Recognises an architecture principle contradicting the data strategy
An architecture principle that would break an approved data principle; architecture has overridden strategy without a ruling.
Can AI do this?
Not settled yet The benchmark tested this, but the models' answers do not settle yet whether they master it. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 89% | Not shown |
| gemini-3.5-flash-lite | Low cost | 7% | Not shown |
| gpt-6-luna | Low cost | 87% | Not shown |
| claude-haiku-5-5 | Low cost | 89% | Not shown |
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 two principles and the ruling needed
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: AP-007 "Each business line may keep its own copy of customer data" vs data strategy DP-008 "Data is captured once and reused" Acceptable: Raised with the strategy owner; AP-007 narrowed to read-only copies fed from the system of record
Also known as: Principle contradicting the data strategy
Related knobits
Builds on
All 17 knobits of Frame stakeholder concerns and architecture principles.
Source: Review checklist 01-concerns-principles, row 10 (DMBOK)