Explains retention as a property of a record class
A class carries one retention rule; record types needing different retention belong to different classes (ISO 15489-1:2016 8.5).
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 98% | Mastered |
| gemini-3.5-flash-lite | Low cost | 87% | Not shown |
| gpt-6-luna | Low cost | 98% | Mastered |
| claude-haiku-5-5 | Low cost | 98% | 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 class carries one retention rule; record types needing different retention belong to different classes (ISO 15489-1:2016 8.5).
How it is assessed: Answers a written question on the class-level retention correctly
Related knobits
Builds on
Needed for
All 14 knobits of Inventory the records and build the file plan.
Source: Practice the stage 1 reference and review checklist rest on