Product Talk · Teresa Torres
articleplaybookGenerating Opportunity Solution Trees with AI: How Vistaly Rebuilt Its Product Around Interview Synthesis, Evals, and Repair Loops
1 October 2026Product
Source excerpt
About Product TalkListen to this episode on: Spotify | Apple PodcastsWhat happens when you hand your opportunity solution tree to an AI? Vistaly rebuilt its entire product to find out—and the agents were the easy part.In this episode of Just Now Possible, Teresa Torres talks with Matt O'
This is a limited feed-provided excerpt, not the full original work.
Apollo layer
What a founder can learn
Founder takeaway
When building AI into a discovery product, focus less on the agent itself and more on the quality system around it: synthesize customer interviews, evaluate outputs against explicit criteria, and create repair loops for weak results.
Why it matters
AI-generated opportunity maps are only useful if teams can trust and improve them. Evals and repair loops turn a promising demonstration into a product that can deliver more consistent customer value.
Relevant guides
Put it to work
Choose one AI-generated output in your product. What evidence should inform it, how will you evaluate whether it is useful, and what happens when it fails that evaluation?