Synthetic Users That Work: What Most People Miss
Hosted by Caitlin Sullivan
Thu, Mar 26, 2026
1:30 PM UTC (30 minutes)
Virtual (Zoom)
Free to join
By continuing, you agree to Maven's Terms and Privacy Policy.
Go deeper with a course
AI Analysis for PMs: From Feedback Chaos to Decisions in Hours
Caitlin Sullivan
Ex-Head of User Research at Spotify Business, Advisor to AI platforms, Top 100
Thu, Mar 26, 2026
1:30 PM UTC (30 minutes)
Virtual (Zoom)
Free to join
Go deeper with a course
AI Analysis for PMs: From Feedback Chaos to Decisions in Hours
Caitlin Sullivan
Ex-Head of User Research at Spotify Business, Advisor to AI platforms, Top 100
What you'll learn
Not all data works for synthetic users
You have behavior data, customer calls, surveys... But not all data is right for synthetic users. Know what to use.
Where synthetic users actually work (and where they don't)
Not every research question fits. I'll show you which use cases can deliver real value — and which are a gamble.
What big studies did that you're not replicating
Academic studies did specific things most Product teams skip. Learn what, and how to apply it to your own data and setup
Why this topic matters
Synthetic users sound like magic — instant customer feedback without recruiting anyone.
But most attempts produce plausible-sounding nonsense.
Why? Wrong data, wrong use case, or trying to copy academic study results without the same conditions.
I've dug into the research and run 30+ synthetic experiments myself. This session covers what you need to know before you waste time on bad outputs
You'll learn from
Caitlin Sullivan
Ex-Head of Research at Spotify Business/SYB ᐧ AI Advisor for Customer Insights
Why trust me?
- Product teams like Maze hire me to fix prompts behind their AI tools—I help them build the functionality that gets customers better AI results.
- Ex-Head of User Research embedded in Product—sitting alongside PMs shipping to tough B2B audiences. I know how fast feedback piles up.
- Trained 450+ people at Canva, YouTube, Figma, Meta, and more to use AI for analysis they can actually defend in high-stakes decisions. (My previous course is rated 4.8/5)
- 1500+ hours testing AI for customer insights.
Trusted by teams and individuals at
By continuing, you agree to Maven's Terms and Privacy Policy.