Automated but Atrophied? Student Over-Reliance vs Expert Augmentation of AI in Learning and Cybersecurity

University students and working professionals are increasingly encountering generative artificial intelligence (AI) in education and practice, yet their approaches and outcomes differ markedly. This paper proposes an academic study contrasting novice over-reliance on AI with expert augmentation of AI, grounded in two real-world narratives. In one, a university student attempted to outsource learning entirely to AI, eschewing course engagement. In the other, seasoned cybersecurity professionals in the Tradewinds 2025 red/blue team exercise collaboratively employed AI tools to enhance (not replace) their domain expertise. This proposal outlines a comparative research design to investigate how students' perception of AI as a learning replacement versus professionals' use of AI as an expert tool impacts outcomes. Drawing on current literature in educational technology and workplace AI, we examine implications for curriculum design, AI literacy, and assessment reform in higher education. We hypothesize that blind reliance on AI can erode fundamental skills and academic integrity, whereas guided use of AI by knowledgeable users can amplify productivity without sacrificing quality. The paper details methodologies for classroom and workplace data collection, including student and professional surveys, interviews, and performance analyses. Anticipated findings aim to inform responsible AI integration in curricula, balancing innovation with the necessity of domain knowledge. We conclude with recommendations for pedagogical strategies, institutional policies to foster AI literacy, and a call for longitudinal studies tracking how AI usage during university affects professional competencies over time.