Agentic education · Learning science

Actionable companion · Accessibility & inclusion

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

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Age / stage not established. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Abstract 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. Keywords: Artificial intelligence, AI, Agentic workflow, Scenario design, Healthcare simulation, Automation, N8n, ChatGPT, INACSL standards, ASPiH standards

What kind of evidence is this?

Agentic & multi-agent systems · Design / feasibility study

Stage: Age / stage not established. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Limitations and uncertainty · source passage

Despite its advantages, this implementation demonstrated several inherent limitations. First, the system remained entirely contained within the ChatGPT environment, restricting its integration with external systems and workflows, and limiting its content knowledge to a maximum of 12 documents. Second, it relied exclusively on the OpenAI models, preventing exploration of alternative LLM architectures potentially better suited for specific aspects of scenario design. Third, the system lacked connectivity with document creation tools, necessitating manual export and formatting of generated content. Finally, its outputs were limited to text, precluding the automatic generation of visual elements that could enhance scenario fidelity and learner engagement.

Design the system before the pilot

Document the agent goal, available tools, memory, planning loop and stopping rule. Test tool calls in a sandbox and require human approval for external actions. A multi-agent debate is not independent verification when agents share the same failure modes.

  • Co-design accommodations with learners and specialists. Check access and error burden across groups without inferring subgroup effectiveness from small or unreported samples.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Federico Lorenzo Barra; Giovanna Rodella; Alessandro Costa; Antonio Scalogna; Luca Carenzo; Alice Monzani; Francesco Della Corte. From prompt to platform: an agentic AI workflow for healthcare simulation scenario design. Advances in Simulation (2025-05-16). https://doi.org/10.1186/s41077-025-00357-z

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.