Free Lesson

Synthetic Users You Can Trust: Ground, Test, Validate

Part of The AI Research Capability Stack

Hosted by John Whalen, PhD

Wed, Jul 15, 2026

4:00 PM UTC (30 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

AI for Customer Research: Deliver Trusted Insights at Scale
John Whalen, PhD
View syllabus

What you'll learn

Ground

Build synthetic users from real participant data — interviews, verbatims, motivations — not from a job title and a wish.

Test

Know the boundary. Synthetic users are decent at surfacing objections, weak assumptions, and confusing language. They are unreliable on purchase intent, behavior change, and anything that requires lived context they don't have.

Validate

Run synthetic against real, and treat every divergence as calibration for the next round.

Why this topic matters

Synthetic users can sharpen a study before you recruit a single participant. They can also hand you confident answers no real customer would give. The difference isn't the tool — it's whether you have a way to check. In this Lightning Lesson, John shows the validation skill he teaches inside both of his courses: ground synthetic users in real participant data, learn which questions they answer reliably and which they get wrong, and compare synthetic output against real customers so each divergence improves the next round. You'll leave knowing when to trust a synthetic answer, when to override one, and how to make that call visible to your team.

You'll learn from

John Whalen, PhD

CEO, AI Research Leader, Cognitive Scientist, O'Reilly Author

I’m CEO of Brilliant Experience, have a PhD in cognitive science, and wrote Design for How People Think (O’Reilly).

For 20 years, I’ve helped teams at companies like Google, GSK, and Capital One better understand their customers, capture insights, and build better products.

When AI started reshaping research, I got curious and learned. My team ran “AI vs. Humans” studies to see where AI excels, where human judgment matters most, and how to effectively blend both.

I’ll teach you how to create trustworthy AI research workflows that let you trace every step and insight.

Then advance to the next course and learn to orchestrate agentic research teams, work strategically with synthetic users grounded in real data, and bring in human judgement so you can scale research without losing rigor.

See all products from John

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.