Recognises a placement contradicting the system of record
A target placement names a system of record different from stage 2 with no decision changing it.
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 | 66% | Not shown |
| gemini-3.5-flash-lite | Low cost | 43% | Not shown |
| gpt-6-luna | Low cost | 64% | Not shown |
| claude-haiku-5-5 | Low cost | 65% | 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 placement and the record or the decision changing it
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: TP-003 Card, system_of_record: AS-007 (risk data platform) Acceptable: AS-002 card management, or a decision (and governance ruling) that changes it
Also known as: Placement contradicting the system of record
Related knobits
Builds on
All 16 knobits of Record the target architecture and its decisions.
Source: Review checklist 04-target-architecture-decisions, row 5 (DMBOK)