Design Implications for Student and Educator Needs in AI-Supported Programming Learning Tools

Abstract

AI-powered coding assistants can support students in programming courses by providing on-demand explanations and debugging help. However, existing research often focuses on individual tools, leaving a gap in evidence-based design recommendations that reflect both educator and student perspectives. To address this gap, we surveyed educators (N = 50) and students (N = 90) to compare preferences regarding acceptable use boundaries, learner requests and context provision, AI responses and scaffolding, and control over assistance. Educators generally favored indirect scaffolding that preserves students’ reasoning, whereas students preferred direct, actionable help. Educators highlighted the need for course-aligned constraints and instructor-facing oversight, while students emphasized timely support and clarity when stuck. An exploratory analysis suggests that students’ prior AI experience was associated with perceived learning value, while structural preferences remained broadly similar across experience groups. We derive stakeholder-grounded design implications for learning-oriented AI coding assistants that balance students’ agency with instructional constraints.