The AI Runtime - Boston

​The AI Runtime — Boston

​A monthly meetup for engineers learning the production craft of AI. Each event features practitioner talks designed to teach practical lessons — AI design patterns, optimizations, reliability practices, real incidents and what they taught us. The kind of work that happens between the model and the product. Real lessons from people shipping in production.

​The in-person companion to The AI Runtime — the publication where AI engineers learn the craft.

​theairuntime.com

​———

​SPEAKERS AND TALKS

​Welcome to The AI Runtime - Kranthi Manchikanti, AI Architect, Microsoft

​A short introduction to The AI Runtime — for engineers shipping AI to production. What we cover and what we don't.

​Tradeoffs and Learnings with AI Agent Self-Signups - Ray Liao, Cofounder of Inkbox, MIT CS PhD

​As AI agents increasingly become first-class actors on the internet, every existing auth model breaks down — they all assume a logged-in human at the start of the flow, but agents now arrive at endpoints before any human does. At Inkbox, Ray and his team recently enabled agent self-registration, which forced them to rethink identity, trust, and permissions from the ground up. A lesson from one of the first production teams solving this problem.

​The Greenfield Delusion: Shipping AI Inside Real Organizations - Michael R. Schulte, AI Builder, Harvard Business School

​Everyone can now build impressive AI demos in a weekend. Almost none of that work ever makes it into production at a real organization. This session walks through the three questions every deployment dies on, then puts the framework to work: we'll deploy an AI agent into an existing codebase in real time, not a blank folder. The gap between demo and production, made concrete.