Skip to main content
Answered

Advice Needed: Improving Fin AI Responses to Vague Queries

  • 5 December 2024
  • 4 replies
  • 74 views

Hi there,

We’ve implemented Fin AI (Chat and Email) on our support desk, and it’s been fantastic so far—it’s doing a great job handling first-line queries! 😊

However, we’ve noticed a challenge when a customer submits a vague message. Fin will respond with technically correct information, but it’s often not relevant to what the customer truly needs.

I’m wondering if it’s possible to improve this by getting Fin to ask clarifying questions before responding. I’ve been advised to set up a new workflow where specific vague questions prompt Fin to ask follow-ups, but trying to predict and account for all the potential vague queries customers might come up with feels inefficient.

Is there a better way to manage this? Any advice or insights you could share would be hugely appreciated!

Thanks so much

Best answer by Nathan Sudds

@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. 

View original
Did this topic help you find an answer to your question?

4 replies

Nathan Sudds
Expert User ✨
Forum|alt.badge.img+5
  • Top Expert
  • 283 replies
  • Answer
  • December 9, 2024

@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. 


  • Author
  • New Participant
  • 1 reply
  • December 10, 2024

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. :) 


Nur Nahid
Super User ✨
Forum|alt.badge.img+3
  • Super User ✨
  • 95 replies
  • December 10, 2024

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.


John Pjontek
  • New Participant
  • 1 reply
  • December 12, 2024
Nathan Sudds wrote:


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.  

 

@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. 


Cookie policy

We use cookies to enhance and personalize your experience. If you accept you agree to our full cookie policy. Learn more about our cookies.

 
Cookie settings