Identify the best PRD update when an AI feature has an unstated fallback behavior.
Legal has asked how the assistant behaves when it cannot safely answer. Which move makes the PRD reviewable instead of leaving the AI fallback as an implementation guess? Add a fallback requirement with trigger, user-facing behavior, and acceptance criteria before sign-off. Right. PRDs align teams by defining observable product behavior and success criteria. AI fallback is part of the user experience, so it belongs in the requirement. Tell engineering to handle low-confidence cases during implementation. Weaker. That treats product behavior as a private technical decision and violates the PRD principle of shared understanding across stakeholders. Approve the PRD and ask…
Sign up free: one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in