Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{203976,
        author = {Isha Vaibhav Nikam and Poonam Dholi},
        title = {CodeReviewAI: An AI-Powered Automated Code Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2288-2292},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203976},
        abstract = {Code review is an essential activity in software development, but manual review is time-consuming, inconsistent, and highly dependent on reviewer expertise. This paper presents CodeReviewAI, an AI-powered automated code review system designed to analyze Python, Java, and C++ source code for bugs, security vulnerabilities, code smells, and performance issues. The proposed system combines traditional static analysis with machine learning, code embeddings, vector similarity search, and natural language generation to provide meaningful and actionable review suggestions. Static analysis is performed using Abstract Syntax Tree-based inspection and rule-based pattern matching, while AI-based detection uses deep learning and transformer-based code representation models to identify hidden defects and vulnerable code patterns. 
The system is implemented using a Django-based web architecture where users upload source code, the backend preprocesses it, and multiple analysis layers evaluate the submitted program. The final output is generated as a structured review report containing issue type, severity level, explanation, and improvement suggestions. The proposed system reduces manual review effort, improves defect detection, and supports secure software development practices. The project demonstrates how hybrid AI techniques can be used to build intelligent software engineering tools for modern development environments.},
        keywords = {Automated Code Review, Static Analysis, Machine Learning, CodeBERT, LSTM, Vulnerability Detection, Code Smell Detection, Natural Language Generation, Deep Semantic Analysis, Django.},
        month = {June},
        }