<p>This paper presents a user application that streamlines the virtual tire development process by incorporating both subjective and objective tire evaluations, size information, and target performance values. The tool leverages a content-based filtering recommendation system and DBSCAN clustering to address the challenge of sparse subjective data and to identify optimal vehicle performance domains that align with drivers’ evaluations. Monte Carlo simulations are then employed to validate the reliability of these target domains. An AI-based meta-model, consisting of a Radial Basis Function (RBF)-based handling prediction model and an XAI-enhanced energy efficiency prediction model, captures the relationship between MF tire parameters and key performance indicators, such as rolling resistance coefficient (RRC) and wet grip index (WGI). This approach enhances interpretability and ensures that the tool provides clear insights into how input variables influence output performance. Finally, a differential evolution (DE) optimization algorithm is employed to generate virtual tire models that satisfy the multi-constraint performance requirements. Overall, this application offers a practical and flexible solution for tire designers to efficiently explore the design space and develop tires that meet both performance and energy efficiency targets.</p>