Skip to main content

Hello!

 

I’m working on integrating Fin AI to our queries handling.

When conversations are handled by a teammate, we use a custom attribute “Subject Line” to ‘tag’ the query and report on volumes each week. Subject Lines would look like this:

hAccount] Login issue, gAccount] Change Email Address

rBilling] Refund Request

uGeneral] Query / Premium, /Feedback] Content

etc etc

 

If I want Fin to handle tickets, how can I get it to tag the conversation based on its content? either via our Subject Line attribute or via tags

At the moment, we have a workflow where users select what they want to talk about with buttons (“Question about my account”, “Help with my subscription”, “Share feedback”, “Something else”). Subscription queries go through Fin, the rests goes to a teammate. I’d like to open “Something else” to Fin AI too but I’d need to be able to tag the conversations properly to create usable data.

 

What’s the best practices here? What have you found the most helpful?

 

Hey ​@Andrea_ 👋 Jacques here from support engineering! I hope all is well :)

What you could do here is simply add a branch to your workflow to check the message content. Then if the content contains a specific word or phrase, you can tag it accordingly and then let Fin AI answer.

The workflow would look something like below 👇 Would that work for you or did you mean something different?

 


Hi ​@Jacques Reynolds , thank you for the reply and for the tips!

 

Does “message content” search through the user message only, or both the user’s and Fin’s? 

Most of the time, the first message isn’t very explicit, but when I used this tagging system with “customer sends any message”, I end up with too many tags on the ticket to make it relevant/useful. 

Do you have suggestions to navigate this better? 

Thanks!


Reply