Explains generated artefacts and their single source of truth
Generated files are rebuilt from the model and never edited; every fix goes to the deliverable owning the decision.
Can AI do this?
AI does this well Most of the tested AI models master this. 10 of 10 models master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.1-pro-preview | Flagship | 100% | Mastered |
| gpt-6-astra | Flagship | 100% | Mastered |
| claude-fable-5-1 | Flagship | 100% | Mastered |
| gemini-3.8-flash | Mid tier | 100% | Mastered |
| gpt-6.1-sol | Mid tier | 100% | Mastered |
| claude-sonnet-5-5 | Mid tier | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 100% | Mastered |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | 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: Generated files are rebuilt from the model and never edited; every fix goes to the deliverable owning the decision
How it is assessed: Routes sample fixes to the model, configuration, rule or deployment
Related knobits
Builds on
Needed for
- K-641 Routes a defect to the deliverable responsible for it
- K-801 Recognises generated SQL edited by hand
- K-802 Recognises DDL older than its model
- K-803 Recognises an object in the SQL missing from the model
- K-804 Recognises generator warnings carried without a decision
- K-806 Recognises a configured dialect left unregenerated
All 33 knobits of Generate and review DDL.
Source: Data-management practice used by the stage 8 reference and review checklist