This paper introduces the design and implementation of a rule-based expert system tailored to enhance academic decision-making for undergraduate mathematics students. The system integrates a structured knowledge base with a fuzzy inference engine, allowing it to deliver context-aware recommendations that support personalized learning pathways. Unlike conventional academic advising tools, this expert system draws on domain expertise and linguistic rules to simulate human-like reasoning, thereby improving accuracy in identifying academic difficulties and suggesting appropriate interventions. The model was validated through expert input and real student scenarios, demonstrating its potential to foster early academic support and optimize educational outcomes. Moreover, the system’s architecture confirms the viability of integrating artificial intelligence into higher education as a strategic tool to promote data-informed pedagogical decisions.