Behavior FAQ

Guidance on writing effective behavioral rules, channel filtering, and handling edge cases.

Answers to common questions about behavioral rules including best practices, examples, channel and language filtering, and planning for risky scenarios. See Behavior for full documentation.

What are global rules?

Global rules set consistent agent behavior across all interactions. Use them for tone, scope, and task-specific instructions.

Examples:

• “Always remain professional and empathetic, even when the customer is frustrated.”
• “Only answer questions about [service]. For anything else, say: ‘I can only help with [service]-related questions.’”

How long should global rules be?

Keep global rules concise so the model can follow them consistently.

Best practices:

• State the most important rules first.
• Combine overlapping rules into a single, clear instruction.
• Remove redundant or contradictory rules.
• Regularly audit your rules against actual agent behavior using conversation review.

Should I include examples in global rules?

Yes – specific examples are more reliable than general instructions. The more concrete you are about what the agent should say, the more consistently it will follow the rule.

Instead of: “Be empathetic.”

Use: “When a customer expresses frustration, respond with empathy before problem-solving. Example: ‘I completely understand your concern, and I want to make sure we get this sorted for you.’”

Can I apply rules to specific channels or languages?

Yes. You can use channel and language tags to filter content and rules. Each tag requires a matching closing tag (</channel> or </language>):

• <channel:voice>...</channel> – applies only to voice calls
• <channel:webchat>...</channel> – applies only to webchat
• <channel:sms>...</channel> – applies only to SMS
• <language:en>...</language> – applies only to English interactions

Closing tags are always plain </channel> or </language> – never </channel:voice> or </language:en>. Tags can be nested, e.g. <channel:voice><language:en-US>Call 1-800-...</language></channel>.

This is useful for multi-channel agents (where voice and chat may need different handling) and multilingual agents (where certain phrases or instructions only apply in specific languages).

How should I handle small talk, silence, and broken input?

These are common patterns that benefit from explicit global rules:

• Small talk: “If the user makes small talk, briefly acknowledge and redirect to the task.”
• Silence / no input: “If the user does not respond, prompt them once, then offer to transfer to an agent.”
• Broken or unintelligible input: “If you cannot understand the user’s request after two attempts, offer to transfer to a human agent.”

These rules help the agent handle real-world edge cases that are especially common in voice interactions.

How should I plan for risky scenarios?

Identify high-risk situations (like refunds, cancellations, or emergencies) and add clear rules or dedicated topics.

Example for refunds: “Route all refund-related queries to a support specialist.”

Always test risky scenario handling in sandbox before deploying to production.