Tags let the AI automatically categorize incoming messages so your team can filter, prioritize, and act on the right conversations. The tag description is what tells the AI when to apply a tag, so writing a clear, specific description is the difference between tags that work and tags that create noise.
Writing Tag Descriptions
A vague description leads to over-tagging (the tag fires on conversations it shouldn’t) or under-tagging (it misses conversations it should catch). The goal is a description specific enough that the AI knows exactly when to apply the tag and when not to.
Be Specific About What Qualifies
Describe the exact situation, not a general category. Include the type of message, the context, and the intent behind it.
Bad: “When a guest has a problem”
Good: “When a guest reports that something in the unit is physically broken, damaged, or not functioning correctly. Examples: broken appliance, leaking faucet, damaged furniture, malfunctioning AC or heater.”
Include Negatives (What Shouldn’t Be Tagged)
Adding explicit exclusions prevents the AI from over-applying a tag to similar but unrelated conversations. Think about the most common false positives and call them out.
Bad: “Guest wants to change their reservation”
Good: “When a guest requests to change their check-in date, check-out date, or number of guests on an existing reservation. Do NOT apply for new booking inquiries, cancellation requests, or questions about availability.”
Use Concrete Examples
Give the AI a few real-world message examples so it understands the language guests actually use, not just the abstract category.
Bad: “Refund request”
Good: “When a guest asks for money back or compensation for their stay. Examples of guest messages: ‘I’d like a refund,’ ‘Can I get my money back,’ ‘I think I deserve a discount for the issues.’ Do NOT apply when a guest is simply complaining without requesting compensation.”
Good vs Bad Tag Descriptions
Example 1 - Access Issues
Bad: “When a guest can’t get in”
Good: “When a guest reports they cannot physically enter the property, the unit, or a specific room. This includes lockbox code not working, smart lock failures, keys not in the expected location, and gates or doors not opening. Do NOT apply for guests asking what the access instructions are before arrival.”
Example 2 - Early Check-In
Bad: “Guest wants to check in early”
Good: “When a guest asks to arrive or access the unit before the standard check-in time. Do NOT apply when a guest simply asks what the check-in time is, or when they confirm they will arrive at the scheduled time.”
Example 3 - Noise Complaint
Bad: “Noise issue”
Good: “When a guest reports excessive noise affecting their stay, such as loud neighbors, construction, street noise, or noise from shared spaces. Do NOT apply when a guest asks about general noise levels in the area before booking, or when a neighbor or third party reports noise from the guest.”
Example 4 - Payment Issue
Bad: “Problem with payment”
Good: “When a guest reports a failed charge, double charge, unexpected charge, or billing discrepancy. Examples: ‘My card was charged twice,’ ‘I see an extra fee I wasn’t expecting,’ ‘My payment didn’t go through.’ Do NOT apply for refund requests (use the Refund Request tag) or general pricing questions.”
Tips
- Start broad, then narrow down. Write the tag description, then think about every situation where it might incorrectly apply. Add exclusions for each.
- Think from the guest’s perspective. Guests don’t use your internal terminology. Describe the tag using the language guests actually use in messages.
- One tag, one purpose. If your description covers two distinct situations, split it into two separate tags.
- Test with the Test Tags feature. After writing a description, use the Test Tags feature in your chat agent to send sample messages and verify the tag applies when it should and doesn’t when it shouldn’t. Iterate on the description until it’s accurate.
Use the Test Tags feature in Agent Hub to validate your tag descriptions. Send sample messages that should trigger the tag and messages that should not. Refine your description until the results match your expectations.
