The general-purpose platform scored higher in early EDBL stages while the education-focused platform scored higher in feedback-intensive iterative stages¶

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? C1 was stronger at identifying the problem; C2 received higher scores in evaluating and retesting, reflecting capacity for iterative refinement. → Karaismailoglu 2026

Evidence¶

Karaismailoglu 2026¶

Karaismailoglu, F., Surmeli, H., & Yildirim, M. (2026). Suitability of Artificial Intelligence Supported Lesson Plans from the Perspective of Science Education Experts. Journal of Science Education and Technology. https://doi.org/10.1007/s10956-026-10342-4

q2 · i? · qualitative · r2

Comparative expert evaluation of both plans across EDBL stages (Figs. 1 and 2). Bubble charts show C1's mean of 44.73 at Identifying the Problem versus C2's 46.00, and C2's 48.45 at Evaluating & Retesting versus C1's 42.55; the text states the contrast quoted here.

"While both scored highest for "Presenting the solution," C1 was stronger in early stages such as "Identifying the problem," whereas C2 received higher scores in feedback-intensive stages like "Evaluating and retesting.""

Discussion¶

Related Claims¶

• Both AI platforms received their lowest expert ratings in engineering skills, indicating a shared limitation in supporting iterative design competencies — related
• The education-focused AI platform (C2) received numerically higher expert ratings than the general-purpose platform (C1) across all eight overall quality criteria — related
• Expert plan preferences were split, with some experts preferring the lower-scoring general-purpose plan for its social-emotional emphasis — related
• Turkish-language prompts produced poorer EDBL alignment than English prompts, revealing a linguistic equity limitation of AI lesson-planning tools — related