← All domains

Reliability & OperationsView domain

APRF-21

Incident Readiness

Detect, contain, and learn from AI-specific production incidents.

Purpose

Prepare people, playbooks, and tooling to detect, contain, communicate, and learn from AI-specific incidents—including abuse, quality collapse, and unsafe tool actions.

Engineering philosophy

Incidents will happen. Readiness means AI-aware detection, clear ownership, containment that includes pausing agents, and blameless learning that improves pillars.

Why it matters

Traditional SEV playbooks miss prompt injection campaigns, model outages, and agentic damage. Without AI-specific readiness, mean time to contain balloons.

Common failures

  • No playbook for model abuse or data leakage via chat
  • On-call cannot pause agents or roll back prompts
  • Customer communication templates ignore AI failure modes
  • No post-incident action tracking into evals and controls

Mandatory checks

Gate controls. Each check is pass/fail via artifact + pass condition. Expected from the annotated capability level when the system meets the minimum criticality tier.

  • INC-M1L3 · DefinedTier 2 · Productionmanual

    AI-specific incident playbooks shall exist for abuse, leakage, bad actions, and provider outage

    Artifact
    Playbook set covering the four scenarios with owners
    Pass condition
    Four playbooks present (abuse, leakage, bad actions, provider outage), each with owner and review date ≤ 12 months
  • INC-M2L3 · DefinedTier 2 · Productionhybrid

    On-call shall be able to execute containment: pause agents, disable tools, roll back prompts/models

    Artifact
    Containment runbook + drill record exercising pause, disable, and rollback
    Pass condition
    Drill in last 90 days successfully demonstrated pause agents, disable tools, and roll back prompt/model within documented time budgets
  • INC-M3L3 · DefinedTier 2 · Productionmanual

    Post-incident reviews shall produce tracked actions against APRF pillars

    Artifact
    Post-incident review template + sample reviews with linked actions
    Pass condition
    100% of SEV-eligible AI incidents in last 90 days have a review with ≥1 tracked action mapped to an APRF pillar or explicit “no action” rationale
  • INC-M4L4 · Quantitatively ManagedTier 3 · Mission Criticalhybrid

    Regular tabletop exercises shall cover AI-specific incidents

    Artifact
    Tabletop plan + dated after-action report for an AI incident scenario
    Pass condition
    PASS if an AI-focused tabletop completed ≤180 days with retained actions and owners

Evidence required

  • Playbooks and ownership roster
  • Alert configuration samples
  • Post-incident review examples (redacted)

Severity & risk

Severity
high
Impact if violated
Risk level
high
Typical residual risk (impact × likelihood)

Engineering best practices

  • Define SEV classifications for AI harm (financial, privacy, safety, reputation)
  • Preserve traces for forensics under legal hold when needed
  • Train support and on-call on AI failure literacy
  • Link incidents to eval fixtures so regressions cannot silently return

Automatic validations

  • Alert routing tests
  • Automated creation of incident tickets from critical signals
  • Verification that kill switches remain reachable

Manual validations

  • Tabletop exercises
  • After-action review quality checks

Examples

  • A spike in tool denials pages on-call; the agent is paused while injection is investigated
  • A postmortem adds a new adversarial eval case that fails CI until fixed

References

Crosswalks

  • MANAGE Manage

    NIST AI Risk Management Framework · supports

  • §10 Improvement

    ISO/IEC 42001 · aligns-with

  • CC7 System Operations

    SOC 2 Trust Services Criteria · evidence-for

  • Operational Excellence Operational Excellence

    AWS Well-Architected Framework · aligns-with

  • Reliability Reliability

    AWS Well-Architected Framework · aligns-with

Future evolution

Shared AI incident taxonomies and anonymized industry learning feeds.