Recognises conflicting data policies
Two policies whose scopes overlap and whose intents cannot both hold for the same data. Each reads well alone.
Can AI do this?
AI does this partly Some of the tested AI models master this; others do not show it. 2 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 99% | Mastered |
| gemini-3.5-flash-lite | Low cost | 7% | Not shown |
| gpt-6-luna | Low cost | 43% | Not shown |
| claude-haiku-5-5 | Low cost | 98% | Mastered |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: The policy pair, the data in both scopes and the ruling needed
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: PO-004 "Customer personal data is deleted within 30 days of a verified erasure request" vs PO-005 "Transaction records are kept for 10 years after the relationship ends" Acceptable: Raised for a ruling by both owners; resolved by scoping (GDPR Art. 17(3)(b): erasure does not apply where retention is a legal obligation), stated in both policies
Also known as: Conflicting policies
Related knobits
Builds on
All 26 knobits of Write governance policies, standards and procedures.
Source: Review checklist 03-policies-standards, row 14 (38505 conformance; DMBOK)