AI

Front could build a copilot or in-app reporting powered by AI that ingests and analyzes Front conversations/Support tickets/sales transcripts to produce useful and actionable Support/Product insights. The AI can report the most common feature requ...

Situation: The current “similar conversation” feature in Front is based on semantic proximity. This approach can be inefficient, especially when users need to find conversations related to specific entities like a ticket number, order number, ship...

Show the conversation summaries when it can help understand what a conversation is about, across the app so a user can work faster. For example, showing the summaries on conversation previews in the inbox view the search view linked conversation t...

Similar conversations lack of accuracy.Ideas: Allow to remove "similar" results and use this as training signal to improve the accuracy

Want to connect my own AI directly inside Front. Things like AI assistant/co-pilot that works within Front . listen and build a context about the conversation assist: suggest best resources keep conversation on track by nudging agent to detect ext...

The training of AI tagging takes too much time because it doesn't have enough sample messages to review.

Case: after tag deletion Situation: Currently, when an admin deletes an AI tag from an AI tagging rule, the associated message samples used for training are also removed. If the admin wishes to add the tag back, they must go through the process of...

Situation & Request Wish to tag based on spec values such as dates, amounts, and durations. Currently, the AI Tagging tool is not equipped to detect and apply tags based on these structured data types. Potential Solution Invest in entity detec...

Jerry Services has multiple internal KBs depending on what insurance company their customer uses - i.e. Geico, FarmersInsurance, Progressive. This brought up an idea where in the future, can we connect multiple KBs to use for AI answers and depend...