0% helpful
0 likes 0 dislikes
Inputs Required
Model/system limitations; uncertainty patterns; key failure modes; brand/legal requirements; user trust risks; UX flows (where AI appears); feedback channels.
Output Artifact
1-page UX policy: disclosure language, confidence/uncertainty cues, citations/source rules (if applicable), refusal/fallback behavior, user control (edit/undo), feedback/reporting, and “don’ts.”
When to use this
When users might overtrust the AI, or when inconsistent UI behavior (confidence, citations, refusals) would damage trust and adoption.
Link copied