Listen: How to do AI analysis you can actually trust
AI models like ChatGPT, Claude, and Gemini often produce confident but unreliable insights from customer data, including fabricated quotes and generic conclusions. Caitlin Sullivan outlines four failure modes in AI-powered user research and provides actionable prompting techniques to ensu
Sign up to read the full summary
Free AI-powered recaps of every episode, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.
Guest
Caitlin Sullivan
solo on Lenny's Reads
Mentions
Books, people, and resources mentioned in this episode.
People
Companies
Products & Tools
Topics
Listen to This Episode
More from Lenny's Reads
Listen: Building AI product sense, part 2
Listen: How to use AI for your next job interview
Listen: AI tools are overdelivering: results from our large-scale AI productivity survey
Listen: How to build your PM second brain with ChatGPT
Listen: Not all AI agents are created equal
Listen: Part 2 of how to get the most out of your product pass—and welcome, Stripe Atlas, to the bundle!
Similar episodes
Other shows covering related topics.
#183 - The Best Ways to Use AI in UX Research with Laura Klein of NN/g
Awkward Silences
#187 - Throwback: Harnessing AI For Better Insights with George Whitfield of MIT and Google
Awkward Silences
Listen: Building AI product sense, part 2
Lenny's Reads
Why most AI products fail: Lessons from 50+ AI deployments at OpenAI, Google, and Amazon
Lenny's Podcast: Product | Career | Growth
#188 - Why AI Can't Replace Qualitative Research with Sam Ladner of Workday
Awkward Silences
Listen: How to use AI for your next job interview
Lenny's Reads
Get summaries like this every morning.
Free AI-powered recaps of Lenny's Reads and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.