AI Powered Code Review Assistant


Authors : Alok Anand; Anish Kumar; Akash Babu NJ; Deepak Kumar; Varshitha M K

Volume/Issue : Volume 9 - 2024, Issue 12 - December

Google Scholar : https://tinyurl.com/2krapt75

Scribd : https://tinyurl.com/yck6pvy3

DOI : https://doi.org/10.5281/zenodo.14533537

Abstract : With the increasing complexity of software systems, maintaining high code quality is essential to ensure reliability, maintainability, and security. Traditionally, code reviews havebeen a manual and time- consuming process, often resulting in inconsistencies and missed issues due to human error. Recent advance- ments in artificial intelligence, specifically generative AI models like OpenAI’s Chat- GPT and Google Gemini, have opened new possibilities for automating code reviews by providing real-time, intelligent feedback on code quality. This survey paper explores the current state ofAI- assisted code review tools, focusing on the potential of generative AI models to improve software development workflows. We exam- ine the methodologies, benefits, and limita- tions of existing tools such as GitHub Copilot, Amazon CodeWhisperer, and other AI-drivensolutions. Additionally, we discuss the archi- tecture and design of an AI-powered code review assistant that integrates seamlessly with popular development environments like VS Code, leveraging cloud-based processing through AWS. Our findings suggest that integrating gener- ative AI into the code review process can significantly reduce review time, improve consistency, and enhance developer produc- tivity. This paper also highlightsthe cost-effective implementation of AI models in code reviews, demonstrating the feasibility of deploying scalable, budget-friendly solu- tions in real-world applications. By analyz- ing the strengths and weaknesses of current approaches, we outline the path for futureadvancements in AI-powered code review systems, focusing on multi- language support, enhanced security analysis, and continuouslearning capabilities.

Keywords : AI, Code Review, Generative AI, ChatGPT, GeminiAPI, Software Development.

References :

  1. M. Coutinho, L. Marquez, and F. Wang, “Evaluating the Code Quality of AI-Assisted Code Generation Tools: An   Empirical   Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT,” arXiv, 2023. Available: https://ar5iv.labs.arxiv.org/html/2312.10868
  2. T. R. McIntosh, T. Susanto, and L. Brown, ”From   Google Gemini to OpenAI Q: A Survey on Gen- erative AI,” 2023. Available: https://alok180202- my.sharepoint.com
  3. Odeh, N. Odeh, and R. Ahmed, ”A Compara- tive Review of AI Techniques for Automated Code Generation,” Journal of Recent AI Advancements, vol. 13, no. 1, pp. 726-739, 2023.
  4. R. Ferdiana, ”The Impact of Artificial Intelligence on Programmer Productivity,” ResearchGate, 2024. Available: https://www.researchgate.net
  5. Amazon Web Services, ”Amazon EC2 User Guide for Linux Instances,” AWS Documentation. Avail- able: https://docs.aws.amazon.com
  6. Pallets Projects,”Flask API Documen-tation,” Flask Documentation. Available: https://flask.palletsprojects.com/en/stable/api/
  7. GitHub,Inc.,   ”GitHub   API   Docu- mentation,” GitHub Docs. Available: https://docs.github.com/en/rest
  8. OpenAI,”ChatGPT API     Documenta- tion,” OpenAI Documentation. Available: https://platform.openai.com/docs/overview
  9. Google,”Google Gemini API Documen- tation,” Google Documentation. Available: https://cloud.google.com/gemini/docs
  10. Microsoft, ”VS Code Docu- mentation,” Microsoft. Available: https://code.visualstudio.com/docs

With the increasing complexity of software systems, maintaining high code quality is essential to ensure reliability, maintainability, and security. Traditionally, code reviews havebeen a manual and time- consuming process, often resulting in inconsistencies and missed issues due to human error. Recent advance- ments in artificial intelligence, specifically generative AI models like OpenAI’s Chat- GPT and Google Gemini, have opened new possibilities for automating code reviews by providing real-time, intelligent feedback on code quality. This survey paper explores the current state ofAI- assisted code review tools, focusing on the potential of generative AI models to improve software development workflows. We exam- ine the methodologies, benefits, and limita- tions of existing tools such as GitHub Copilot, Amazon CodeWhisperer, and other AI-drivensolutions. Additionally, we discuss the archi- tecture and design of an AI-powered code review assistant that integrates seamlessly with popular development environments like VS Code, leveraging cloud-based processing through AWS. Our findings suggest that integrating gener- ative AI into the code review process can significantly reduce review time, improve consistency, and enhance developer produc- tivity. This paper also highlightsthe cost-effective implementation of AI models in code reviews, demonstrating the feasibility of deploying scalable, budget-friendly solu- tions in real-world applications. By analyz- ing the strengths and weaknesses of current approaches, we outline the path for futureadvancements in AI-powered code review systems, focusing on multi- language support, enhanced security analysis, and continuouslearning capabilities.

Keywords : AI, Code Review, Generative AI, ChatGPT, GeminiAPI, Software Development.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe