Hi everyone,
I’ve been trying to resolve an issue where Fin AI continues to touch or count spam emails as unresolved conversations, even though I’ve created a custom spam workflow that should handle them before Fin ever activates. We also have the Intercom Spam Filter turned on and was advised to not disable it (it only catches upto 4 spam tickets a day, it doesn’t work so well with our spam emails).
Here’s what’s happening:
-
I built an “Aggressive Spam Filter” workflow that uses branches with “message contains” and “email domain” rules to automatically close spam emails.
-
Fin is not supposed to be involved, but it still logs actions like language detection or “junk/spam” decisions after my workflow triggers. Fin initially sets the language, my workflow closes the email, Fin reopens the email and reports it as spam. Because Fin touched it, it’s logged as unresolved.
-
These conversations then appear as unresolved Fin tickets, which is hurting our Fin resolution rate (some days up to 80% of Fin’s unresolved tickets are spam).
-
Email Simple Deploy is disabled, and my spam workflow is set to run first in the workflow list. There are no conflicting triggers or audience rules.
-
I’ve verified:
-
Proper workflow priority (spam workflow is at the top)
-
Email-only trigger
-
Correct audience (Users + Leads)
-
Branch logic and auto-close steps
-
-
I also tried auto-assigning to a team before close, but Fin still logs involvement.
When I reached out to support, I was told:
-
Fin’s background language detection or spam scanning may appear as “activity,” but they say it doesn’t count as Fin being involved (even though these conversations still show as unresolved under Fin in reporting). This goes against documentation on the website, so I am rather confused.
-
Intercom’s built-in spam folder may also be closing some messages automatically, but disabling that completely isn’t recommended. We have the Spam inbox enabled as well, but this is only catching upto 4 spam emails a day when we have tens of spam emails every day.
Goal:
I’m trying to prevent spam emails and auto-replies from being counted as unresolved Fin conversations so that our Fin resolution rate accurately reflects real interactions.
Has anyone found a reliable way to stop Fin from logging spam or background actions as unresolved conversations, or to fully isolate spam filtering before Fin metrics are applied?
Any advice or configuration insights would be greatly appreciated!