Recognises an unapproved production refresh
Production data copied with no approver or record.
Can AI do this?
AI does this partly Some of the tested AI models master this; others do not show it. 2 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 91% | Mastered |
| gemini-3.5-flash-lite | Low cost | 42% | Not shown |
| gpt-6-luna | Low cost | 92% | Mastered |
| claude-haiku-5-5 | Low cost | 89% | 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 defect named on the refresh of production data without the owner's approval, and its fix or the question for its owner
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: EV-003 weekly refresh, refresh_approval: null Acceptable: Each refresh approved by the data owner and logged
Also known as: Unapproved refresh
Related knobits
Builds on
All 15 knobits of Plan environments and capacity.
Source: Review checklist 02-environments-capacity, row 8 (27002 8.33)