Resource savings, sustainability and financial success are very closely linked to the lowest possible rework and scrap rate in production. Innovations in the measurement process, AI-based data analytics and adaptive quality control are not sufficiently represented in existing learning factory designs. The paper presents a scalable new solution to achieve the defined goals. The presented use case allows the detection of unsuspected systematic deviations when combining product quality data with operational process data. The “Advanced Quality Control” approach offers a hands-on learning opportunity in the execution of a manufacturing process and, at the same time, emphasizes the importance of capturing data that at first view seems irrelevant but is later important for root cause analysis. The key didactic elements are manipulated workpiece carriers that cannot be identified without a detailed final inspection (e.g. using a coordinate measurement machine). Manipulated carriers lead to misalignments of the workpiece during exemplarily a drilling process and therefor to a geometrical deviation. Using of smart factory infrastructure, robot-assisted drilling is utilized to achieve the required level of process accuracy and stability. An additional objective of the contribution is to facilitate understanding and implementation of quality principles in general. AI-based data analysis is being addressed as a teaching content.