Shipping Products When You Don't Know What they Can Do
summary
A platform called Teammates builds an autonomous coworker (Stacy) that lives in Gmail and Slack and surprisingly handles being tagged in a Google Doc comment — it worked in a customer experiment. Product practice pivots to designing affordances not features, using AI evals as specs to measure probabilistic behavior, vibe-coding interactions to feel emergent UX, and treating discovery experiments plus model upgrades as the real development loop rather than fixed requirements.
AI-written summary · about
chapters (8)
- 0:00Introduction and background
- 2:51Why product management is changing
- 5:58Thinking in affordances over features
- 8:21The role of evals in product development
- 10:51Vibe coding and emergent behavior
- 13:15Discovering functionality through experimentation
- 16:06Customer interactions in an uncertain world
- 18:11Conclusion and future of product development
related talks
57mOne Team’s Journey to Using AI Without the Hype
41mOur New AI Coworkers & Enemies
15mFrom Hype to Help: An AI Product Journey
55mEnterprise Chatbots (using messaging and AI to build novel user interfaces for work)
27mPixels and prompts: building products in the AI era
42mUX+AI: Mastering the UX of AI-Powered Products
35mShipping with Confidence in the Age of AI
27mThe Shape of AI : How designers integrate AI into their workflow