AI-Generated Slides: Are They Good? Can Students Tell?

2026-05-13 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Human-Computer Interaction · Depth: Expert, quick

Summary

A study investigated the quality and student perception of AI-generated slides created from instructor course notes, comparing an end-to-end education tool (NotebookLM), two general-purpose LLMs (Claude, M365 Copilot), and two coding assistants (Cursor, Claude Code). Educators first assessed the GenAI-generated slides for quality. The best slides, with some modifications, were then used in a real course to compare student perceptions against instructor-created slides. The research found that coding assistant tools produced the most accurate, complete, and pedagogically sound slides. Furthermore, students rated GenAI slides as being of similar quality to human-created slides and could not reliably identify AI-generated content. A negative correlation was observed between high quality ratings and high "AI-generated" ratings, suggesting students might associate lower quality with AI origins.

Key takeaway

For educators considering integrating AI tools into their instructional design, this research indicates that coding assistants like Cursor or Claude Code can produce high-quality, pedagogically sound slides. You should experiment with these specific tools to generate course materials, as students perceive their quality similarly to human-made slides and cannot reliably differentiate them. This suggests a viable path for augmenting your content creation process.

Key insights

AI-generated slides, especially from coding assistants, match human quality and are indistinguishable to students.

Principles

• Coding assistants excel at slide generation.
• Students cannot reliably detect AI-generated slides.

Method

The study involved narrative assessment of AI-generated slides by educators, followed by using selected slides in a real course to compare student perceptions of human vs. AI-generated content.

In practice

• Explore coding assistants for slide creation.
• Integrate GenAI into instructional design workflows.

Topics

• AI-Generated Slides
• Instructional Design
• Generative AI Tools
• Student Perception
• Educator Perception

Best for: Research Scientist, AI Scientist, Domain Expert, AI Product Manager

Related on AIssential

• Use model-to-model comparison to improve code quality — Comparing AI-generated code with a dedicated AI reviewer improves code quality and architectural consistency.
• Best AI Creators in 2026: Why Finding the Right Artificial Intelligence Creator Matters More Than… — Effective AI learning shifts from searching videos to discovering trusted, high-quality expert creators.
• Can AI Tools Transform Low-Demand Math Tasks? An Evaluation of Task Modification Capabilities — AI tools show moderate success in upgrading low-demand math tasks, with generative modification distinct from classification.
• 5 Free AI Tools to Understand Code and Generate Documentation — AI tools significantly streamline code comprehension and documentation generation for developers.
• Interact with agent-created visualizations in canvases — Agent-created canvases transform text-based AI interactions into interactive, visual data explorations.
• Can AI tools assess coding assignments? — Generative AI can assist in coding assignment assessment when integrated thoughtfully with human expertise and context.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.