AI Builder · Harvard Business School
Michael R. Schulte is an AI Builder at Harvard Business School working on the gap between AI demos and AI shipped inside real organizations.
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.
Curated picks from The AI Runtime library that align with Michael R. Schulte's work.
Chip Huyen's early but durable map of the production LLM stack — what changes when you move from a notebook to real users. Cost, latency, hallucination, evals, drift. The starting reading for anyone moving from research to product.
Seven production patterns — evals, RAG, fine-tuning, caching, guardrails, defensive UX, collect feedback — with cites and rationale. The reference Eugene's been updating since 2023; the canonical "what does ship-to-prod look like" map.
How to actually improve an AI product after the demo: build evals from real failures, cluster errors, iterate the prompts and the data. The closest thing the field has to a playbook for "we shipped, it kind of works, now what."