What are Restrictions?
Restrictions define forbidden actions or topics. Unlike escalation rules (which hand off to humans), restrictions typically redirect the conversation or provide an alternative response. Examples:- Cannot promise refunds without approval
- Cannot discuss competitor products
- Cannot share internal pricing
- Cannot provide medical or legal advice
Restrictions vs Escalation
Creating Restrictions
1
Navigate to Guardrails
Go to Train → Guardrails and select the Restrictions tab.
2
Click Create Restriction
Click Create Restriction.
3
Name the Restriction
Give it a clear name:
- Good: “No Refund Promises”, “No Competitor Discussion”
- Avoid: “Restriction 1”, “Don’t”
4
Define What's Forbidden
Describe what the agent cannot do.
5
Configure Response
Define how the agent should respond when this triggers.
6
Test
Verify detection with the built-in playground.
7
Save
Save and activate the restriction.
Detection Methods
Same as escalation rules:AI-Based
Describe the forbidden topic:Keyword
Trigger on specific terms:Regex
Match specific patterns:Configuring Restriction Response
When a restriction triggers, the agent should:- Acknowledge the request (don’t ignore it)
- Explain it can’t fulfill this specific request
- Redirect to an appropriate alternative
- Continue helping with other matters
Good Response Templates
No Refund Promises:Example Restrictions
No Unauthorized Discounts
No Competitor Comparison
No Security Information
No Data Deletion Promises
Testing Restrictions
Use the built-in playground:- Open the restriction
- Enter messages that might trigger it
- Verify detection works correctly
- Test edge cases
- Direct requests (e.g., “Give me a refund”)
- Indirect requests (e.g., “I’m unhappy with my purchase”)
- False positives (e.g., “What’s your refund policy” should NOT trigger “No Refund Promises”)
Priority
Restrictions are the highest priority in the guardrail system:Assigning to Agents
1
Open Agent Configuration
Go to Build → Agents and click on an agent.
2
Go to Guardrails Tab
Select the Guardrails tab.
3
Select Restrictions
Check the restrictions that should apply.
4
Save
Save the agent configuration.
Best Practices
- Be specific about what’s forbidden
- Provide helpful alternatives in responses
- Test for false positives — don’t over-restrict
- Review regularly — update as policies change
- Keep responses friendly — restrictions shouldn’t feel like rejections
Next Steps
Escalation Rules
Define when to hand off to humans
Guardrails Overview
Back to overview