AI-Powered SQL Bug Analyzer and Auto Fix Assistant
Authors
Dr. V. S. Gaikwad
Head of IT department (IN)
Ganesh Borole
Student Department of Information Technology, Trinity College of Engineering and Research, Pune, India (IN)
Omkar Jadhav
Student Department of Information Technology, Trinity College of Engineering and Research, Pune, India (IN)
Himanshu Tambe
Student Department of Information Technology, Trinity College of Engineering and Research, Pune, India (IN)
Krishna Kinikar
Student Department of Information Technology, Trinity College of Engineering and Research, Pune, India (IN)
Article Information
DOI: 10.51583/IJLTEMAS.2026.150500252
Subject Category: Computer Science & Engineering
Volume/Issue: 15/5 | Page No: 3090-3099
Publication Timeline
Submitted: 2026-06-23
Published: 2026-06-23
Abstract
This work describes the development of a system based on AI and chat technology that allows users to communicate with several databases by posing questions in natural language. Standard databases require knowledge of SQL and technical skills from their users; therefore, they are difficult to use for individuals who lack expertise in computer science and programming. In this work, we incorporate MERN stack technology and integrate AI technology within it to translate user commands into valid queries for databases. Our proposed system is capable of processing queries and communicating with different types of databases, including MongoDB, MySQL, SQLite, and BigQuery..
Keywords
Artificial Intelligence,Text-to-SQL, SQLFixAgent, Large Language Models, SQL error correction, Multi- agent framework, Semantic accuracy
This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Downloads
References
1. Z. Zhong, C. Xiong, and D. Yu, ”Seq2SQL: Generat ing Structured Queries from Natural Language Using Reinforcement Learning,” in Proc. ACM SIGMOD, pp. 1913–1927, 2017. [Google Scholar] [Crossref]
2. Yu, Z. Zhang, and D. Yu, ”Spider: A Large Scale Human- Labeled Dataset for Complex and Cross Domain Semantic Parsing and Text-to-SQL Task,” in Proc. EMNLP, pp. 3911–3921, 2018 [Google Scholar] [Crossref]
3. Wang, X. Liu, and M. Richardson, ”RAT-SQL: Relation-Aware Schema Encoding and Linking for Text to- SQL Parsers,” in Proc. ACL, pp. 7567–7578, 2020. OpenAI, ”GPT-4 Technical Report,” arXiv preprint arXiv:2303.08774, 2023. [Google Scholar] [Crossref]
4. Z. Hong, J. Xu, and Y. Chen, ”MetaGPT: Meta Pro gramming for Multi-Agent Collaboration,” arXiv preprint arXiv:2308.00352, 2023. [Google Scholar] [Crossref]
5. S. Sergeyuk, L. Mironova, and A. Pashkov, ”Using AI Based Coding Assistants in Practice: A Large-Scale Sur vey,” Journal of Software Engineering Research, vol. 12, no. 3, [Google Scholar] [Crossref]
6. pp. 215–228, 2024. [Google Scholar] [Crossref]
7. J. Lee, K. Park, and S. Choi, ”FixAgent: A Multi-Agent Framework for Automated Debugging and Code Repair,” in Proc. IEEE Int. Conf. on Artificial Intelligence and Data Science (AIDAS), pp. 88–95, 2024. [Google Scholar] [Crossref]
8. L. Wang, Y. Qian, and D. Zhou, ”MAC-SQL: Multi-Agent Collaboration for Robust Text-to-SQL Parsing,” in Proc. AAAI Conf. on Artificial Intelligence, pp. 12765–12773, 2024. [Google Scholar] [Crossref]
9. H. Gao, Y. Sun, and X. Li, ”Enhancing Semantic Con sistency in Text-to-SQL Generation with Context-Aware Reasoning,” in Proc. NAACL, pp. 6432–6445, 2024. [Google Scholar] [Crossref]
10. H. Gao, Y. Sun, and X. Li, ”Enhancing Semantic Con sistency in Text-to-SQL Generation with Context-Aware Reasoning,” in Proc. NAACL, pp. 6432–6445, 2024. [Google Scholar] [Crossref]
11. Y. Cen, K. Liu, and H. Li, ”SQLFixAgent: Towards Semantic- Accurate Text-to-SQL Parsing via Consistency Enhanced Multi-Agent Framework,” arXiv preprint arXiv:2503.01234, 2025. [Google Scholar] [Crossref]
12. OpenAI, “Codex: Evaluating Large Language Models for Code Generation,” OpenAI Research Publication, 2021. [Google Scholar] [Crossref]
13. J. Austin, A. Odena, M. Nye, et al., “Program Synthesis with Large Language Models,” arXiv preprint arXiv:2108.07732, 2021. [Google Scholar] [Crossref]
14. Y. Sun, T. Gao, and H. Li, “Improving Semantic Accuracy in Text-to-SQL Systems Using Reflective Query Validation,” in Proc. International Conference on Computational Linguistics (COLING), pp. 4521–4533, 2023. [Google Scholar] [Crossref]
15. AutoGPT Team, “AutoGPT: An Autonomous GPT-4 Experiment for Complex Task Solving,” GitHub Repository, 2023. [Online]. Available: https://github.com/Significant-Gravitas/AutoGPT [Google Scholar] [Crossref]
16. JetBrains, “JetBrains AI Assistant: Intelligent Coding Support for Developers,” JetBrains Official Documentation, 2024. [Online]. Available: https://www.jetbrains.com/ai/ [Google Scholar] [Crossref]
17. Tabnine, “Tabnine AI Code Assistant for Software Development,” Tabnine Official Documentation, 2024. [Online]. Available: https://www.tabnine.com/ [Google Scholar] [Crossref]
18. Microsoft, “Azure OpenAI Service for Intelligent Database Query Assistance,” Microsoft Documentation, 2024. [Online].Available: https://learn.microsoft.com/ [Google Scholar] [Crossref]
19. Google Cloud, “AI-Powered Database Query Optimization Using Generative AI,” Google Cloud Research, 2024. [Google Scholar] [Crossref]
Metrics
Views & Downloads
Similar Articles
- Block-Based Programming for Education: A Comprehensive Analysis of Visual Programming Environments in K-12 Learning
- Management of Academic Libraries and Client Satisfaction Towards Digital Utilization: Basis for Monitoring Library Operations in SOCCSKSARGEN Region.
- Revenue Leakages in TPA Insurance Claims and Corporate Claims: An Institutional Overview of Aster Prime Hospital, Hyderabad
- Technology and Innovation in Hospitality and Tourism: A Management Perspective
- Geospatial Distribution of Tarok Sacred Grove of Langtang North and Langtang South Local Government Areas