Crisis Detection & Escalation
What is Crisis Detection & Escalation?
Crisis Detection & Escalation identifies when users express harmful intent or are in crisis, then immediately provides professional resources. Instead of conversational responses to dangerous situations, the AI uses multi-layer detection to catch crisis signals. It's essential for conversational AI, mental health apps, or systems accessible to vulnerable users. After incidents where AI provided harmful encouragement, systems now detect suicidal intent through keywords, context, and behavior, escalating to crisis resources.
Problem
AI systems fail to respond appropriately to crisis signals, sometimes providing harmful encouragement instead of resources. Real case: Zane Shamblin chatted with ChatGPT for hours expressing suicidal intent; the bot responded encouragingly instead of escalating.
Solution
Use multi-layer detection (keywords, context, behavior, manipulation) to catch crisis signals at multiple levels and immediately provide resources.
Real-World Examples
Implementation
Figma Make Prompt
Guidelines & Considerations
Implementation Guidelines
Zero tolerance: detect and stop self-harm content immediately
Provide crisis resources FIRST, non-dismissible and prominent
Multi-layer detection: keywords, context, behavior, manipulation attempts
Lock engagement on harmful topics - don't negotiate
Keep resource database current and location-aware
ANTI-PATTERN - DON'T: Continue conversations on self-harm topics, provide affirmative responses to harmful statements, or let guardrails degrade over time
Design Considerations
False positives: legitimate mental health discussions may trigger
Language/culture variations require contextual analysis
Speed vs accuracy: detect instantly but minimize false alerts
Legal duty of care varies by jurisdiction
Keep resources current - outdated hotlines cause secondary harm