A Study About Using a Cognitive Agent in Replacing Level 1 and 2 Service Desk Activities

Abstract

The radical change in technology and high customer expectations and demand are pushing the service desk to provide a competent service for the customers. And this service should be faster, more flexible and gives a more accurate response and high user experience. Replacing the human call agent’s activities with a cognitive agent could improve the user experience by providing a faster response to customer’s requests, removing the human errors and giving 24/7 support with less operational cost. The cognitive agent has the potential to scale personalized and tailored interactions. And this will provide business scalability. The paper’s goal is giving a study about the usage of the cognitive agent and automation to replace deterministic Level 1 and Level 2 service desk incidents. So, human service desk could focus on high-level tasks. All of these incidents are done according to static steps. These requests could be handled by a cognitive agent, which will be integrated with the current business systems. Now, there are many cognitive systems that help us to build cognitive agents like IBM Watson, Amazon LEX. During this study, we have selected IBM Watson as a cognitive system, IBM WebSphere as an integration middleware layer, BotKit as a Chatbot framework and logging the user interaction through tickets. Where most of the cognitive systems are cloud based, we have selected IBM Bluemix as a cloud platform. In addition, an initial reusable architecture has been proposed in this paper that is integrated with cognitive systems, back-end system, Chatbot framework, and different interaction channels.