Novice creative coders exhibited three distinct initial interaction patterns with Flowcode: flowchart-first, code-first, and prompt-first¶

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? In the lab study, 4/9 participants took a flowchart-first approach, 3 took a code-first approach, and 2 took an LLM-first (prompt-first) approach, with users working across approaches as they iterated. → 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

Interaction-trace analysis (Figure 5) from the lab study (n=9) of how participants initially engaged with the editor. The article characterizes prompt-first users as potentially placing "higher emphasis on the ultimate design outcome than fully understanding the code."

"In our study, 4/9 participants took a flowchart-first approach, 3 took a code-first approach, and 2 took an LLM-first approach."

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