​@Harry Gardner  Very interesting question, I would love to jump on a call and see some of these queries to see if we can pinpoint a way to help make this easier without having to build workflows to handle this. 

In my experience working with Fin AI with customers, it often ends up pointing to a gap in help center content in some way that leaves Fin answering more generically or irrelevant answers. 

Another thing to pay attention to, is if the answers may be Custom Answers as well that are triggering based on a keyword -- we’ve seen this as well where a vague question might actually be triggering a Custom Answer instead of an AI answer and that’s the source of the issue. 

One quick suggestion, is in these scenarios does the user tend to click Talk to a Person? If so, having Fin follow up with asking them to share more info that will be helpful to the human agent can be useful because Fin can also reply to that and get things more on track.  That’s something we’ve found quite useful too in getting to a resolution after the first message.  

I do think Workflows can be helpful but I feel like looking at the types of queries could present some other interesting ideas, like adding some snippets/prompts to address things you want Fin to consider if something isn’t clear etc. 

Hope this helps, my calendar link is in the signature below if you’d like to connect. 

Hi ​@Nathan Sudds 

Thanks so much for taking the time to share this helpful info, really helpful food for thought, 

I have also booked in for a call this Friday. 

Thanks again. :) 

You could improve Fin AI's handling of vague queries by setting up triggers based on keywords or message patterns that identify ambiguity. This way, Fin can ask for clarification before providing an answer.

​@Nathan Sudds  Do you have any suggestions for setting up this kind of workflow? We are also having this challenge where the answer is vague, but technically correct and the customer asks to talk to an agent.