The AI Agent Gap

79% of enterprises adopt AI agents. 11% reach production. This book is about the other 89%. The demo always works. An agent triages the inbox, drafts the report, answers the customer — the room nods, the budget clears, a launch date gets a slide. Then the launch date moves. And moves again. The most-cited number of the year says it plainly: in a 2025 MIT study of enterprise AI, ninety-five percent of generative-AI pilots never reached measurable production impact. The failures were not failures of capability. They were failures of how organizations operate and govern the systems they had already bought. The AI Agent Gap names that space precisely — the distance between "it worked when I tried it" and "it works every time, for everyone, under load, when something upstream breaks, at a cost we can defend." Andreas Anding calls it the Production Chasm, and this is the operating discipline for crossing it. Drawing on twenty years in digital transformation and agents he runs in production himself, Anding gives technical leaders a complete operating model: – The Reliability Ladder: why reliability is a designed operating property, not a model property – Evaluation as Infrastructure: golden sets, regression gates, offline and online evals – Observability, cost, and latency under control: traces not logs, budget gates, real unit economics – Governance and human-in-the-loop as a production enabler, EU AI Act–ready – The Agent Operating Model: who owns agents, the Agent Ops function, runbooks – A Production-Readiness Assessment and a concrete 30/60/90-day plan you can run on Monday Written from the operator's chair, not the engineer's. If you have run the pilots and you are tired of watching them stall, this is the playbook for closing the gap. A demo proves possibility. Production demands reliability. The two are not the same skill — and this book is about the second one.