AI
Sort by:
Trending
Status:
Showing 85
21
VOTE
[accuracy] AI tagging accuracy improvements (more training, negative/positive reinforcement, audit ...)
Actions requests from the admin to improve the accuracy Guidance to write good tag description Suggest negative reinforcement for AI tagging (either raising it to the admin or training the AI) Let user flag good examples of conversations that shou...
0
Backlog
8
VOTE
6
VOTE
[context] AI compose with a prompt and message template
Situation: Users need to respond quickly to messages, especially when dealing with simple inquiries. While the Suggested Reply feature is useful, it can be difficult to control the exact content or appropriateness of the response, and it doesn’t s...
0
Backlog
6
VOTE
3
VOTE
[accuracy] Option to reuse the message samples used for training after a tag deletion
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...
0
Backlog
5
VOTE
[context] AI to "understand" images (summary, similar conversation, tagging, suggested replies & AI answer ...)
Request: AI features to be multi-modal, meaning they could understand images within the content they are based on. For example, SimilarConversation could recommend a conversation that includes a similar image, AI tagging could classify content bas...
0
Backlog
5
VOTE
[package] Automatic CSAT from conversation analysis
Context: Understanding customer satisfaction is important for our business, however, today's approaches are too imperfect: Survey : asking users directly. Response rate low (1-3%) and polarized (super happy or frustrated) Not representative of all...
0
Backlog
6
VOTE
[granularity] AI summary at the contact and account levels
See a summary of conversations with a specific contact See a summary of conversations with a specific customer/account review all email correspondence with the client account list all references to the word 'transfer pricing' with date, subject he...
0
Backlog
4
VOTE
[accuracy] Similar conversation based on a more specific entity (inquriy, ticket, order, shipment ...)
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...
0
Backlog
7
VOTE