The demand for cybersecurity professionals with advanced static analysis expertise has grown exponentially, driven by the increasing sophistication of malware, advanced persistent threats, and nation-state cyber attacks. Our project provides a design and implementation of an innovative static analysis course that integrates large language models (LLMs) to enhance student learning and engagement. Our approach leverages LLMs as intelligent assistants within a Capture The Flag (CTF) framework, enabling students to collaborate with LLMs to solve complex binary analysis tasks. We present our course structure, AI facilitation process, and evaluation results, highlighting how LLM integration impacts students’ understanding of reverse engineering and symbolic execution concepts, how students adapt their learning strategies when working with LLMs, and cons and pros of LLMs in reverse engineering. This report provides valuable insights for educators seeking to incorporate LLMs technologies into cybersecurity curricula, addressing both technical and motivational challenges in static analysis education.