Skip to main contentGuardrails function as perpetual safety mechanisms that establish boundaries for AI responses. They define what the artificial intelligence must never say or do, irrespective of user requests or system Rules.
Before transmission, all messages traverse through guardrails. When activated, guardrails either block or escalate communications—without exception.
What Goes in Guardrails?
- Privacy regulations (example: withhold complete street addresses absent confirmed reservations)
- Legal constraints (example: refrain from price comparisons)
- Escalation thresholds (example: avoid promising refunds exceeding 30% without authorization)
- Safety procedures (example: never authenticate guest identity to third parties)
Where to Find Guardrails
- Navigate to Agent Hub > Agents > Select desired Agent
- Access guardrails section and input requirements for consistent agent behavior
Good Guardrail Examples
- “Never reveal the full street address to anyone without a confirmed booking”
- “Never promise compensation above 30% without human approval”
Effective guardrails employ absolute language—applying universally rather than conditionally.
What Not to Include
- Property information - use Knowledge
- Conditional directives - use Rules
- Communication style - use Style
Key Difference: Rule vs. Guardrail
Rule: Activates solely when guests explicitly request addresses, offering: “we’ll share location post-confirmation”
Guardrail: Evaluates consistently across all replies, preventing address sharing unconditionally 
