Executive Summary
A SaaS company recently engaged Manceps to develop and deploy an AI-powered Interactive Voice Response (IVR) System to help them improve the speed and accuracy of their customer service phone system. By deploying an end-to-end solution that integrated with existing datasets, the organization was able to offer its customers an extremely powerful AI-powered agent who could answer all sorts of questions, troubleshoot their issues, and otherwise anticipate their unique needs.
The Problem
Despite sophisticated advancements in smart assistants like Apple’s Siri and Amazon’s Alexa, interactive service agents have yet to provide a customer experience that doesn’t leave most users frustrated. To be sure, automation can save customer support teams significant capital; however, most organizations have to balance the cost savings with the inevitable degradation of the customer experience.
When our client came to us, their existing phone system connected with customers to an endless forest of menu options that increasingly failed to provide the type of positive customer service their paying subscribers had come to expect. Furthermore, a lack of nuance in their system meant that once their customers finally reached a live agent, the phone tree had failed to sort them to the correct department.
Special Requirements
Unstructured Documentation
A successful interactive agent needed to be able to tap into a variety of unstructured documents such as knowledgebase articles or FAQs in order to deliver the customer exactly the right information they need. The solution we built needed to seamlessly blend these resources with the agent to prevent the need for complex and ongoing integrations.
Sentiment Analysis
The client needed our solution to easily surface frustrated customers in order to provide them with a higher-touch experience and reduce churn.
Analytics
Managers needed a way to assess the success and efficiency of their customer service teams without listening to hours of customer interactions or relying upon the customers to participate in post-call surveys, a rare occurrence.
Integration
This new system needed to play nicely with their chosen VOIP service. Additionally, they wanted the ability to roll-out these interactive capabilities to other points of customer interaction such as their on-site chatbot and email teams.
