Recognises a missing or meaningless requirement priority
No priority, or every requirement is must. Test: if this were the only thing not delivered, would the release be cancelled?
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 10 models master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 39% | Not shown |
| gemini-3.1-pro-preview | Flagship | 43% | Not shown |
| gpt-6-astra | Flagship | 40% | Not shown |
| claude-fable-5-1 | Flagship | 40% | Not shown |
| gemini-3.8-flash | Mid tier | 40% | Not shown |
| gpt-6.1-sol | Mid tier | 39% | Not shown |
| claude-sonnet-5-5 | Mid tier | 42% | Not shown |
| gemini-3.5-flash-lite | Low cost | 43% | Not shown |
| gpt-6-luna | Low cost | 40% | Not shown |
| claude-haiku-5-5 | Low cost | 40% | 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 requirements whose priority is missing or uniformly must
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: DR-003 with no priority; a register in which 40 of 42 requirements are must Acceptable: Priorities that survive the cancellation test, with must reserved for the ones that do.
Also known as: Priority missing or meaningless (data requirement)
Related knobits
Builds on
All 47 knobits of Capture data requirements.
Source: Review checklist 01-requirements, row 16; 29148 5.2.8 (priority); REQ-006