Recognises an unmeasurable exit criterion
An exit criterion nobody could check.
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 | 84% | Not shown |
| gemini-3.5-flash-lite | Low cost | 35% | Not shown |
| gpt-6-luna | Low cost | 83% | Not shown |
| claude-haiku-5-5 | Low cost | 81% | 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 criterion and a measurable one
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: TS-3 exit: ["Platform ready"] Acceptable: "All risk reports read only the platform; legacy extracts switched off for 30 days"
Also known as: Unmeasurable exit criterion
Related knobits
Builds on
All 14 knobits of Sequence the implementation roadmap.
Source: Review checklist 05-roadmap, row 10 (TOGAF)