Staging environment
Free Lesson

3 Tactics for PMs: Immediately Better AI Analysis

Part of Product Management Fundamentals

45 min
Jan 14, 2026 8:30 AM
Virtual (Zoom)

In this video

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

Caitlin Sullivan

Ex-Head of User Research at Spotify Business/Soundtrack. AI Advisor.

Trusted by teams and individuals at

Canva
YouTube
Ramp
Figma
See all products from Caitlin