← Back to Dashboard
1. AI Incident Taxonomy2. Postmortems and Corrective Actions

AI Incident Taxonomy

📚 Incident Response for AI10 min120 XP

Classify Incidents by Failure Mode

AI incidents include quality regressions, safety policy breaches, latency spikes, cost explosions, and tool orchestration failures. Separate detection and response playbooks by incident type for faster triage - "the AI is acting weird" is not a pageable signal; "guardrail intervention rate tripled in 30 minutes" is.

The Five Failure Classes

ClassExampleDetection signalFirst response
Quality regressionTriage accuracy silently drops after model/prompt changeOnline eval score dip, escalation rate riseCorrelate with release manifest; roll back candidate
Safety breachProhibited content served; PII echoedGuardrail false-negative report, user reportContain first: tighten guardrail/disable feature; preserve evidence
Reliabilityp95 spikes, throttling waves, region impairmentLatency/error SLO alarmsClassic SRE: failover, shed load, engage backpressure
Cost explosionAgent retry loop burns 40M tokens overnightToken budget alerts, anomaly detectionKill switch per tenant/route; find the loop in traces
Orchestration failureDuplicate side effects, stuck plans, tool cascadeTool error rate, idempotency-conflict logsPause affected flows; reconcile side effects from audit log

Why the Taxonomy Pays Rent

  • Different oncalls - safety breaches page the safety owner and may trigger legal/comms; latency pages the platform SRE. One generic "AI incident" page delays both.
  • Different evidence - quality incidents need eval diffs and release manifests; cost incidents need token telemetry by route; safety incidents need preserved prompt/response pairs.
  • Different severity ladders - a P3 latency blip and ANY safety false negative are not the same urgency, and your paging rules should encode that.
Detection completeness check: for each class, ask "what alarm fires, within how many minutes, paging whom?" A class with no answer is an incident you'll discover from a customer tweet.
🧪 Knowledge Check
Press 1-4 to select1 of 2
A useful AI incident taxonomy should:
Use one generic bucket
Separate quality, safety, reliability, and cost failure classes
Ignore policy issues
Exclude tooling failures