Recognises a record class mixing different retention
Record types needing different retention in one class.
Can AI do this?
Not settled yet The benchmark tested this, but the models' answers do not settle yet whether they master it. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 82% | Not shown |
| gemini-3.5-flash-lite | Low cost | 72% | Not shown |
| gpt-6-luna | Low cost | 82% | Not shown |
| claude-haiku-5-5 | Low cost | 82% | 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 class and the types to separate
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: RC-004 "Loan correspondence" holds signed agreements and marketing letters Acceptable: Agreements and marketing correspondence in separate classes
Also known as: Class mixing different retention
Related knobits
Builds on
- C-153 Explains retention as a property of a record class
- C-151 Explains records classification by business activity
Usually followed by
All 14 knobits of Inventory the records and build the file plan.
Source: Review checklist 01-file-plan, row 5 (15489 8.3, 8.5)