Scientific discovery is an iterative process that requires transparent reasoning, empirical validation, and structured problem-solving. This work presents a novel human-in-the-loop AI system that leverages case-based reasoning to facilitate structured scientific inquiry. The system is designed to be note-centric, using the Obsidian note-taking application as the primary interface where all components, including user inputs, system cases, and tool specifications, are represented as plain-text notes. This approach ensures that every step of the research process is visible, editable, and revisable by both the user and the AI. The system dynamically retrieves relevant cases from past experience, refines hypotheses, and structures research workflows in a transparent and iterative manner. The methodology is demonstrated through a case study investigating the role of TLR4 in sepsis, illustrating how the system supports problem framing, literature review, hypothesis formulation, and empirical validation. The results highlight the potential of AI-assisted scientific workflows to enhance research efficiency while preserving human oversight and interpretability.