Use AI to Flag Communications in Staircase with Sensitive Information for Review

One of our technical resources sent an email to a client that included a username and password for a particular item. We have Staircase turned on with the AI Follow-up feature that posts to the Gainsight Timeline. He was looking in Timeline later and he saw the email posted had the user/password info. I know Staircase has settings to filter out PII, but I am wondering if there is anything available or in the works to deal with a situation like what happened in this instance? I am thinking maybe the AI could "flag" these or notify the user in some way before posting them?