Our project is an AI-powered natural language sports analytics engine that enables users to ask basketball statistics questions in plain English and receive accurate, data-driven insights. The system is built around a three-stage architecture: a natural language interpreter, a query execution layer, and an AI analysis module. When a user submits a question such as “Who were the top three players in assists last season?” the interpreter identifies intent, metrics, comparisons, filters, and time ranges. This structured interpretation is then translated into a database query that retrieves only the necessary data from our curated NBA statistics dataset. After the data is returned, the AI analysis module applies a flexible library of analytical functions to determine rankings, comparisons, aggregates, leaders, trends, or player-to-player evaluations. This layer focuses on performing the correct mathematical and statistical operations, allowing the system to handle phrasing like “best,” “most,” “top X,” or “who led the league,” independently of how the user expresses the question. The final result is reformulated into a clear, readable, conversational answer that mirrors the experience of speaking to a sports analyst. The goal of this project is to create an accessible, intuitive tool that lowers the barrier to sports analytics by removing the need for technical skills such as SQL or statistical modeling. Our system demonstrates how AI, data engineering, and natural language processing can be combined to make complex data exploration simple and interactive. This platform has potential real-world applications for sports fans, analysts, journalists, and team organizations seeking fast, reliable insights.