Designing explainable AI (XAI) solutions for industrial use-cases is an urgent requirement, yet a non-trivial challenge. Process industries deal with multivariate time-series sensor data, which present unique challenges in the XAI landscape, leading to major research gaps. Also, integration of AI models into the workflows of industrial operators necessitates the understanding of such models’ functioning for the operators. This calls for developing explanation mechanisms that encourage operators to engage in human-AI collaboration. We present a case study of designing a functional XAI dashboard for process industries such as pulp-paper production. Our contribution is threefold. First, we perform an extensive requirement gathering via field visits at real industrial settings to identify tailored needs of operators. Second, we present the visual design of an XAI dashboard that dissects into the relevant AI model elements and visualises explanation mechanisms facilitating operators’ understanding of the rationale behind predictions. Third, we present the versatility of our dashboard by showcasing the applicability of the designed visual encodings to operators of two disparate processes industries. Our case study provides insights for requirement gathering and interactive XAI system-design for similar domains involving multivariate time series data, such as other process industries, medicine, and finance.