AI Powered Code Review System
Keywords
Abstract
This paper presents an AI-powered code review system designed to assist developers by providing real-time, intelligent feedback on software code. The system integrates advanced language models via OpenAI and Hugging Face APIs within a secure Java Spring Boot backend, using AES-256 encryption for data privacy and JWT for secure user authentication. A key feature is its intelligent fallback mechanism: when OpenAI is unavailable, the system seamlessly switches to Hugging Face, ensuring high availability and responsiveness. The frontend, built with React.js, offers a smooth and interactive user experience. Evaluation results show the system delivers over 90% accurate and relevant feedback, with average response times under 2 seconds. This solution supports developers by automating routine review tasks while preserving human oversight, ultimately enhancing code quality and accelerating development workflows.
Copyright & License
Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Cite this Article
Mr. Sonti Ganesh, Mr. Nagaraju Vassey, Mr. Manne Naga VJ Manikanth (2025). AI Powered Code Review System. International Journal of Technology & Emerging Research (IJTER), 1(1), 63-69
BibTeX
@article{ijter2025212505212153,
author = {Mr. Sonti Ganesh and Mr. Nagaraju Vassey and Mr. Manne Naga VJ Manikanth},
title = {AI Powered Code Review System},
journal = {International Journal of Technology & Emerging Research },
year = {2025},
volume = {1},
number = {1},
pages = {63-69},
issn = {3068-109X},
url = {https://www.ijter.org/article/212505212153/ai-powered-code-review-system},
abstract = {This paper presents an AI-powered code review system designed to assist developers by providing real-time, intelligent feedback on software code. The system integrates advanced language models via OpenAI and Hugging Face APIs within a secure Java Spring Boot backend, using AES-256 encryption for data privacy and JWT for secure user authentication. A key feature is its intelligent fallback mechanism: when OpenAI is unavailable, the system seamlessly switches to Hugging Face, ensuring high availability and responsiveness. The frontend, built with React.js, offers a smooth and interactive user experience. Evaluation results show the system delivers over 90% accurate and relevant feedback, with average response times under 2 seconds. This solution supports developers by automating routine review tasks while preserving human oversight, ultimately enhancing code quality and accelerating development workflows.},
keywords = {Code Review, Artificial Intelligence, Spring Boot, Hugging Face, Software Quality.},
month = {May},
}