Building AI Products - All Things Product Podcast with Teresa Torres & Petra Wille

Listen to this episode on: Spotify | Apple Podcasts

In this episode of All Things Product, Petra Wille flips the script and asks Teresa Torres a big, timely question: How do product teams learn to build AI-powered products—beyond just dabbling with ChatGPT? Teresa shares fresh insights from her own experience building a real AI product over the past several months, breaking down the unique skills, workflows, and cross-functional collaboration patterns required for success.

You’ll hear why building AI features is more like orchestrating a team of interns than just writing a killer prompt, and how practices like observability, evals, and ongoing maintenance need to evolve for the LLM era. If you’re a product person figuring out where AI fits in your org, this conversation will give you a clear, practical starting point.

What you’ll learn in this episode:

  • The difference between an AI-powered product manager and an AI product manager

  • Why prompt engineering for a product is different from prompting ChatGPT for personal use

  • The role of prompt decomposition and orchestration in building robust AI features

  • How to think about system design, risk mitigation, and cross-functional collaboration

  • Why observability and logging traces are critical for LLM products

  • The challenge of evaluating non-deterministic AI features (and why “thumbs up/thumbs down” isn’t enough)

  • How to decide when AI is the right solution for a customer problem

  • The hidden cost of ongoing maintenance for AI features

Resources & Links:

Mentioned in this episode:

Petra Wille