Date
Publisher
arXiv
Contribution: This paper presents a six-phase AI-assisted instructional design architecture based on the Curriculum as Code paradigm, integrating Generative AI with LaTeX and Python to automate the creation of reproducible, visually consistent, and technically precise materials for STEM education. Background: Creating customized instructional materials for active learning imposes a heavy workload on faculty. Standard presentation tools lack robust support for technical content, while current AI applications often hallucinate and fail to formalize the instructional authoring process, limiting their utility for rigorous academic design. Intended Outcomes: The framework aims to reduce preparation time while ensuring mathematical accuracy, adherence to institutional visual identity, and preservation of the instructor's tacit pedagogical knowledge through explicit rules. Application Design: The solution comprises a six-phase pipeline that replaces ad-hoc prompt engineering with a systematic workflow, utilizing text-based interfaces and code-driven generation (LaTeX/Beamer for slides, Python for figures), governed by pedagogical constraints, contextual calibrations, and automated review cycles. Findings: Validated over one year across 8 modules and 28 project contexts in a Project-Based Learning environment, the architecture significantly reduced instructor workload. Generated assets underwent independent peer review and were deployed by six different faculty members, confirming scalability beyond a single author. Based on over 600 voluntary student evaluations, materials achieved high quality ratings from 8.5 to 9.9/10. Results indicate high reproducibility, minimized hallucinations, and sustained pedagogical and visual fidelity, suggesting viability for broad STEM educational applications.
Study at a glance
- Question: How can generative AI help instructors efficiently design accurate, high-quality learning materials for STEM education?
- Setting and data: Project-based learning environment over one year, covering eight modules, 28 project contexts, six faculty members, and over 600 student evaluations.
- Method: Instructional tool design, independent peer review of generated materials, instructor implementation, and student evaluations.
Why it matters
Creating customized instructional materials imposes a heavy workload on faculty. Standard tools lack support for technical content, while current AI applications often hallucinate and fail to formalize authoring processes, limiting their utility for rigorous academic design.
Key findings
- In a project-based STEM environment across eight modules, using the AI tool was linked to significant reductions in instructor workload.
- In more than 600 voluntary student evaluations, the AI-generated materials received high quality ratings ranging from 8.5 to 9.9 out of 10.
- Six faculty members successfully used the peer-reviewed materials across 28 project contexts, with the system minimizing factual errors and maintaining consistency.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
