AI-Guided Inquiry Learning (AGIL): A Pedagogical Synthesis for Computational Drug Discovery Education

AbstractThe integration of artificial intelligence into pharmaceutical sciences creates both educational opportunities and pedagogical challenges. Tools such as AlphaFold, ESM-1v, and neural network-enhanced docking algorithms have democratised computational approaches previously accessible only to specialists, yet frameworks for teaching students to use these tools critically remain underdeveloped. This manuscript presents AI-Guided Inquiry Learning (AGIL), a pedagogical framework synthesising Process Oriented Guided Inquiry Learning (POGIL), Just-in-Time Teaching (JiTT), and flipped classroom methodology while introducing AI as an active learning partner requiring systematic verification against primary sources. AGIL addresses both student learning and instructor scalability: AI serves as a teaching partner for faculty, automating the feedback loops that make approaches like POGIL and JiTT effective but traditionally unsustainable. The framework's five defining characteristics—AI as inquiry partner, verification as core learning outcome, three-exposure learning cycle, documented AI interaction, and AI as teaching partner—position students to develop both domain expertise and transferable meta-skills. AGIL is instantiated in a 14-week computational drug discovery curriculum featuring 20 guided inquiry notebooks across a six-target therapeutic portfolio, with empirical evaluation planned for Spring 2026.