Reshaping Craft Learning: Insights from Designing an AI-Augmented MR System for Wheel-Throwing

The growth of media technologies and maker culture has expanded craft learning from instructor-guided models to diverse self-directed approaches. However, mastering crafts such as ceramics remains challenging due to their embodied nature and the difficulty of tacit knowledge transfer. While Mixed Reality (MR) and Artificial Intelligence (AI) have supported embodied task learning, their application in craft remains underexplored. We present an AI-augmented MR ceramic guiding system to investigate the interplay between these technologies and craft practices, including how they influence instruction design, shape user perception, and transform learning contexts. Our system provides immersive multimedia instruction and real-time shape-based feedback using computer vision and large language models (LLMs) to guide learners in wheel-throwing on a pottery wheel. Through a Research-through-Design process, we co-designed and evaluated the system with twenty novices and experienced ceramic practitioners. We offer design insights for AI-MR craft learning systems and identify opportunities to extend their application to creative, collaborative, and broader craft-making scenarios.