What are Guardrails?
Guardrails are the safety net for your AI agents. They define boundaries and trigger actions when those boundaries are approached.Two Types
Escalation Rules
Define when the agent should stop and hand off to a human: Examples:
When an escalation rule triggers:
- Agent stops processing
- Sends an appropriate message to the customer
- Creates an internal note with context
- Routes to human queue
Restrictions
Define absolute limits on what the agent cannot do: Examples:
Restrictions are the highest priority — they’re checked before anything else.
Priority Order
Guardrails are evaluated in this order:Detection Methods
Guardrails can detect triggers using:Testing Guardrails
Each guardrail includes a built-in playground:- Open the guardrail configuration
- Enter test messages
- See if the guardrail triggers
- Refine detection criteria
Guardrails vs Guidelines
Guardrail: “Never discuss competitor pricing” → Blocks the topic
Guideline: “Be professional and helpful” → Shapes all responses
Common Guardrail Patterns
Safety Net
Catch situations that need human judgment:- Angry or threatening language
- Legal or compliance topics
- Account security concerns
- Complex edge cases
Brand Protection
Prevent brand damage:- Competitor discussions
- Unauthorized promises
- Confidential information
- Off-brand responses
Compliance
Meet regulatory requirements:- Privacy requests (GDPR, CCPA)
- Financial advice disclaimers
- Medical/legal limitations
- Age-restricted content
Next Steps
Escalation Rules
Define when to hand off
Restrictions
Set hard limits