Skip to content
Book Open access

An Adaptive AI Debugging Assistant for Computing Education

Zahwa Ait Ennecer Lee Clift
Sep 2026 · Proceedings of the 2026 United Kingdom and Ireland Computing Education Research · pp. 1-1 · 0 citations · 6 references

TL;DR

A context-aware Visual Studio Code extension that delivers progressively revealed, adaptive hints tailored to the user’s self-described experience level, indicating that carefully designed scaffolding successfully encourages active reflection and preserves problem-solving skills in computing education.

Abstract

Artificial Intelligence (AI) debugging assistants are increasingly prevalent in software development but present a pedagogical risk: "metacognitive laziness," wherein learners over-rely on automated solutions without grasping the underlying logic. To address this, we developed a context-aware Visual Studio Code extension powered by Gemini 1.5 Pro. Rather than providing direct answers, the tool delivers progressively revealed, adaptive hints tailored to the user’s self-described experience level. A user study yielded perfect bug resolution rates, and participants reported finding the tool useful, indicating that carefully designed scaffolding successfully encourages active reflection and preserves problem-solving skills in computing education.

Read PDF

Similar papers

Open access 2026

From Code Generation to Code Auditing: Constrained AI Scaffolding, Transfer, and Cognitive Efficiency in Debugging

Generative artificial intelligence is reshaping programming education, yet its effects on skill development depend partly on how learners interact with artificial intelligence-supported systems. This study introduces the Artificial Intelligence-Scaffolding Interaction Framework, which conceptualizes constrained, questi...

M. Yenidogan, Zeynep Cömert, Duygu Çakır · 0 citations
#generative ai Book Open access Oct 2026

Designing Constrained AI Assistance for Novice Programmers: Tensions and Hypotheses from a JupyterLab Hint System

A design case study of a JupyterLab addon that delivers Socratic hints instead of direct answers, and six design hypotheses for developers of constrained AI programming assistants, addressing hint escalation, selective dialogue, context granularity, vocabulary calibration, onboarding transparency, and difficulty-aware...

Alexandre De Masi, Chen Wang, Laurent Moccozet · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.