Replace Disclaimers With Behavioral Boundaries

Capture

Many products provide broad suggestions followed by:

• consult a teacher;
• use caution;
• seek professional help.

Safety disclaimers are insufficient if the model can still generate unrestricted advice.

Why

This decision matters because replace Disclaimers With Behavioral Boundaries constrains the product toward continuity, evidence, and human judgment rather than broad AI helpfulness.

Why-Not

The disclaimer does not constrain the preceding behavior.

Exact governing contract and enforcement wording.

---

Commit

Decision: Safety disclaimers are insufficient if the model can still generate unrestricted advice.

Safety is not a paragraph beneath the answer. It is a constraint on what kinds of answers the system is allowed to produce.

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