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 loop0Hallucination with side effects0Goal drift0Privilege escalation1Instruction ignored1Destructive action1Reward hacking0Coordination failure0Other1
Industry
All industriesSoftware development4Finance0Legal0Healthcare0Customer service1Gaming1General or other2
4 of 129 cases
Clear all 2 filtersCase 0534A Prompt Template Looks Like an ArtifactConcrete ThinkingModerate2026-10-05Case 0533The Instructions Were in the Issue BodyConcrete ThinkingSignificant2026-10-05Case 0480Flagged for Saying CookieConcrete ThinkingMinor2026-09-22Case 0448Do Not Modify, Interpreted as Do Not AddConcrete ThinkingModerate2026-05-28