3 Tactics for PMs: Immediately Better AI Analysis
Hosted by Caitlin Sullivan
Mon, Jan 12, 2026
1:30 PM UTC (45 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
Mon, Jan 12, 2026
1:30 PM UTC (45 minutes)
Virtual (Zoom)
Free to join
116 students
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
Why AI analysis outputs feel so inconsistent — and a fix
I'll use the same prompt and transcripts across 6 models. See why we get wildly different results and counts - and a fix
Categorization that's finally consistent across runs
Same feedback messages, same prompt, completely different themes. Small additions solve this if you know why.
Helping AI understand your data before analysis starts
Most people upload and prompt. I'll show you what to do first — it takes 30 seconds and prevents entirely wrong analyses
Why this topic matters
AI analysis is now part of how PMs work — summarizing research, categorizing feedback, pulling patterns from data.
But most people get inconsistent results and don't know why.
Then they doubt *all* AI analysis.
The issue usually isn't the model. It's the prompt and data setup.
I'll demo exactly where things break and show you three fixes you can apply immediately.
You'll learn from
Caitlin Sullivan
Ex-Head of User Research at Spotify Business/Soundtrack. AI Advisor.
Why trust me?
- Ex-Head of User Research at embedded in Product—sitting alongside PMs shipping B2B products. I know how fast feedback piles up.
- 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.
- 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)
- 1000+ hours testing AI for customer insights.
Trusted by teams and individuals at
By continuing, you agree to Maven's Terms and Privacy Policy.