Evaluating ChatGPT’s Proficiency in Understanding and Answering Microservice Architecture Queries Using Source Code Insights

Microservice architecture has become increasingly prevalent in the software domain due to its inherent flexibility, scalability, and enhanced deployment capabilities. However, the shift towards this architecture has also introduced complexities in understanding software systems, particularly when grappling with Enterprise Architecture documentation developed by different teams. While there have been efforts to make comprehension easier through automated code summaries and visual displays, developers still need to make substantial efforts to grasp the system entirely. This study investigates the potential of Large Language Models, such as ChatGPT, to answer intricate queries related to cloud-native systems, leveraging both source code and a system intermediate representation obtained from static code analysis. We focused on assessing ChatGPT’s proficiency in answering questions focused on the service and interaction perspectives of microservice systems. Our results highlight the advantages of integrating intermediate representations of the system for a richer context while addressing the model’s inherent limitations. This work sets the stage for future studies to explore how Large Language Models can make understanding software easier in dynamic, microservice-heavy settings.