Kla Tantithamthavorn

Kla connects explainable defect prediction with code-review tools used within Atlassian’s development environment. The 2026 RovoDev team study reports that 38.7% of generated comments were followed by code changes, offering evidence that automated feedback can help developers act on problems. These observational findings have limitations, but the focus on accurate, usable suggestions makes a practical contribution to software quality.

Kla Tantithamthavorn is Associate Professor in Software Engineering at Monash University and Course Director for the Bachelor of Software Engineering (Honours). After completing a doctorate in software engineering at Nara Institute of Science and Technology in 2016, Kla focused on developing AI tools that help developers identify defects and improve code review. Current projects also investigate practical methods to test and monitor the safety and security of software built around large language models.

Kla co-authored LINE-DP, a research framework that identifies potentially defective lines of code and explains the predictions behind those choices. Evaluated across 32 releases of nine Java open-source systems, the approach helps teams focus inspection effort on specific lines within files. Collaborative work with Atlassian also produced RovoDev Code Reviewer, an automated tool that generates review comments, assesses factual accuracy, and checks whether suggestions can be acted upon. Deployed within Atlassian’s development environment, the system connects research directly with everyday engineering feedback to help developers address problems and make useful code changes.