Ai-Powered Code Debugger & Error Auto-Fixer”

The proposed AI-Powered Code Debugger and Error Auto-Fixer successfully demonstrates an intelligent web-based platform for automated code debugging and correction using Artificial Intelligence. Developed using Java Servlet MVC Architecture, the system integrates modern web technologies with AI models such as OpenAI GPT and Google Gemini to analyze source code, detect programming errors, generate meaningful explanations, and suggest appropriate corrections. The application provides a centralized environment for code analysis, debugging history management, and user interaction through a responsive web interface. By automating error detection and providing simplified explanations, the system significantly reduces debugging effort, improves coding productivity, and enhances the learning experience for students, beginner programmers, and software developers. The integration of a MySQL database for maintaining debugging records further enables users to review previous analyses and monitor their programming progress. The proposed system also offers significant educational value by helping learners understand compiler errors through natural language explanations rather than complex technical messages. This approach encourages self-learning, improves programming skills, and demonstrates the practical application of Artificial Intelligence, Java web technologies, API integration, and database management in software engineering. However, the current system has certain limitations. The quality of debugging suggestions depends on the capabilities of the integrated AI model, and API-based analysis requires a stable internet connection. Furthermore, debugging large-scale projects may increase processing time and be subject to API usage limits, while AI-generated corrections may still require human verification before deployment in production environments. Future enhancements will focus on integrating more advanced AI models capable of deeper semantic code analysis, supporting complete project-level debugging, and providing real-time code analysis during programming. Additional improvements include integrating built-in code execution and testing environments, developing IDE plugins for platforms such as Visual Studio Code, Eclipse, and IntelliJ IDEA, implementing AI-powered conversational chatbot support, deploying the system on scalable cloud infrastructure, incorporating security vulnerability analysis and code quality metrics, enabling voice-assisted debugging, and supporting collaborative debugging for multiple users. These enhancements will further improve the intelligence, scalability, and practical applicability of the proposed debugging platform.  

Ian Sommerville, Software Engineering, 10th Edition, Pearson Education, 2016.Herbert Schildt, Java: The Complete Reference, 11th Edition, McGraw-Hill Education, 2018.Murach Joel and Andrea Steelman, Murach’s Java Servlets and JSP, 3rd Edition, Mike Murach & Associates, 2014.Kathy Sierra and Bert Bates, Headfirst Java, 3rd Edition, O’Reilly Media, 2022.E. Balagurusamy, Programming with Java: A Primer, McGraw-Hill Education, 2019.Gavin King and Chet Haase, Java Persistence with JDBC, Oracle Documentation Series, 2020.Oracle, “Java Servlet Technology Documentation,” Available:Oracle Java Documentation