Perceived improvement after prompt-engineering training was concentrated among students with little or no prior prompting experience¶

Claim · All claims
Evidence · 1 study · qualitative r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Students with little to no prior prompt-engineering experience reported a significant change in their Gen AI interactions after training, whereas students reporting no change cited previous experience or already using basic prompting techniques. → Lindsay Dawson 2026

Evidence¶

Lindsay Dawson 2026¶

Lindsay Dawson, N. Sanjay Rebello. (2026). Exploring Students' Perceptions of Using Generative AI-Assisted Problem Posing. https://arxiv.org/abs/2608.12523 doi:10.48550/arxiv.2608.12523

q2 · i? · qualitative · r2

Cross-cutting theme from the phenomenological analysis of the 49 students' reflections: novices to prompting "found a significant change in their interactions with Gen AI after the training video", while students reporting no change cited prior experience with Gen AI platforms or basic prompting habits.

"Students who had little to no prior experience with prompt engineering found a significant change in their interactions with Gen AI after the training video."

Discussion¶

Related Claims¶

• A majority of physics students (76%) perceived a positive change in their Gen AI interactions after prompt-engineering training — related
• Within prompt–response AI interfaces, students without guidance rarely move beyond prompt tuning, yielding interactions of limited educational value and increased reliance on outputs — related
• Students’ prompt self-efficacy increased significantly after the scaffolded GenAI course (t = 3.729, p < .001) — related
• Explicit training in constraint-seeking questions showed only moderate, non-generalizing benefits, whereas prompting explanation supports better question asking — related