In a five-teacher pilot in a 160-student introductory programming course, teachers valued rapid process-level insight and the pilot drove iterative usability improvements¶

Claim · All claims
Evidence · 1 study (2 entries) · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Teachers using the tool in a 160-student introductory programming course appreciated the visual overview of activity types and clearly marked pauses, and reported that the tool helped identify largely copied solutions and incorrect or incomplete log files. → Heidi Taveter and Marina Lepp 2026 q2 i? Pilot feedback led to concrete usability improvements, including performance fixes for student switching, additional replay speeds of 15x and 30x, and red coloring of very short solving times below 10 minutes. → Heidi Taveter and Marina Lepp 2026 (2)

Evidence¶

Heidi Taveter and Marina Lepp 2026¶

Heidi Taveter and Marina Lepp. (2026). From Idea to Classroom in Days: Using “Vibe Coding” to Create a Programming Process Visualizer from IDE Activity Logs. https://arxiv.org/abs/2607.24757 doi:10.48550/arxiv.2607.24757

q2 · i? · design · r2

Teacher pilot in the Introduction to Programming course with 160 students and five teachers, with feedback gathered through informal teacher-led reviews and written comments. The article reports that "Teachers particularly appreciated the initial visual overview of different activity types and the clearly marked pauses" and that the tool helped identify cases where solutions were largely copied. No effect sizes are printed.

"The pilot was conducted in the “Introduction to Programming” course, which enrolled 160 students, and the tool was used by five teachers."

Heidi Taveter and Marina Lepp 2026 (2)¶

Heidi Taveter and Marina Lepp. (2026). From Idea to Classroom in Days: Using “Vibe Coding” to Create a Programming Process Visualizer from IDE Activity Logs. https://arxiv.org/abs/2607.24757

q2 · i? · design · r2

Iterative refinement during the same pilot: corrections were typically completed within a few days of feedback. Implemented changes included 15x and 30x replay speeds, red coloring of solving times below 10 minutes, and performance improvements for student-by-student review; a time-window selection suggestion was not yet implemented.

"Teachers also suggested adding a visual indicator in the “All people” view by coloring the solving time red when it is very short; this was implemented by coloring the text red when it is below 10 minutes."

Discussion¶

Related Claims¶

• The programming-process replay was the most prompt-intensive view to develop, requiring 31 prompts to work reliably and handle edge cases — related
• Teachers find ChatGPT a creative, fast, iterative brainstorming partner that adds specific numbers and details when posing math questions from photos — related
• Mathematics teachers appreciate ChatGPT-generated generative learning activities as hands-on, collaborative, engaging, open-ended, differentiated, and using multiple representations — related
• Student perceptions of GenAI feedback functionalities diverged, with some finding them redundant when feedback was perceived as clear — related
• Iterative advisory group feedback drove four framework iterations, including adding disruption and multi-level oppression — related
• Knowledge gained by self-analysis is more likely to produce constructive change in teaching than insights given by an observer — a broader claim this one bears on
• Identifying copy-typed sessions requires combining product and process views, since neither view is sufficient alone — related