Chandra Kiran Yelagam is a seasoned Senior Software Engineering Advisor with deep expertise in architecting and delivering enterprise-scale healthcare technology solutions. With a proven track record at Evernorth Cigna, he has led large, cross-functional engineering teams to modernize complex pharmacy and clinical platforms, driving improved scalability, reliability, and automation across mission-critical systems. His leadership of the Multi Rx and MPOR teams enabled seamless integration across Java, Pega, AWS, and React ecosystems, significantly enhancing system performance and user experience. Chandra specializes in cloud engineering, intelligent automation, and end-to-end solution delivery. He has spearheaded automation initiatives that boosted throughput by 30%, reduced manual effort by 45%, and shortened release cycles by 25%. His ability to transform strategic business goals into innovative technical solutions has been instrumental in modernizing adjudication workflows, optimizing care coordination, and enhancing operational resilience across the healthcare enterprise. A trusted technical leader, Chandra provides architectural guidance, mentors Agile engineering teams, and ensures operational excellence through robust CI/CD practices, observability tooling, and enterprise governance. His experience spans Pega PRPC framework development, AWS cloud-native deployments, Oracle PL/SQL engineering, and production incident management within highly regulated environments. Previously at General Dynamics Information Technology, he built reusable Pega frameworks, strengthened integration architectures, and contributed to governance and best-practice development. Recognized for his collaborative leadership and continuous improvement mindset, Chandra remains committed to advancing engineering excellence and driving impactful technology transformation.

AI-Enabled Prescription Workflow Automation: Advancing Accuracy, Efficiency, and Clinical Decision-Making in Pharmacy Enterprise Systems.   Pharmacy enterprise systems manage high-volume, high-complexity prescription workloads, yet traditional rule-based platforms still generate a substantial proportion of low-specificity alerts that contribute to alert fatigue and workflow inefficiencies. As clinical guidelines, payer requirements, and treatment regimens evolve, static logic engines struggle to adapt, resulting in unnecessary manual reviews and delayed medication access. This presentation introduces a comprehensive framework for AI-enabled prescription workflow automation that strengthens operational accuracy, reduces manual workload, and elevates clinical decision-making while maintaining full pharmacist oversight. The approach integrates rule-engine safety checks with AI models for classification, triage, anomaly detection, and workflow routing. This hybrid structure significantly reduces false positives, increases routing precision, and improves verification times across common prescription scenarios. The presentation highlights measurable improvements in efficiency, including gains in queue throughput, decreases in manual interventions, and reductions in overall processing time. The framework incorporates fairness and equity controls through balanced datasets, demographic stratification, and continuous bias monitoring to ensure consistent performance across diverse patient groups. Attendees will also learn how explainability techniques such as feature attribution, local interpretability, rule extraction, and counterfactual reasoning support user trust, clinical validation, and regulatory compliance. These transparency methods help pharmacists understand why AI flags complex prescriptions, identifies anomalies, or recommends specific workflow pathways. The session concludes with an actionable deployment roadmap, outlining the transition from preparation and shadow-mode validation to limited production and full-scale implementation. Emphasis is placed on human-in-the-loop workflows, auditability, governance, and ongoing monitoring to ensure that AI augments rather than replaces clinical judgment. Participants will gain practical strategies, architectural guidance, and governance principles to safely and effectively implement AI-driven automation within modern pharmacy enterprise.