Researchers have introduced a novel approach to AI game programming, utilizing large language models to build upon Claude Shannon's taxonomy of game-playing machines. At the core of this approach is Nemobot, a dynamic environment that allows users to design, tailor, and deploy game agents powered by large language models, while interacting with AI-driven strategies1. This paradigm enables the creation of strategic AI gaming agents for interactive learning, facilitating a more immersive and engaging experience. By leveraging large language models, Nemobot enhances the capabilities of game agents, allowing for more sophisticated and adaptive gameplay. The introduction of Nemobot has significant implications for the development of AI-powered games, as it enables users to craft customized game agents that can learn and adapt in real-time. This matters to practitioners because it has the potential to revolutionize the field of AI game programming, enabling the creation of more intelligent and interactive game agents.