🐺 [Oct 28] GitBlame: Werewolf Happy Hour @GitHub Universe
Co-Founder & CTO, Milestone
How teams build software when AI coding agents write the code: directing agents, what code review and validation become when code is nearly free, durable systems with disposable code, orchestrating many agents, keeping them safe inside an organization, and how roles change. Drawn from practitioners at HumanLayer, Sentry, Honeycomb, Google DeepMind, and others.
AI is moving into messy, high-stakes domains where evidence is incomplete and often conflicting. It’s fine for code gen, but when it comes to managing engineering teams or systems diagnosis, agents collapse uncertainty into confident, untraceable answers. Dr. Stephen Barrett argues for a control layer of “governed reasoning,” where AI decisions are structured, stateful, and constrained like software, making them inspectable, reliable, and safe to use at scale.
