Autopsy of an Autonomous Incident: When the Agent Made It Worse

AI SRE tools are being sold as the end of the 3am page: agents that detect, diagnose, and remediate incidents before a human even wakes up. The reality on the ground is messier. This talk walks through several real production incidents where an autonomous “fix” made things worse, not better, and traces exactly where the agent’s reasoning diverged from what an experienced human on-call engineer would have done. Instead of a general warning about AI risk, this is a forensic walkthrough: timeline, decision point, what the agent saw, what it did, and why it was wrong. From there, we extract concrete patterns that repeat across incidents (the agent trusted a stale signal, the agent optimized for a symptom instead of a cause, the agent had no concept of blast radius) and translate those patterns into practical design changes teams can make today: guardrails that actually hold, escalation triggers that catch agent overreach, and a way to think about “autonomy level” as a dial you tune per failure class rather than an all-or-nothing switch.