Safety & Refusal
Refusals that explain and redirect, moderation interruptions, and confidence-qualified answers.
Components
3 components availableRefusal Message
How to say no without ending the conversation — the refusal, a plain-language reason, and one redirect the reader can click.
Moderation FlagWhat to show when the content filter fires — a stopped stream that keeps its partial text, or a blocked prompt, with a false-positive path.
Confidence AnswerAn answer that says how sure it is — a warning badge only when there is something to warn about, and a hedge that names what to verify.