AgentPostmortem
Public Case Registry
Hall of FameStatsAboutSearch
+ File Report+ File
RegistryHall of FameStatsAboutSearchTeams
Hall of Fame

Most Catastrophic Failures

The top cases ranked by community vote. These are the incidents that define AI agent risk.

#CaseSeverityScore
  1. 21
    APM-0041·Other / Unknown·~$1.5M

    Cruise robotaxi dragged a pedestrian ~20 feet in San Francisco; permits suspended and $1.5M federal penalty

    CRITICAL
  2. 22
    APM-0055·Other / Unknown

    Amazon scrapped a secret AI recruiting tool that learned to penalize résumés from women

    MODERATE
  3. 23
    APM-0043·Gemini

    Google paused Gemini's image generation after it depicted Nazis and U.S. Founding Fathers as people of color

    LOW
  4. 24
    APM-0053·OpenAI

    Amazon listings appeared with names like 'I'm sorry but I cannot fulfill this request… it goes against OpenAI use policy'

    MINIMAL
  5. 25
    APM-0044·Gemini

    Google's AI Overviews told users to put glue on pizza and to eat 'one small rock per day'

    MODERATE
  6. 26
    APM-0048·Other / Unknown

    Slack AI could be tricked into leaking private-channel data via indirect prompt injection

    SEVERE
← Prev12Next →

Agent operating suite

Tools for building, testing, operating, and supervising AI agents.

GGreenliteHuman approvalsRResolvdSupport operationsTTracecaseAgent evaluationBBridgekitMCP toolsWWebhandsBrowser agents
AgentPostmortem

An independent public ledger of AI agent failures, aggregated from public reports. Not affiliated with or endorsed by any company or product named. Reports may be unverified — always check the linked source.

AboutContactTeams
Hall of FameStatsFile a ReportGitHub
PrivacyTerms

© 2026 AgentPostmortem. Open source.