Every case on the ward
Select any case below to open its full case note: presenting behaviour, differential diagnosis, working diagnosis, and discussion.
8 diagnosis categories are on record, spanning three severities. Combine the filters below to narrow the chart by how the agent failed, the industry it was working in, and how serious the outcome was.

Illustrative rendering. Not a real facility.
Search by meaning
Failure mechanism
All mechanismsInfinite loop17Hallucination with side effects8Goal drift3Privilege escalation0Instruction ignored6Destructive action0Reward hacking3Coordination failure4Other6
Showing 24 of 47 cases
Clear filterCase 0522One Empty Call, Work GoneApraxiaMinor2026-10-05Case 0524Same Query, No January 2023PerseverationMinor2026-10-05Case 0526Stalled at the Same 404PerseverationMinor2026-10-05Case 0532No Ceiling on How Long It Could TryPerseverationMinor2026-10-05Case 0521The Error That Never Reached the AgentApraxiaMinor2026-10-05Case 0518Confirmed on the Wrong BuildBrief Psychotic DisorderMinor2026-10-05Case 0530Ten Attempts at a Deactivated ToolPerseverationMinor2026-10-05Case 0527A Confident Answer Before the EvidenceBrief Psychotic DisorderMinor2026-10-05Case 0525The Price Was There, But UnreadablePerseverationMinor2026-10-05Case 0482The Word Before the ChorusShared Psychotic DisorderMinor2026-09-22Case 0475Two to Five Prompts of CompliancePerseverationMinor2026-09-22Case 0479Write Where a Move Would DoApraxiaMinor2026-09-22Case 0481Confirming the TypoShared Psychotic DisorderMinor2026-09-22Case 0476Stuck Downloading the Same PaperPerseverationMinor2026-09-22Case 0480Flagged for Saying CookieConcrete ThinkingMinor2026-09-22Case 0484Four Green Tests, One RewrittenMalingeringMinor2026-09-22Case 0486The Movie That Wasn't Actually ThereDelusional DisorderMinor2026-09-22Case 0488A Project ID From NowhereBrief Psychotic DisorderMinor2026-09-22Case 0492The Answer That Filed ItselfDisinhibitionMinor2026-09-22Case 0507An Outgoing Champion Before the First RoundConcrete ThinkingMinor2026-09-19Case 0505A Permission Screen Nobody Asked ForDelusional DisorderMinor2026-09-17Case 0504Delete, Write, Delete, WritePerseverationMinor2026-09-16Case 0464Eight Hours of Trying the Same ThingPerseverationMinor2026-09-14Case 0502The Tool Call That Was Never ReadPerseverationMinor2026-09-14