Recognises an ambiguous business term in a data requirement
A business word that has two meanings in the organisation, or a qualifier nobody has defined. Two readers would select different records.
Can AI do this?
AI does this partly Some of the tested AI models master this; others do not show it. 5 of 10 models master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.1-pro-preview | Flagship | 89% | Not shown |
| gpt-6-astra | Flagship | 100% | Mastered |
| claude-fable-5-1 | Flagship | 100% | Mastered |
| gemini-3.8-flash | Mid tier | 100% | Mastered |
| gpt-6.1-sol | Mid tier | 100% | Mastered |
| claude-sonnet-5-5 | Mid tier | 89% | Not shown |
| gemini-3.5-flash-lite | Low cost | 0% | Not mastered |
| gpt-6-luna | Low cost | 9% | Not shown |
| claude-haiku-5-5 | Low cost | 0% | Not mastered |
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 term and its competing meanings
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: "Store the address of every active customer." (active since when? by which measure?) Acceptable: "Store the address of every customer who holds an open account." Or keep active customer, mark it for the glossary and add an open_question until it is defined.
Also known as: Ambiguous term (data requirement)
Related knobits
Builds on
All 47 knobits of Capture data requirements.
Source: Review checklist 01-requirements, row 4; 29148 5.2.5 (unambiguous)