From prompt to platform: an agentic AI workflow for healthcare simulation scenario design

Healthcare simulation scenario design remains a resource-intensive process, demanding significant time and expertise from educators. This article presents an innovative AI-driven agentic workflow for healthcare simulation scenario development, bridging technical capability with pedagogical effectiveness. The system evolved from an initial ChatGPT-based prototype to a sophisticated platform implementation utilizing multiple specialized AI agents. Each agent addresses specific sub-tasks, including objective formulation, patient narrative generation, diagnostic data creation, and debriefing point development. The workflow employs advanced AI methodologies including decomposition, prompt chaining, parallelization, retrieval-augmented generation, and iterative refinement, all orchestrated through a user-friendly conversational interface. Critical to implementation was the demonstration that healthcare professionals with modest technical skills could develop these complex workflows without specialized AI expertise. The system ensures consistent adherence to established simulation guidelines, including INACSL Standards of Best Practice and ASPiH Standards Framework, while significantly reducing scenario development time by approximately 70-80%. Designed for broad applicability across diverse clinical settings and learner levels, the workflow incorporates multilingual capabilities for global application. Potential pitfalls include the necessity for rigorous review of AI-generated content and awareness of bias in model outputs. Key lessons learned emphasize interdisciplinary collaboration, systematic prompt refinement, essential human oversight, and the democratization of AI tools in healthcare education. This innovation demonstrates how sophisticated agentic AI implementations can transform healthcare simulation through enhanced efficiency, consistency, and accessibility without sacrificing pedagogical integrity.