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

2026-03-23

AI Summary

Current AI-powered programming learning tools lack design guidelines that effectively reconcile educators’ instructional objectives with students’ learning needs. This study addresses this gap by conducting parallel surveys with 50 educators and 90 students to systematically compare their preferences regarding help-seeking mechanisms, forms of AI responses, and allocation of control. Findings reveal that educators favor indirect guidance to preserve students’ reasoning processes, whereas students prefer direct, actionable assistance. Building on these insights, this work proposes the first interaction framework that integrates pedagogical constraints with learner autonomy, articulating design principles that balance scaffolded support with equitable control allocation. The resulting framework offers empirical grounding and actionable guidance for developing learning-oriented AI programming assistants.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Machine Learning: Learning Preferences or Rankings

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 in education settings. To ground the design of learning-oriented AI coding assistants for both sides' needs, we conducted parallel surveys of educators (N=50) and students (N=90) to compare preferences about (i) how students should request help, (ii) how AI should respond, and (iii) who should control. Our results show that educators generally favored indirect scaffolding that preserves students' reasoning, whereas students were more likely to prefer direct, actionable help. Educators further highlighted the need for course-aligned constraints and instructor-facing oversight, while students emphasized timely support and clarity when stuck. Based on these findings, we discuss the interaction-focused design space and derive design implications for learning-oriented AI coding assistants, highlighting scaffolding and control mechanisms that balance students' agency with instructional constraints.

Problem

• AI-supported programming learning
• design implications
• student-educator needs
• coding assistants
• scaffolding

Innovation

• AI-powered coding assistants
• scaffolding
• learner agency
• design implications
• educational AI