Our customers are asking questions that are answered by diagrams within our knowledge. However, it seems FIN only can interpret images provided by users in the chat session. Adding the ability to use images in knowledge would be a crazy game changing multiplier for us.
Here’s the answer I got back from FIN when asking…
Fin can interpret images uploaded by users during conversations, but not images you upload as knowledge, due to how Fin Vision is designed. Fin Vision is specifically built to analyze images sent by customers in chats or emails, helping to diagnose issues faster and understand visual content like error messages or screenshots.
On the other hand, Fin doesn't analyze images within your support content, such as those embedded in articles or documents you upload as knowledge sources. It only processes images actively sent by customers during conversations. This limitation ensures that Fin focuses on real-time customer interactions rather than static content in your knowledge base.