This chapter examines the crucial role of interpretable AI models in transforming manufacturing processes, the examination of the relationship between interpretability and extendibility within industrial settings is of particular significance. It begins by providing an explanation of how AI has evolved in the manufacturing sector, highlighting the need for interpretable AI in light of traditional manufacturing challenges. The discussion then explores the fundamental principles that underpin interpretable AI, carefully considering the trade-offs between transparency and accuracy, and elucidating various techniques for explainability. Additionally, the article discusses the concept of extendible AI frameworks, emphasizing their adaptability and scalability within industrial domains. It proceeds to showcase a broad range of applications for interpretable AI in manufacturing, including maintenance and quality control, supported by insightful case studies from the automotive, semiconductor, and food industries. Simultaneously, it addresses the existing challenges and envisions future directions, taking into account ethical considerations and regulatory requirements. Ultimately, the article synthesizes the key insights into a comprehensive conclusion, providing recommendations for promoting the adoption of interpretable AI models to enhance manufacturing efficiency, quality, and sustainability.