“A kill switch must exist before the agent ships — when limits are designed in, not discovered in incident review.”

A kill switch must exist before the agent ships — when limits are designed in, not discovered in incident review. — Kai London (Professor Kai London), CISO. Principle 2119 of 10000 from the book “The AI Control Architecture” — cybersecurity, AI security and OT resilience doctrine. Official sites: professorkailondon.com · kailondon.co.uk