.

Get reimbursed

Team discount

Learn with your teammates

Save 20%+ when 2 or more teammates enroll in the same cohort.

Save 20%+ with a team

Private cohort

Run a cohort for your org

A dedicated cohort with a custom schedule and curriculum, tailored to your team.

Book a private cohort
Save 25% through Sunday

$999

USD

·

8 days left to enroll