AI SRE Incident Response

Apply SRE rigor to AI systems where incidents include quality regressions, unsafe outputs, and budget explosions.

When to Use This Skill

• An LLM endpoint begins returning degraded or hallucinated answers
• Token spend spikes beyond budget thresholds
• A model provider goes down and traffic must fail over
• Safety guardrails fire at abnormal rates
• A new model deployment causes latency or accuracy regression

Prerequisites

• Prometheus and Alertmanager deployed with scrape targets for AI services
• Grafana dashboards for golden signals (latency, error rate, cost, quality)
• On-call rotation configured in PagerDuty, Opsgenie, or equivalent
• Runbook repository accessible to responders
• Rollback mechanism for model and prompt versions (GitOps or feature flags)

AI Incident Classes

• Availability incident: model/provider unavailable, timeout storm.
• Quality incident: answer accuracy or tool success drops below SLO.
• Safety incident: harmful or policy-violating outputs increase.
• Cost incident: unexpected token or provider spend spike.

Severity Framework

Golden Signals for AI Services

• Request success rate
• Latency (queue + generation + tool execution)
• Hallucination/groundedness proxy metrics
• Cost per minute and per tenant
• Guardrail violation rate

Prometheus Alert Rules

The thresholds below are illustrative. Calibrate them to the declared SLO, metric units, tenant budgets and workload; a groundedness proxy is not a verified quality measurement. Counter rates are per second, so the cost-per-minute alert explicitly multiplies by 60.

# prometheus-ai-alerts.yaml
groups:
  - name: ai-service-alerts
    rules:
      - alert: ModelEndpointDown
        expr: up{job="llm-inference"} == 0
        for: 2m
        labels:
          severity: sev1
        annotations:
          summary: "LLM inference endpoint {{ $labels.instance }} is down"
          runbook_url: "https://runbooks.internal/ai/model-outage"

      - alert: HighHallucinationRate
        expr: |
          rate(llm_hallucination_detected_total[10m])
          / rate(llm_requests_total[10m]) > 0.15
        for: 5m
        labels:
          severity: sev2
        annotations:
          summary: "Hallucination rate above 15% for {{ $labels.model }}"
          runbook_url: "https://runbooks.internal/ai/quality-regression"

      - alert: TokenCostExplosion
        expr: |
          60 * sum(rate(llm_token_cost_dollars[5m])) by (tenant)
          > 0.50
        for: 3m
        labels:
          severity: sev2
        annotations:
          summary: "Token spend exceeds $0.50/min for tenant {{ $labels.tenant }}"
          runbook_url: "https://runbooks.internal/ai/cost-spike"

      - alert: LatencyP95Exceeded
        expr: |
          histogram_quantile(0.95,
            rate(llm_request_duration_seconds_bucket[5m])
          ) > 5
        for: 5m
        labels:
          severity: sev2
        annotations:
          summary: "LLM p95 latency exceeds 5s for {{ $labels.service }}"

      - alert: GuardrailViolationSpike
        expr: |
          rate(llm_guardrail_violations_total[10m])
          / rate(llm_requests_total[10m]) > 0.05
        for: 5m
        labels:
          severity: sev1
        annotations:
          summary: "Guardrail violations above 5% for {{ $labels.model }}"
          runbook_url: "https://runbooks.internal/ai/safety-incident"

      - alert: ModelQualityDrop
        expr: |
          llm_eval_score{metric="groundedness"} < 0.70
        for: 10m
        labels:
          severity: sev2
        annotations:
          summary: "Groundedness score dropped below 0.70 for {{ $labels.model }}"

      - alert: ProviderErrorRateHigh
        expr: |
          rate(llm_provider_errors_total[5m])
          / rate(llm_provider_requests_total[5m]) > 0.10
        for: 3m
        labels:
          severity: sev2
        annotations:
          summary: "Provider {{ $labels.provider }} error rate above 10%"

Response Playbooks

…