"Mark as Spam" to improvement spam detection over time

Manually using “mark as spam” should be able to learn over time what senders/key words/subjects could be considered spam. Ex. we often receive messages to do sponsored blog posts and we mark as spam. Based on the content of the message, it would be great for Intercom to learn what is more likely to be spam. I understand that Fin can be used for workflows, but then there is the added risk that something that is a legit email gets sent to spam.