Prompt engineering is the most prevalent customization method in AI writing education research¶

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

Subclaims¶

q2 i? Across 23 reviewed studies, prompt engineering (N = 13) was the most common customization approach, followed by fine-tuning (N = 7) and hybrid architectures (N = 3). → Luo 2026

Evidence¶

Luo 2026¶

Luo, Y. (2026). Customizing AI for writing pedagogy: a systematic review of pedagogical goals, theoretical principles, and technical design. Education Tech Research Dev. https://doi.org/10.1007/s11423-026-10697-w

q2 · i? · quant-synthesis · r2

Systematic review frequency analysis of customization methods across 23 empirical studies (2020–2025), reported in the RQ2 findings section. The review states "Prompt engineering was the most prevalent approach", with fine-tuning (N = 7) and hybrid architectures (N = 3) less common.

"Prompt engineering was the most prevalent approach. In these studies, pedagogical alignment was achieved by designing task- or role-specific instructions that constrained model outputs without altering internal parameters."

Discussion¶

Related Claims¶

• Technically oriented theoretical rationales are operationalized more often than learning-centered theories in AI writing customization — related
• Structural misalignment: learning-oriented goals are predominantly operationalized through performance-driven theories and modular customization — related
• Six implementation modes operationalize customized AI writing systems, with standalone evaluation most common — 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