Recognises a criticality rationale naming no use
A rationale that names no use or consequence.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 1 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 90% | Mastered |
| gemini-3.5-flash-lite | Low cost | 3% | Not shown |
| gpt-6-luna | Low cost | 10% | Not shown |
| claude-haiku-5-5 | Low cost | 90% | 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 rationale stated as the use the element feeds
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: CD-004 ledger_balance, "important" Acceptable: "Feeds LCR outflows and the DGS payout amount"
Also known as: Criticality with no rationale
Related knobits
Builds on
All 10 knobits of Select the critical data elements.
Source: Review checklist 01-cdes, row 5 (BCBS 239 P3; DMBOK)