Explainable Artificial Intelligence (XAI) has become crucial in addressing the opacity of complex AI models, aiming to enhance transparency, accountability, and trust. However, creating XAI systems that effectively elucidate intricate models and their decision processes remains challenging. This research introduces an innovative approach that harnesses Model-Driven Engineering (MDE) techniques to design and implement explainable AI systems. By synthesizing MDE principles with XAI concepts, we present a structured, model-based framework for developing transparent and interpretable AI models. Guided by the Design Science Research (DSR) methodology, we develop and demonstrate our proposed solution. Our framework addresses the limitations of post-hoc explanations by integrating explainability into the core design of AI systems. This approach enables real-time explanation generation alongside predictions, ensuring consistency between model behavior and explanations, while offering domain-specific adaptability. Through a detailed design process and a case study in recommender systems, we demonstrate the practicality and efficacy of our MDE-based XAI approach. This research contributes to the advancement of XAI by introducing a model-driven perspective and providing a versatile framework applicable across various AI domains. Our work paves the way for more transparent, interpretable, and trustworthy AI systems, addressing a critical need in the evolving landscape of artificial intelligence.