In a narrative educator assessment, coding assistants (Cursor and Claude Code) produced the most accurate, complete, and pedagogically sound slides from textbook chapters¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Educators rated Cursor and Claude Code as producing the most compelling slides among five GenAI tools, with Cursor rated accurate, complete, and strong in pedagogical soundness. → anchor-tool-assessment

Evidence¶

anchor-tool-assessment¶

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 doi:10.48550/arxiv.2605.13532

q2 · i? · design · r2

Narrative collaborative assessment by two computing educators plus the course instructor of slides generated for four web programming topics by five tools (NotebookLM, M365 Copilot, Claude, Cursor, Claude Code), summarized in Table 1; "the programming-based tools, Cursor and Claude Code, produced the most compelling slides".

"Overall, the programming-based tools, Cursor and Claude Code, produced the most compelling slides and are used in Section 4."

Discussion¶

Related Claims¶

• Automated verification of AI-drafted content produced mixed results: strong accuracy and integrity scores but only 5 of 10 chapters meeting the pedagogical-progression bar — related
• GenAI's default output on a take-home exam question remained at the quantitative, multistructural SOLO phase, producing polished but pedagogically thin responses — related
• Recurring risks of GenAI in STEAM education include hallucination, bias, superficial completion strategies, and compromised assessment validity — related
• Only 9 of 23 courses publicly named AI tools, with Claude Code, Cursor, and GitHub Copilot most frequent and a fragmented long tail — related