I’m facing an issue with Zendesk AI intent detection and webhooks. I have AI intent detection enabled, and the intent is successfully detected on the ticket (I can see the system tags and the intent/confidence in the ticket events).
I am trying to send the detected intent to an external system via webhook. My webhook body looks like this:
{
"ticket_id":"{{ticket.id}}",
"action":"{{ticket.ticket_field_33209525892626}}",
"intent":"{{ticket.ticket_field_option_title_33190930229522}}",
"tags":"{{ticket.tags}}",
"intent2":"{{ticket.ticket_field_33190930229522}}",
}
The problem is:
- Sometimes the webhook receives the correct intent.
- Other times, the webhook fires but the intent field is empty.
- In the ticket events, I can see that AI intent detection
My questions:
- What is the recommended way to ensure the webhook only fires after AI intent detection is completed?
- Is there a guaranteed event or condition that indicates AI processing has fully finished?
- Is mapping AI intent directly to a custom field the most reliable approach, and if so, what trigger conditions should be used?
Any guidance on the correct trigger configuration for a reliable setup would be greatly appreciated.
Thanks in advance!
Zendesk’s AI intent detection runs asynchronously and may not complete immediately after a ticket is created or updated, causing triggers that fire too early to miss the intent data. To ensure your webhook reliably includes the detected intent, it’s best to create a trigger that watches for the AI intent system tags added once detection finishes and then maps that intent into a custom ticket field. You can then configure your webhook to fire only after this custom field is populated or updated, avoiding premature executions. This two-step process—detect AI intent via tags, map to a custom field, and trigger webhooks based on that field—ensures the webhook only fires after intent detection is complete and provides a consistent and reliable integration.