The vehicle spare parts recommendation system has been designed with a user-centered approach, ensuring an intuitive and efficient experience. This system utilizes an artificial intelligence model that, through advanced natural language processing (NLP) techniques, interprets user-described vehicle issues in everyday language. By doing so, it accurately identifies the necessary spare parts, considering critical factors such as the vehicle’s make, model, and year. To power the AI model, a robust and structured knowledge base was developed, integrating key information about spare parts, common issues, and specific compatibilities. This knowledge base was built using techniques like Retrieval-Augmented Generation (RAG) and web scraping, enabling the collection and organization of large volumes of relevant data from multiple reliable online sources. Additionally, the system was designed with a focus on accessibility and usability, optimizing every interaction to provide accurate and personalized recommendations tailored to users’ specific needs. This approach not only enhances user satisfaction but also ensures that the spare parts selection process is faster and more reliable.