This paper presents an innovative approach that combines robust optimization and artificial intelligence (AI) to enhance the logistical management of blood products within the Inventory Routing Problem framework. Robust optimization ensures resilient decision-making in the face of demand uncertainty, which is a persistent and critical issue in healthcare logistics. On the other hand, AI refines demand forecasts by integrating historical and contextual data, thereby improving predictive accuracy and relevance. The Inventory Routing Problem is designed to synchronize inventory management and transport planning in order to ensure a reliable supply while minimizing logistics costs. A key challenge lies in demand uncertainty, which can lead to critical shortages. AI plays a pivotal role by dynamically adjusting uncertainty intervals in robust optimization, as opposed to conventional approaches that rely on fixed margins. This synergy enables real-time adaptation of deliveries, storage, and resource allocation, thereby enhancing the responsiveness and efficiency of the logistics system.