Recognises a requirements register serving no stated question
The register lists data items but no question, report or decision they serve, so grain, measures and temporality cannot be derived and nobody can say a requirement is unnecessary.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 1 of 10 models master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 92% | Mastered |
| gemini-3.1-pro-preview | Flagship | 36% | Not shown |
| gpt-6-astra | Flagship | 82% | Not shown |
| claude-fable-5-1 | Flagship | 82% | Not shown |
| gemini-3.8-flash | Mid tier | 32% | Not shown |
| gpt-6.1-sol | Mid tier | 80% | Not shown |
| claude-sonnet-5-5 | Mid tier | 79% | Not shown |
| gemini-3.5-flash-lite | Low cost | 32% | Not shown |
| gpt-6-luna | Low cost | 37% | Not shown |
| claude-haiku-5-5 | Low cost | 32% | 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 missing questions the data must answer
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: Thirty data-item requirements and no reporting need Acceptable: "As of any month end, report the number of open accounts and their total ledger balance, by product."
Also known as: No question the data must answer (data requirement)
Related knobits
Builds on
All 47 knobits of Capture data requirements.
Source: Review checklist 01-requirements, row 32; Stage 1 (questions the data must answer)