This study presents a flexible and user-centric Explainable AI (XAI) framework for e-commerce product recommendation systems, emphasizing transparency, adaptability, and user engagement. Traditional recommendation systems often function as opaque “black boxes,” where users are unaware of the rationale behind suggestions, potentially impacting trust and user satisfaction. To solve this problem, we describe an adaptive XAI framework that tailors the explanation to fit the user’s level of expertise. This will be done by classifying users into novice, intermediate, expert, and advanced users with domain-specific knowledge. Feature importance scoring, Local Interpretable Model-agnostic Explanations (LIME), and attention maps will be employed to tailor explanations fitting the user’s level of understanding and preferences. Our approach strengthens user trust, promotes digital literacy, and improves the user experience generally. We implemented BERT transformers on a recommendation dataset and have achieved better similarity scores (above 0.9) between input user queries and recommendations. They have been presented to users at different knowledge levels through XAI integration.