Design and Pilot Evaluation of SmartCode Tutor (SCT): A Mixed-Methods Framework for AI-Assisted Introductory Programming in Higher Education

DOI

10.2991/978-94-6239-636-4_8How to use a DOI?

Keywords

Generative AI; AI coding assistants; programming education; automated feedback; learning analytics

Abstract

Generative AI and AI coding assistants such as large language model–based tutors and IDE copilots can provide immediate, personalized feedback for novice programmers, but unstructured use risks shallow learning and academic integrity issues. This paper presents SmartCode Tutor (SCT), a structured, AI‑enhanced framework that combines scaffolded prompt templates, automated formative feedback, and lightweight learning analytics to support introductory programming. We report a pilot, mixed‑methods, single‑group pretest–posttest study conducted in an undergraduate programming course in Malaysia. Quantitative evidence from pre/post assessments and interaction logs was complemented with student and instructor questionnaires and short reflective interviews. The pilot indicates that SCT approach is feasible to integrate into weekly labs and helps students progress from syntax‑level troubleshooting to more systematic debugging and explanation‑based problem solving, while providing instructors with actionable indicators of common misconceptions. We also describe the academic‑integrity safeguards embedded in SCT (answer‑avoidance prompting, citation and attribution guidance, and policy‑aligned usage rules). The contributions of this study are an SCT conceptual model grounded in scaffolding and cognitive load principles; an operational workflow that can be adopted with common tools (LLM chatbot + repository/IDE); and pilot evidence and lessons learned to inform a larger controlled study.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nor Zakiah Lamin
AU  - Wan Nor Asnida Wan Jusoh
AU  - Wan Asiah Wan Muhamad Tahir
AU  - Siti Faizah Miserom
AU  - Abdullah Mohd Zin
PY  - 2026
DA  - 2026/04/28
TI  - Design and Pilot Evaluation of SmartCode Tutor (SCT): A Mixed-Methods Framework for AI-Assisted Introductory Programming in Higher Education
BT  - Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
PB  - Atlantis Press
SP  - 81
EP  - 90
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-636-4_8
DO  - 10.2991/978-94-6239-636-4_8
ID  - Lamin2026
ER  -