Problem AI tagging accuracy cannot be fine-tuned — admins have no way to provide negative reinforcement, flag good examples, or audit tag predictions, and the AI mispredicts on signatures and forwarded content. Request Add training and feedback to...
Problem The AI tagging rule has limited trigger capabilities. It doesn't support triggers for new inbound conversations only, conversation moves, outbound conversations, or comments. This prevents customers from efficiently auto-tagging all conver...
Problem AI tagging is not available on SMS conversations, chat, social media, WhatsApp, and custom channels. Request Extend AI tagging support to SMS, chat, social media, WhatsApp, and custom channel types.
[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...
Problem Manual tagging is time-consuming, but fully automatic tagging is not trusted without human review. Request Display AI-generated tag suggestions for conversations that the team can review and validate before applying.
[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...
Problem When an AI tagging model is trained, it only applies to new incoming conversations. Previously received conversations don't get retroactively tagged with the trained sentiment or AI tags. Request Apply trained AI tags retroactively to prev...
Problem AI tagging model training is slow because it has insufficient sample messages to learn from. Request Improve the AI tagging training process to work effectively with fewer sample messages or accelerate training.