AI
Sort by:
Trending
Status:
Showing 80
3
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
4
VOTE
[context] AI answer for chat to support multiple KBs as source of knowledge
Situation: Currently, AI Answer for Chat only supports a single knowledge base, limiting its ability to draw from multiple sources of information. In scenarios where knowledge is spread across several external public knowledge bases, users cannot ...
0
Backlog
1
VOTE
1
VOTE
[granularity] Improve the granularity of summaries details to include the inquiry, steps taken, entities shared like conv_ID, error codes ….
The summary's structure and granularity don't match all use cases. Support agents need more specific information than a collaborator or manager joining a conversation
0
Planned
11
VOTE
[language] AI Answer to support more languages
AI-based features seem to support some languages but it's not guaranteed for many of them. cc https://help.front.com/en/articles/914304#prerequisites I'd be great if features like AI answer for chat, Suggested replies could leverage knowledge base...
0
Backlog
5
VOTE
Detect duplicate conversations & route them
Situation: Support teams can encounter multiple customer requests that are duplicates of previously resolved issues, leading to redundant work and decreased efficiency. Request: Implement a feature that automatically detects and flags duplicate cu...
0
Backlog
3
VOTE
[activation] Shared AI training for same tag across AI tagging rules
Situation: when I want to create an AI tagging rule for multiple inboxes, all using the same tag (e.g., VIP), I have to train the AI, by reviewing message samples, separately for each rule, even though it's the same tag. Request: Streamline the pr...
0
Backlog
5
VOTE
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
2
VOTE
[activation] have the training messages to respect the rule conditions
situation: If the rule conditions have a not from X, then it's confusing to have messages in the training messages not respecting the rule condition request: Respect the rule conditions for the selection of the message to review
0
Backlog