The author reports that prompt phrasing and the specific foundational model had secondary impact on final material quality compared with the structure of the workflow itself.¶

Claim · All claims
Evidence · 1 study · design r2 · q1
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q1 i? The exact phrasing of prompts and the choice of foundational model (e.g., Gemini or DeepSeek) had secondary impact on final quality relative to the workflow structure. → Henrique Mohallem Paiva 2026

Evidence¶

Henrique Mohallem Paiva 2026¶

Henrique Mohallem Paiva. (2026). Curriculum as Code: An AI-Assisted Architecture for Instructional Design in STEM Education. https://arxiv.org/abs/2608.07364 doi:10.48550/arxiv.2608.07364

q1 · i? · design · r2

This is the author's interpretive observation from the validation phase, not a tested comparison; no quantitative contrast between models or prompt variants is reported. The article offers this as a suggested paradigm shift toward instructional architecture.

"A critical observation from the validation phase is that the exact phrasing of the prompts or the specific foundational model used (e.g., Gemini or DeepSeek) had a secondary impact on the final quality compared to the structure of the workflow itself."

Discussion¶

Related Claims¶

• At the test level, only Claude with interview or demographic prompts improved alignment on the relative autonomy index — related
• Interview-containing prompts increased response diversity for Claude and GPT, while Gemini diversified with demographic-only prompts — related
• Claude showed the highest alignment with human BREQ responses, and interview-containing prompts aligned better than baseline prompts — related
• Prompt settings and temperature settings have significant main effects on correlations among the three LLM chatbots — related
• GPT-4o and GPT-5.2 achieve higher accuracy and more fully correct answers on university IVDA multiple-choice questions than the smaller Mistral-7B and DeepSeek-R1 models — related
• Chain-of-thought and reasoning prompting significantly improve LLM proportional match with human-authored distractors over direct prompting on both math and science MCQs — related
• In the MM-04 workflow case, similar-looking model activity has different evidential validity: GPT-5.5 closes the evidence-to-action loop while GLM-5.1 leaves the assigned deck unchanged and Gemini-3.1-Pro misses required numeric or visual evidence — related
• Reasoning-capable model variants and chain-of-thought prompting yield no measurable improvement in either alignment axis for classroom evaluation — related
• FATE benchmarks rank Gemini 2.5 Flash highest among commercial AI tutors, with actionability weakest for all models — related