The rapid growth of e-commerce has increased pressure on warehouses to efficiently manage a rising number of products and organize them onto shelves with speed and accuracy. In this scenario, automation has become crucial, especially with the implementation of goods-to-shelf (GTS) systems that reduce the need for human movement and enhance picking efficiency. Among these advancements, Autonomous Guided Vehicles (AGVs) emerge as a versatile and scalable option that can revolutionize traditional warehouse operations. This study examines the performance and scalability of AGVs by creating a detailed simulation model using FlexSim 25.0.2. The model reflects real-world classical warehouse dynamics through visually adaptable shelving systems, comprehensive order lists, advanced process flows, and dynamic rules for resource allocation that dictate robot actions. The simulation investigates various AGV deployment strategies and assesses key performance metrics such as order fulfillment time, robot usage, travel distance, and overall system throughput. The results indicate that employing the right number of AGVs significantly boosts warehouse efficiency by minimizing manual tasks, enhancing task distribution, and improving the system's overall responsiveness. Single-load robots demonstrated a balanced performance, while double-load robots provided greater capacity but risked creating bottlenecks when handling heavier loads. This research highlights the promise of AGV-driven automation in contemporary warehousing while also addressing the challenges of scaling these systems in intricate environments. The simulation-based methodology discussed here offers valuable insights for warehouse designers, managers, and researchers aiming to enhance logistics performance and move towards smarter, automated fulfillment systems.