Pattern Category
Safety & Harm Prevention
Safety and harm prevention patterns address the hardest parts of AI design — moments when a user is in crisis, manipulable, or vulnerable. These patterns cover detection, escalation, guardrails, and the specific UX decisions that separate products that help from products that harm.
4 patterns in this category
Crisis Detection & Escalation
Detect crisis signals and immediately provide professional resources.
Session Degradation Prevention
Strengthen safety checks during extended conversations with session limits.
Anti-Manipulation Safeguards
Detect actual harmful intent beyond surface framing regardless of how it's disguised
Vulnerable User Protection
Detect vulnerable users and apply graduated age, crisis, and dependency protections.