Agentic AI improves accuracy and usefulness of industrial code reviews
Using Agentic AI for contextualized and multifaceted code review at Ericsson
Software Engineering
Summary
Code reviews are important but getting harder because software is more complex and AI writes code faster. The authors designed a system using multiple AI helpers, each focusing on different things like readability and performance, to check code changes better. They tested it in a real company and found the system correctly spotted most issues and identified many important problems developers should fix. Developers said the AI feedback was helpful and trustworthy.
What this means in practice
- •For software development teams: Use AI agents with specialized expertise to provide detailed, project-aware code feedback that helps teams fix severe and important code issues.
- •For devops engineers: Integrate multifaceted AI-based code review tools into pipelines to detect maintainability and reliability issues before deployment.
Authors
Muhammad Laiq, Ricardo Britto, Muhammad Usman, Nishrith Saini, Deepika Badampudi
Abstract
Context: Conducting effective code reviews is increasingly challenging due to the growing complexity of software systems and the accelerated code generation by AI coding agents. LLM-based approaches for code reviews have shown promising results in identifying defects and improving code quality. However, existing approaches rarely consider project-specific contextualized knowledge, and few have been evaluated in industrial settings. Objective: In this study, we propose a multi-agent-based solution that provides multifaceted assessments of code changes. Method: Following the Design Science Research Process, we developed and evaluated our solution in an industrial setting. Our solution combines specialized agent skills with context-specific knowledge to identify antipatterns in code changes across four dimensions: readability, maintainability, reliability, and performance. Using our solution, we generated reviews for several code commits and identified more than 200 issues. These issues were then manually validated by the developers of the case company for their correctness and importance. Results: The evaluation results show that our solution achieves 96% accuracy in correctly identifying issues in the investigated code commits. Furthermore, around 69% of the correctly identified issues were rated as important, with approximately 33% rated as severe issues that must be fixed and 36% as important issues that should be fixed. Qualitative feedback from developers corroborates these findings and highlights the usefulness of the generated reviews. Conclusion: Our findings provide empirical evidence from an industrial evaluation that combining specialized agent skills with context-specific knowledge yields accurate, practically useful code reviews.