Explains BI requirements gathering
Requirements stated as decisions, audiences and business questions, then measures, dimensions, grain, timeliness and history (DMBOK2 ch. 11; Kimball, The Data Warehouse Toolkit).
Can AI do this?
AI does this well Most of the tested AI models master this. 4 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 100% | Mastered |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | 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: Requirements stated as decisions, audiences and business questions, then measures, dimensions, grain, timeliness and history (DMBOK2 ch. 11; Kimball, The Data Warehouse Toolkit).
How it is assessed: Answers a written question on the decision-based BI requirement correctly
Related knobits
Needed for
- G-532 Raises a decision for its owner instead of taking it
- W-101 Recognises a report request with no decision
- W-105 Recognises an existing report requested under a new name
- W-106 Recognises a chart requested instead of a question
- W-107 Recognises a BI requirement with no audience
- W-131 Restates a BI request as a decision and a question
All 13 knobits of Capture BI requirements.
Source: Practice the stage 1 reference and review checklist rest on