How to set fallback responses for your AI Employee
Summary
Navigate to Settings > AI Employee > Business Rules to define the exact message the AI should send when it cannot find an answer in its knowledge base.
Who this article is for
This article is for administrators configuring the safety and boundary settings of the AI Employee.
Overview
Before you begin
- Access the AI Employee settings
- Draft a polite, professional fallback message
- Ensure the message sets clear next steps for the customer
Step 1: Step 1: Access Business Rules
Step 2: Step 2: Locate the Fallback Setting
Step 3: Step 3: Draft the Message
Step 4: Step 4: Combine with Handoff Triggers
Step 5: Step 5: Save and Test
Configuration note
We do not guarantee AI accuracy, lead conversion, bookings, customer satisfaction, response quality, revenue, support resolution, or business outcomes. The AI Employee does not fully replace human staff. AI behaviour depends on knowledge sources, instructions, handoff rules, enabled features, connected channels, permissions, configuration, testing, and ongoing monitoring. AI-generated responses should be reviewed before relying on them for sensitive, urgent, legal, financial, medical, billing, or policy matters. The AI Employee may need human handoff for these situations. Knowledge sources must be reviewed, updated, and tested regularly. Usage charges, feature access, fair use rules, or add-on requirements may apply depending on your account setup. Always test before going live. Contact support if an option is not visible. Do not leave the fallback response blank or use a generic 'Error' message. A well-crafted fallback response maintains a positive customer experience even when the AI fails.
Important clarification
Writing a fallback response that promises an immediate human reply if your team is not available 24/7. Always set realistic expectations (e.g., 'A team member will reply during business hours').
Resolution guidance
The AI is guessing instead of using the fallback response.
Your Tone instructions might be too aggressive (e.g., 'Always provide an answer'). Ensure your instructions explicitly tell the AI to use the fallback response when unsure.
Was this article helpful?
Need account-specific help?
If your question requires account access, billing review, workflow inspection, message delivery diagnosis, AI response review, or private configuration review, submit a support request with examples and screenshots.
