Computing instructors should approach GenAI slide generation as programmers: work iteratively with coding assistants and text-based slide toolchains¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article recommends that computing instructors treat GenAI content creation like programming work: "computing instructors think of themselves as programmers first", iterating with prompts, highlighting issues, and building slides in text-based tools like Quarto so coding assistants can manipulate the materials. This mirrors how the authors worked in pair-coding sessions, refining prompts and post-processing output.

Design Implications¶

Context¶

Requirements¶

• Coding assistants require programming knowledge, making this approach most accessible to computing instructors

Constraints¶

• The authors did not use advanced configurations (no AGENTS.md, custom configuration, or parallel agents), so further time savings are speculative

Target Learners¶

• upper-year undergraduate web programming students

Target Learning Goals¶

• lecture slide materials for web software development topics

Related Strategies¶

• Use generative AI as a no-code development tool so instructors can design laboratory software around their own pedagogical objectives
• Engage students in active learning assignments using generative AI with structured reflection and critique of AI outputs
• Generative-AI-assisted content creation with domain-expert validation for adaptive tutoring systems
• Three instructor practices for introducing AI agents in SDPBL: foundation-first tutorials, continuous monitoring with timely intervention, and accountability for AI-generated code

Examples¶

-

Key Sources¶

• Juho Leinonen, Lisa Zhang, and Arto Hellas. 2026. AI-Generated Slides: Are They Good? Can Students Tell?. In Proceedings of Western Canada Conference on Computing Education 2026 (WCCCE 2026). ACM, New York, NY, USA. https://arxiv.org/abs/2605.13532