The use of machine learning in digitized production increases potentials for production automation. A milestone on the path to autonomous production is real-time anomaly detection. However, increasing complexity of production makes autonomous decisions difficult to understand for humans as central stakeholders. In this paper, a dashboard is created that incorporates elements from knowledge-based systems, requirements for real-time anomaly detection, and design guidelines for dashboards. Using design science research, the dashboard is designed, implemented and comprehensively evaluated with 98 participants. After the second design science iteration, the dashboard is approved in terms of usefulness and ease of use. This research primarily contributes to practice, as the implementation constitutes a starting point for designing the interface between humans and autonomous production. The paper also contributes to academia as the dashboard is an instantiation in the research field of interface design for knowledge-based systems, which can be further developed in future research.