Skip to main content

Learning Design

Attribution

Original work: "Educators' guide to multimodal learning and Generative AI" — Tünde Varga-Atkins, Samuel Saunders, et al. (2024/25) — CC BY-NC 4.0
Adapted for UK Nursing Education by: Lincoln Gombedza, RN (LD)
Last Updated: December 2025

Learning design is the process of choosing the right "modality" of AI to match the educational goal identified in the Needs Analysis.

1. Choose the AI Modality​

Depending on the module, you might choose one or more of these modalities:

  • AI as a Personal Tutor: Students use AI to explain complex concepts (e.g., "Explain the RAAS system like I'm a first-year student").
  • AI as a Clinical Simulator: Students interact with an AI-driven "patient" to practice history taking or de-escalation skills.
  • AI as a Feedback Bot: Students submit a draft care plan or reflection and get instant, formative feedback based on specific rubrics.
  • AI as a Creative Partner: Students work with AI to generate patient education visuals or clinical metaphors.

2. Structure the Prompting Strategy​

Educators should provide students with "Scaffolded Prompts" rather than letting them start with a blank screen. This ensures clinical safety and pedagogical focus.

Example Structured Prompt for Students:

"You are an AI patient named Arther, a 65-year-old with heart failure. I am a student nurse performing a nursing assessment. Only answer from Arthur's perspective. Do not provide medical advice. Wait for me to ask my first question."

3. Human-in-the-Loop (HITL) Design​

Crucially, some parts of the activity must remain human-centric:

  • The Briefing: Educator explains the purpose and the AI's limitations.
  • The Interaction: Student engages with the AI tool.
  • The Debriefing (Critical): A group or individual session to discuss what the AI got right, what it got wrong, and how it felt to use it.

4. Multimodal Integration​

Consider how different types of AI can work together:

  • Text AI: To generate a case script.
  • Image AI: To generate a photo of the "wound" or the "patient's environment" based on that script.
  • Voice AI: To "speak" the patient's lines during a simulated handoff.

Next: Once the design is ready, follow the Implementation Guide for a smooth rollout.