Sales Intelligent Agents
The telco clients, wanted to automate the sales process through an intelligent agent to provide a 24×7 service and help customers find products & services information easily. The intelligent agent had to be multichannel, so customers could communicate with the telco clients via web, Slack, Telegram, or WhatsApp. Also, the system should be able to redirect the conversation to a human agent in case customer was not happy or preferred to be helped by a human agent.
Sigmas’s Intelligent Agent is multichannel and multilingual, learns from conversation examples, and continuously monitors sentiment and intent.
Sigma’s Intelligent Agent is based on DNNs. It is customized in two steps: Training of the basic system, and monitoring and fine tuning. First, existing or artificially created conversations are used to train the basic system. Later, a human agent monitors the performance and corrects dialogues with customers typically for a month. Finally, the new dialogues are used to fine tune the system incrementally. In this way customers have a good user experience from the beginning. It monitors sentiment, so as to transfer the call to a human agent if it detects that a customer is having a negative experience.
It combines text conversation with menus, graphics and images, so it makes conversations very intuitive and efficient.
The system handles over 60% of the conversations and transfers the rest to human agents, who receive typified conversations with the collected information. It has increased sales by 17% and has reduced the duration of conversations by 52%. The ROI was less than 1 month.