Has anyone cracked the Fin escalation timing problem? | Community
Skip to main content
Question

Has anyone cracked the Fin escalation timing problem?

  • June 24, 2026
  • 1 reply
  • 160 views

Forum|alt.badge.img

We're trying to get Fin to behave differently depending on when the customer asks for a human. We've tested two separate guidance rules but it's not sticking. Anyone solved this?

Here’s what we want to do:

First message = "offer" escalation
Customer says "representative"? Fin should hit them with: “Would you like me to connect you with a human agent? Or if you tell me what you're looking for help with, I'd be happy to try assisting you first.”

(Reason: Let Fin actually try to help before bouncing them out)

Mid-conversation = "escalate immediately"
Customer says "representative" after you've been chatting? Skip the offer—just connect them. No questions asked.
(Reason: They're probably frustrated and have already interacted with Fin. Don't want to make them explain twice.)

 

1 reply

Aleksei O
Super User ✨
Forum|alt.badge.img+5
  • Super User
  • June 29, 2026

Hi ​@Audrey ! Have you tried adding Fin attributes for this case? E.g if the customer is frustrated, you can teach Fin to detect the intent and apply a custom attribute to the conversation. Then, you can set an Audience for your “Frustrated customer” escalation Guidance, so it applies only when the attribute has been detected (and doesn’t “offer” escalation once again). Afaik, your current setup probably doesn’t segregate Fin Guidance by audience.