(Partial) Automation of an Online Customer Service

Development of an Intelligent Digital Agent for (Partially) Automated Response to Customer Inquiries

Project team

Prof. Dr. Mathias Klier
Patrick Bedué
Eleonore Graef
Roland Graef
Johannes Redl
Jan-Felix Zolitschka



Due to a sharp increase in the number of users in online forums, it is a major challenge to answer all customer inquiries quickly, in a personalized manner, and with consistently high quality. Companies must therefore look for new ideas and solutions that support the answering of customer inquiries in their forum using new methods and technologies.

With the project of developing an intelligent digital agent that supports insurers in making their online service efficient and customer-oriented, the University of Ulm, in cooperation with a large German insurance company, developed a new, innovative tool that supports online service employees in answering customer inquiries. The aim of the project was to investigate the extent to which the latest research can be used to revolutionize customer service to the benefit of the company and its customers in such a way that the next stage of digital transformation can be achieved.

The intelligent digital agent is designed according to the approach of case-based reasoning. This is an artificial intelligence methodology that successfully solves new cases based on similar cases that have already been answered. This methodology allows the digital agent to use knowledge from questions already answered in the forum, as well as from an additional insurance-specific knowledge base, to suggest automated answers to new customer queries. In order to continue to ensure at least consistent quality despite automated answer suggestions, agents check suggested answer options for correctness before making them available to the customer via the forum. Correctly solved customer inquiries are then transferred to the digital agent's knowledge base. In this way, the knowledge base grows with each additional question solved in the forum and the digital agent improves itself in a self-learning manner. By combining Case-Based Reasoning with a methodology developed specifically for online forums, an approach was designed that is adaptive as well as flexible and also enables a high-level increase in workflow efficiency.

The results of the project showed that the quality of the newly developed methodology already outperforms all previous approaches by at least 25 percentage points with the first two response suggestions. This enables employees to devote more of their working time to particularly challenging customer inquiries and answer them efficiently with the support of artificial intelligence. In addition, the digital agent ensures faster and more consistent responses to customer inquiries, further improving the service time and service quality perceived by customers.

Cooperation partner: German insurance company

Project period: July 2017 - January 2018


This pilot project demonstrates how close collaboration of researchers and practical experts and managers can result in the rapid development of a revolutionary prototype for practical use while laying the scientific foundation for promising research activities. While the researchers at the Institute of Business Analytics were able to gain visibility and reputation through corresponding research publications, the text-based digital agent developed within this framework serves as the basis for the company-wide implementation of a high-quality solution.