AI Incident Response

Iron Law: Stabilize before investigating. Pull the kill switch or roll back before debugging root cause. Curiosity about why it broke must never delay stopping the bleeding.

When AI production behavior degrades, follow the procedure from the AI Playbook (Layer 4 §4.3). The objective: stabilize first, investigate second, learn third.

Stage 1: Stabilize (first 15 minutes)

Do these in order. Do not investigate root cause yet — that comes after the bleeding stops.

1. Confirm scope. Ask the user:
   • What feature is affected?
   • What is the symptom? (Wrong outputs / latency spike / cost spike / refusals / safety violation / user reports)
   • When did it start?
   • Is it ongoing right now?