Make the AI Visibly Corrigible
The AI should be correctable without defensiveness.
Capture
Domain users may notice errors the AI misses.
The AI should be correctable without defensiveness.
Why
This decision matters because make the AI Visibly Corrigible constrains the product toward continuity, evidence, and human judgment rather than broad AI helpfulness.
Why-Not
Describe the philosophy. Keep exact memory update behavior private.
Commit
Decision: The AI should be correctable without defensiveness.
Describe the philosophy. Keep exact memory update behavior private.
Public boundary: This ADR publishes the judgment and product boundary while withholding exact prompts, routes, thresholds, schemas, tests, and other reproducible implementation details where applicable.
Confidence: Medium-high for public architecture; implementation details remain private and subject to launch evidence.
Timestamp
2026-07-17