CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework

October 2026
Vol-12, Issue-5
Paper ID: 28962
ISSN: 2395-4396
Downloads: 75
Download PDF

Abstract & Details

Research Area
Artificial Intelligence in Education, focusing on automated code assessment and personalized feedback to improve programming skills.
Keywords
CodeCoach AI programming education automated code assessment formative feedback Python static analysis large language models web-based practice.
Abstract
Automated programming assessment can provide immediate test results, yet a pass/fail indicator often leaves learners uncertain about why code failed or how it should be revised. This paper presents a focused narrative review of four established contributions to automated grading, feedback generation, large language models in computing education, and solution-preserving programming assistance. It synthesizes their implications for CodeCoach AI, a Flask-based web application described in the accompanying project synopsis. The prototype integrates twelve curated Python console challenges, public and hidden test cases, elementary Abstract Syntax Tree analysis, deterministic component scoring, optional language-model coaching, and saved submission analytics. A separate practice lab supports HTML, CSS, JavaScript, and TypeScript through browser previews and device-local drafts. The review distinguishes evidence-based grading from explanatory assistance and identifies a bounded integration gap: transparent tests, interpretable scores, actionable hints, and explicit fallback behaviour must operate together without treating AI-generated text as a source of correctness. The synopsis reports a local development run with 37 passing tests and five skipped Docker integration tests; these are software-verification observations, not measured gains in student learning. The paper presents the architecture, scoring assumptions, privacy and execution boundaries, and an evaluation agenda for feedback reliability, usability and educational effectiveness. CodeCoach AI is therefore positioned as an inspectable educational prototype and research opportunity rather than a validated competency assessment system.

Author Information

# Name Institute / Affiliation
1 Mr. Pratham Tembhurne Guru Nanak Institute of Technology
2 Dr. Sudhir N. Shelke Guru Nanak Institute of Technology
3 Prof. Shivani Jagtap Guru Nanak Institute of Technology
4 Prof. Atul Kapgate Guru Nanak Institute of Technology

How to Cite

Use the following formats to cite this article in your research.

APA Style
Tembhurne, Mr. Pratham, Shelke, Dr. Sudhir N., Jagtap, Prof. Shivani, & Kapgate, Prof. Atul (2026). CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework. International Journal of Advance Research and Innovative Ideas In Education, 12(5), 540-547.
MLA Style
Tembhurne, Mr. Pratham, et al. "CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework." International Journal of Advance Research and Innovative Ideas In Education, vol. 12, no. 5, 2026, pp. 540-547.
IEEE Style
Mr. Pratham Tembhurne, Dr. Sudhir N. Shelke, Prof. Shivani Jagtap, and Prof. Atul Kapgate, "CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework," International Journal of Advance Research and Innovative Ideas In Education, vol. 12, no. 5, pp. 540-547, 2026.
Vancouver Style
Tembhurne Mr. Pratham, Shelke Dr. Sudhir N., Jagtap Prof. Shivani, Kapgate Prof. Atul. CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework. International Journal of Advance Research and Innovative Ideas In Education. 2026;12(5):540-547.
Harvard Style
Tembhurne, Mr. Pratham, Shelke, Dr. Sudhir N., Jagtap, Prof. Shivani, & Kapgate, Prof. Atul (2026) 'CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework', International Journal of Advance Research and Innovative Ideas In Education, 12(5), pp. 540-547.
Chicago Style
Tembhurne, Mr. Pratham, et al. "CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework." International Journal of Advance Research and Innovative Ideas In Education 12, no. 5 (2026): 540-547.
Turabian Style
Tembhurne, Mr. Pratham, et al. "CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework." International Journal of Advance Research and Innovative Ideas In Education 12, no. 5 (2026): 540-547.

Export Citation

Related Research

AI-Based Smart Waste Segregation and Recycling Assistant
Priyanka Patil et al. 2026 Artificial Intelligence (AI) and Machine Learning
Download PDF
Precision Agriculture Using Computer Vision: A Review of In-Field Disease Detection, Foliar Severity Estimation
Ashlesha Adsul et al. 2026 Precision Agriculture, Computer Vision, AI, Machine Learning
Download PDF
Explainable AI for Classification and Prioritization of QHSE Audit Findings
Dr. Feroz Khan Ismail 2026 Artificial Intelligence, Quality Management, QHSE Auditing, Risk Management and Engineering
Download PDF
Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System
Nandini G R et al. 2026 OCR, Machine learning, Image Processing, CNN, Deep learning
Download PDF
PsyForm AI -An AI-Assisted Biopsychosocial Case Formulation Learning Framework.
DIKSHA BHASKAR BARSAGADE et al. 2026 Artificial Intelligence in Psychology and Medical Education
Download PDF