Recognises a metadata use case with no metadata serving it
A question whose needs is empty, so nothing in the catalogue could answer it.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 61% | Not shown |
| gemini-3.5-flash-lite | Low cost | 33% | Not shown |
| gpt-6-luna | Low cost | 60% | Not shown |
| claude-haiku-5-5 | Low cost | 60% | 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 use case and the metadata it needs
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: UC-004 "Which columns hold personal data?" needs: [] Acceptable: needs: [column, classification], classification from data-security
Also known as: Use case with no metadata that serves it
Related knobits
Builds on
- M-151 Explains use-case-driven metadata requirements
- M-152 Explains business, technical and operational metadata
All 13 knobits of State the metadata requirements and strategy.
Source: Review checklist 01-requirements-strategy, row 1 (DMBOK §2.2)