The escalating challenge of antimicrobial resistance (AMR) necessitates innovative approaches to optimize antibiotic selection. We propose a research initiative focused on integrating artificial intelligence (AI), surveillance data, and comprehensive literature to develop a clinical decision support system (CDSS) tailored for use across all levels of healthcare. Our primary objective is to address the complexities of antibiotic treatment for WHO-designated critical and priority organisms by leveraging the vast, diverse data landscape. This project is driven by the need to navigate multiple guidelines, literature and surveillance data from databases such as Paratek-Keystone, Pfizer-Atlas, and Venatorx-Gears to guide the treatment of these organisms. However, the sheer volume of information presents significant challenges for clinicians and policymakers in synthesizing and summarizing evidence-based decisions efficiently. Our proposed CDSS aims to consolidate these data sources into a cohesive platform that leverages AI to analyze, summarize, and present actionable insights. By integrating real-time surveillance data with up-to-date literature, the system will provide users with a comprehensive overview of current evidence, facilitating informed decision-making at both the bedside and policy levels. The envisioned system will support clinicians in selecting optimal antibiotic regimens by delivering tailored recommendations based on the latest research and surveillance trends. Furthermore, it will empower healthcare administrators and policymakers by offering strategic insights into AMR patterns and treatment efficacy, thus enhancing the overall healthcare response to this global threat. By merging AI with existing surveillance and literature resources, our initiative seeks to transform the landscape of clinical decision-making, fostering a more responsive and effective approach to combating antimicrobial resistance.