incident-management

severity_definitions:
  SEV1_critical:
    impact: "Complete service outage or data breach affecting all/most customers"
    examples:
      - Production site completely down
      - Data breach confirmed or suspected
      - Complete loss of a critical business function
      - Security incident with active exploitation
    response_time: "Immediate (within 5 minutes)"
    update_frequency: "Every 15-30 minutes"
    who_is_paged: "On-call engineer, engineering manager, incident commander, executive on-call"
    communication: "Status page update, customer email, executive notification"
    resolution_target: "< 1 hour to mitigate"

  SEV2_major:
    impact: "Major feature broken or severe degradation affecting many customers"
    examples:
      - Key feature completely non-functional
      - Significant performance degradation (>5x latency)
      - Data processing pipeline completely stalled
      - Partial outage affecting a region or segment
    response_time: "Within 15 minutes"
    update_frequency: "Every 30-60 minutes"
    who_is_paged: "On-call engineer, engineering manager"
    communication: "Status page update if customer-facing"
    resolution_target: "< 4 hours to mitigate"

  SEV3_moderate:
    impact: "Minor feature impaired or degradation affecting some customers"
    examples:
      - Non-critical feature broken
      - Moderate performance degradation
      - Elevated error rate (below threshold for SEV2)
      - Single-customer impact on non-critical function
    response_time: "Within 1 hour during business hours"
    update_frequency: "Every 2-4 hours"
    who_is_paged: "On-call engineer"
    communication: "Internal only unless customer inquires"
    resolution_target: "< 1 business day"

  SEV4_low:
    impact: "Cosmetic issue, minor inconvenience, or non-customer-facing problem"
    examples:
      - UI cosmetic bug
      - Non-critical monitoring gap
      - Internal tool degradation
      - Documentation inaccuracy in production
    response_time: "Next business day"
    update_frequency: "As needed"
    who_is_paged: "None (ticket created)"
    communication: "None"
    resolution_target: "Within sprint planning cycle"

escalation_matrix:
  tier_1_on_call_engineer:
    reached_via: "PagerDuty / OpsGenie alert"
    responsibilities:
      - Acknowledge alert within 5 minutes
      - Assess severity and impact
      - Begin troubleshooting
      - Escalate to Tier 2 if unable to resolve within 30 minutes (SEV1/2)
    escalation_trigger: "Cannot resolve, needs additional expertise, or severity upgrade"

  tier_2_team_lead_or_sme:
    reached_via: "PagerDuty escalation or direct page"
    responsibilities:
      - Provide subject matter expertise
      - Assist with diagnosis and resolution
      - Coordinate with other teams if cross-service issue
      - Escalate to Tier 3 if broader coordination needed
    escalation_trigger: "Multi-service issue, needs executive decision, or customer-facing SEV1"

  tier_3_engineering_management:
    reached_via: "PagerDuty escalation or direct call"
    responsibilities:
      - Assign incident commander (if not already)
      - Allocate additional resources
      - Make business decisions (feature disable, rollback, etc.)
      - Coordinate external communication
    escalation_trigger: "Business impact decision, extended outage, or PR/legal concern"

  t