Google Workspace

Shipping Products When You Don't Know What they Can Do — Ben Stein, Teammates

Jul 28, 2025 · 19:34

Ben Stein, founder of Teammates, argues that product management for AI agents requires abandoning traditional specs and embracing uncertainty. He describes how his team discovered emergent behavior when a customer asked to tag an agent in a Google Doc comment—an unplanned feature that worked. Stein advocates thinking in affordances rather than features, using evals as the new spec, and vibe coding to feel interactions before committing. He notes that bugs become ambiguous when behavior is probabilistic, and customer meetings shift from selling vision to co-inventing the future. The episode offers a field guide for product teams navigating boundless surface areas built on unpredictable LLMs.

Privacy First Enterprise AI: Building AI Agents that Never Leave Your Security Boundary

Feb 22, 2025 · 7:10

Steven Moon, founder of Aech AI, argues that enterprise AI agents should be deployed within existing security boundaries by treating them like human employees—using existing identity management, compliance frameworks, and audit tools rather than building parallel systems. He explains that IT departments will evolve into HR departments for AI agents, provisioning them through active directory and applying standard security policies. Moon highlights email as a powerful medium for agent-to-agent communication, where every interaction is logged and auditable through existing systems. He advocates for enhancing current enterprise platforms like Microsoft 365 and Azure with AI agents instead of creating new interfaces, noting that the era of mandatory translation layers between humans and machines is ending.