Our paper investigates the application of clustering machine learning algorithms and large language models (LLMs) to automate the triage of test results in software development. We utilize AI to analyze test reports and artifacts, pinpointing potential causes of failures efficiently. This method significantly streamlines the diagnostic process, enhancing the accuracy and speed of development cycles while bolstering software reliability through targeted, AI-driven insights.

Takeaways from your talk: 1. Understanding AI’s possible Role in Testing: Attendees will gain insights into how AI can be integrated into the software testing process, particularly using clustering algorithms and LLMs to automate and improve the accuracy of test result analysis.

3. Efficiency Improvements: The audience will learn about the potential time savings and efficiency gains from automating the triage of test results, allowing for faster identification of issues and focusing human efforts on high-value tasks.

3. Enhanced Diagnostic Accuracy: You will discuss how AI can help pinpoint the underlying causes of test failures more accurately by analyzing patterns in data that might be too complex or subtle for manual detection.