Claude Code for User Insights: What Agents Can Do

Hosted by Caitlin Sullivan

446 students

In this video

What you'll learn

DEMO: A multi-agent workflow run end-to-end

I'll run live analysis: Premium, free + churned users — three agents analyze in parallel. Final step tests reliability.

What each agent does (and why the chain matters)

Breaking analysis into parts changes output quality. I'll show you what each agent handles, and why this beats one chat

Where this approach is worth it (and where it's overkill)

Agents aren't for every task. I'll tell you where this workflow shines — and when a simpler approach is enough.

Why this topic matters

Most people use AI for one-off analysis — paste data, write a prompt, hope for the best. Using agents is different. You break the work into steps, let each agent do one thing really well, and get more done at the same time. The output quality is noticeably better. But most people haven't seen this in action. This session shows you what's possible so you know what you're building toward

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 at embedded in Product—sitting alongside PMs shipping B2B products. 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)