The proliferation of anime content poses a challenge for enthusiasts and newcomers alike in discovering shows that cater to their preferences. This paper introduces a novel Large Language Model (LLM) chatbot designed to streamline the process of anime discovery and recommendation. Leveraging state-of-the-art natural language processing techniques, the system interprets user inquiries and provides personalized content based on an extensive database of anime metadata. The chatbot incorporates a user-friendly interface deployed through a web application, enhancing the user experience with rich visual content and interactive elements. Initial testing has indicated a high degree of accuracy in the chatbot's recommendations and positive user engagement. The development process, from concept to deployment, including design considerations, system architecture, and the choice of technologies, is detailed in this paper. The outcomes suggest that the integration of LLMs into recommendation systems can significantly improve content discoverability and user satisfaction.