Participants used the Flowcode LLM across all stages of their design process, most frequently asking for code explanations¶

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

Subclaims¶

q2 i? Lab study participants prompted the LLM between 6-15 times (M=9, SD=3), most frequently for code explanations (M=3), then implementing new ideas (M=2) and refining designs (M=1.9). → Tseng 2026

Evidence¶

Tseng 2026¶

Tseng, T., Seoror, L.H., Adda, J., Factor, M., Darabi, R., Matschke, K.R., Fu, T., Lin, A., Maram, A., Sinha, A. (2026). Flowcode: An AI-Powered Programming Environment for Scaffolding Iteration in Creative Computing Education. https://arxiv.org/abs/2607.06721 doi:10.48550/arxiv.2607.06721

q2 · i? · design · r2

Log analysis from the lab study (n=9). The article concludes "participants used the LLM to support all stages of their design process, from explaining existing code, debugging, and implementing new ideas." Pilot participants averaged 32 prompts (SD=8.2).

"Participants prompted the LLM between 6-15 times while iterating on their project (M=9,SD=3), with the most frequent prompts asking for code explanations (M=3)"

Discussion¶

Related Claims¶

• An LLM-generated flowchart linking semantic feature descriptions to code across HTML, CSS, and JS files supports novice creative coders' orientation, navigation, and code understanding — related
• Step-by-step explanations revealed one at a time, plus removed code auto-insertion and copy buttons, encouraged deeper engagement with generated explanations — related
• Novice creative coders exhibited three distinct initial interaction patterns with Flowcode: flowchart-first, code-first, and prompt-first — related
• In the pilot workshop, the LLM unreliably produced fill-in-the-blank snippets, often returning complete code solutions instead — related
• Automatically updating the flowchart and injecting generated code into editors drew participants away from explanations and toward direct code editing — related
• Students shifted AI usage toward debugging and concept explanation over the semester, with 31 of 89 reporting more debugging use — related
• Secondary students most frequently use generative AI for step-by-step theoretical explanation and for checking their own solutions, more than for calculations — related
• Students' AI workflows shifted toward guided, step-by-step use and more sophisticated prompting and critical evaluation over the semester — related