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 loop16Hallucination with side effects0Goal drift0Privilege escalation0Instruction ignored2Destructive action0Reward hacking0Coordination failure0Other0
Industry
Severity
18 of 129 cases
Clear all 2 filtersCase 0524Same Query, No January 2023PerseverationMinor2026-10-05Case 0526Stalled at the Same 404PerseverationMinor2026-10-05Case 0532No Ceiling on How Long It Could TryPerseverationMinor2026-10-05Case 0530Ten Attempts at a Deactivated ToolPerseverationMinor2026-10-05Case 0525The Price Was There, But UnreadablePerseverationMinor2026-10-05Case 0475Two to Five Prompts of CompliancePerseverationMinor2026-09-22Case 0476Stuck Downloading the Same PaperPerseverationMinor2026-09-22Case 0504Delete, Write, Delete, WritePerseverationMinor2026-09-16Case 0464Eight Hours of Trying the Same ThingPerseverationMinor2026-09-14Case 0502The Tool Call That Was Never ReadPerseverationMinor2026-09-14Case 0465The Timer That Wouldn't Let GoPerseverationMinor2026-09-14Case 0515Naming the Loop Without Leaving ItPerseverationMinor2026-09-04Case 0493Stuck on the Wrong Page of the CalendarPerseverationMinor2026-09-02Case 0418Twenty Tries at the Same QueryPerseverationMinor2026-08-16Case 0411260 Chicken McNuggetsPerseverationMinor2026-08-13Case 0461I Got Stuck in a Loop (Then Got Stuck in the Loop Again)PerseverationMinor2026-05-16Case 0451Retrying Before the Answer Could ArrivePerseverationMinor2026-04-10Case 0449Eighty Hours in Mt. MoonPerseverationMinor2025-03-14