Plans the deliverables of a modelling assignment
A plan naming scope and boundary, the layers to deliver and their audiences, inputs, roles, review and schedule
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 | 89% | Not shown |
| gemini-3.5-flash-lite | Low cost | 10% | Not mastered |
| gpt-6-luna | Low cost | 89% | Not shown |
| claude-haiku-5-5 | Low cost | 91% | 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: A plan naming scope and boundary, the layers to deliver and their audiences, inputs, roles, review and schedule
How it is assessed: Given a retail banking modelling request (a new savings product), the plan bounds the scope, names every deliverable layer with its audience, locates the glossary and rules, and plans an independent review
Related knobits
Builds on
- K-912 Explains the planning of data modelling work
- K-901 Explains what data models are and why organisations build them
All 10 knobits of Plan the modelling and set its standards.
Source: DAMA-DMBOK2 chapter 5, element(s) DM-24: a performance at CDMP Practitioner level