Free Lesson
Stop Letting Your LLM "Find the Issues" In Your Data
45 min
Jun 24, 2026 3:00 PM
What you'll learn
Why "ask AI to find the bugs" backfires
An AI agent will read all your data and hand back confident summaries. The catch: it has no taste. It can't tell a pattern that matters from one that's just noise. You'll learn to spot that gap, so a tidy summary never passes for a real finding.
Read your data the way an analyst would
Learn open coding: a hands-on method for reading through real examples of your product in use. The skill isn't summarizing what happened. It's asking who the user was and what they needed, which is where the real insight hides.
Put AI to work without letting it mislead you
See how to bring AI into your analysis as an assistant: it does the grunt work, you stay the judge. You'll also learn to push back on what it gives you, so an answer that sounds smart but says nothing never makes it onto your roadmap.
Why this topic matters
Your AI product does something dumb. How do you fix it? Most teams guess, or dump everything into an AI and trust whatever comes back, then ship fixes that don't move anything. This session is about the alternative: a hands-on way to find what's actually broken in your product, and to put AI to work on the problem without letting it fool you. You'll leave knowing how to debug your AI for real.
You'll learn from
Shreya Shankar
AI researcher; incoming CS Professor at Carnegie Mellon
Hamel Husain
ML Engineer with 20 years of experience