Evaluating a Zero-Shot GenAI Assistant for Clinical Record Writing in Nursing Education

Abstract

Objective: This study evaluated a zero-shot prompting approach for generating pedagogically appropriate AI feedback to support nursing students’ reflective record writing. A generative AI system was developed using GPT-4o, with prompts carefully crafted to reflect ethical, instructional, and contextual principles relevant to clinical practicum education. The system was developed following the ADDIE framework, and its evaluation focused on assessing the quality and educational value of the AI-generated feedback.

Methods: Three nursing faculty members independently reviewed 126 AI-generated responses using a 5-point scale based on clarity, relevance, and educational appropriateness. Items scoring less than 5 were revised, and a second round of evaluation was conducted.

Results: The proportion of responses rated 5 increased from 65.7% to 94.0% after prompt refinement, confirming that even minor adjustments—such as clarifying vague instructions or reinforcing ethical boundaries—had a measurable impact. Inter-rater reliability was moderate (ICC = 0.58), reflecting diverse faculty perspectives—a feature aligned with the contextual complexity of nursing education. The conservative scoring approach, in which the lowest score was adopted per item, ensured that potential pedagogical risks were not overlooked.

Conclusions: These findings suggest that zero-shot prompting offers a practical and scalable method for aligning generative AI systems with educational goals, even without training data or programming expertise. Rather than positioning AI as a replacement for instructors, this study frames GenAI as a formative support tool shaped by educator input. Future work should assess real-world implementation with students to examine usability, personalization, and effectiveness in authentic practicum environments.