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{192668,
        author = {M Jagadeesh and A Sai Yashwanth and Saparay Deepak and V.Rahul kumar and p.vivekananda sai and Dr. P. Veeresh},
        title = {AI-Powered Code Quality Analyzer and Error Fixer: An Intelligent Framework for Automated Code Review, Optimization, and Quality Assessment},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {1939-1943},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192668},
        abstract = {Modern software development, it is of utmost importance to ensure the quality of the code to ascertain the reliability, maintenance, and quality service of the program. In most situations, and particularly among students and novice programmers, the challenge is to ensure the production of quality or optimized code due to minimum exposure to code quality standards and practice. In the traditional practice of code review, a programming expert is needed to enhance code quality, and the review of the code is always a lengthy and non-scalable end, among other limitations. However, to overcome the aforementioned challenge and develop a comprehensive solution, the Code Quality Fixer (CQF), an artificial-intelligence code review and improvement system, was used as a derivative of the particular research subject. An automated system is necessary for the comprehensive review and improvement of code quality using a large model.
In addition, the system allows users to input their corresponding source codes, and then the quality score may be generated, that is, the quality level or program reliability may be elaborated or the quality standards may be generated. Furthermore, it should be noted that the system would be effective in reviewing the codes to enhance or improve the codes in optimized forms and quality standards with the application of AI.
The proposed system would make this system interactive to perform code analysis with the codes given to the system. Graphs were plotted for the quality standards. It seems to be a highly effective system for helping programmers enhance their skills through feedback mechanisms rather than the traditional mechanism of code reviews and good codes for programmers. The proposed system can be extended by adding many features, such as different programming languages and security issues: Integration with Source Control Systems for Continuous Quality Monitoring.},
        keywords = {Artificial Intelligence, Static Code Analysis, Automated Code Review, Code Quality Assessment, Software Engineering, Optimization, Developer Assistance, LLM, AST Parsing.},
        month = {February},
        }