Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68477
Volume:
10 |
10 |
Oct 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science and Engineering
G H Raisoni University, Amravati
Department of Computer Science and Engineering
G H Raisoni University, Amravati
Department of Computer Science and Engineering
G H Raisoni University, Amravati
Department of Computer Science and Engineering
G H Raisoni University, Amravati
Department of Computer Science and Engineering
G H Raisoni University, Amravati
Department of Computer Science and Engineering
G H Raisoni University, Amravati
Code review supports software quality by helping identify potential programming errors, security concerns, performance issues, and code-quality problems. Manual review remains important but can require time and technical expertise. This paper presents AutoShield AI, a web-based application developed to assist developers and students with initial source-code analysis. Authenticated users can submit source-code files and receive AI-generated feedback about possible bugs, security vulnerabilities, performance, code quality, and improvements. The system also combines review-history management, source-code-based interview-question generation, and PDF report generation in one application. The frontend uses React.js and Vite; backend services use Node.js and Express.js; MongoDB and Mongoose provide data storage; JSON Web Tokens support authentication; and the Groq API provides the external AI-analysis service. The thesis reports 31 functional test cases across general functionality, authentication, code review, interview questions, and PDF reporting, all marked as passed. These results represent functional checks rather than an independent measurement of AI accuracy or comparative performance. AutoShield AI demonstrates an integrated implementation of AI-assisted code-review and learning-support features, while its recommendations still require human verification.
KEYWORDS
This paper described AutoShield AI, a web-based application integrating AI-assisted code review with authentication, review history, interview-question generation, and PDF reporting. The system uses a React/Vite frontend, Node.js/Express backend, MongoDB/Mongoose storage, JWT authentication, and an external Groq API for AI analysis. The project thesis reports 31 functional test cases across five categories, all marked as passed. These tests document the operation of application features but do not measure AI-review accuracy or comparative effectiveness. AutoShield AI therefore represents a practical integrated application for initial code-analysis assistance and developer learning, with human verification remaining essential.
[1] M. Chen et al., “Evaluating Large Language Models Trained on Code,” arXiv:2107.03374, 2021. [Online]. Available: https://arxiv.org/abs/2107.03374 [2] D. Hendrycks et al., “Measuring Coding Challenge Competence With APPS,” Advances in Neural Information Processing Systems, vol. 34, 2021. [Online].Available: https://arxiv.org/abs/2105.09938 [3] A. LeClair, S. Jiang, and C. McMillan, “Improved Code Summarization via a Graph Neural Network,” in Proc. 28th International Conference on Program Comprehension, 2020. doi: 10.1145/3387904.3389268. [4] Y. Li et al., “Competition-Level Code Generation with AlphaCode,” Science, vol. 378, no. 6624, pp. 1092–1097, 2022. doi: 10.1126/science.abq1158. [5] Z. Feng et al., “CodeBERT: A Pre-Trained Model for Programming and Natural Languages,” in Findings of ACL: EMNLP 2020, pp. 1536–1547, 2020. [Online].Available: https://aclanthology.org/2020.findings-emnlp.139/ [6] M. Tufano, J. Pantiuchina, C. Watson, G. Bavota, and D. Poshyvanyk, “On Learning Meaningful Code Changes via Neural Machine Translation,” in Proc. 41st International Conference on Software Engineering, pp. 25–36, 2019. doi: 10.1109/ICSE.2019.00021. [7] M. Allamanis, M. Brockschmidt, and M. Khademi, “Learning to Represent Programs with Graphs,” arXiv:1711.00740, 2017. [Online]. Available: https://arxiv.org/abs/1711.00740 [8] S. McIntosh, Y. Kamei, B. Adams, and A. E. Hassan, “An Empirical Study of the Impact of Modern Code Review Practices on Software Quality,” Empirical Software Engineering, vol. 21, pp. 2146–2189, 2016. doi: 10.1007/s10664-015-9381-9. [9] G. A. Campbell and P. P. Papapetrou, SonarQube in Action. Manning Publications, 2013. [10] R. Tufano, L. Pascarella, M. Tufano, D. Poshyvanyk, and G. Bavota, “Towards Automating Code Review Activities,” in Proc. 43rd International Conference on Software Engineering, 2021. [Online]. Available: https://www.microsoft.com/en-us/re search/publication/towards-automating-code-review-activities/
Publication Date
10/29/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...