🤖 AI Summary
This study investigates the mechanisms through which AI-generated code affects software engineers’ productivity and long-term software quality—specifically maintainability and extensibility. Using a mixed-methods approach, it combines practitioner surveys with multi-project empirical codebase analysis and statistical modeling across tasks of varying complexity. Results show that AI significantly improves developer efficiency for small-scale tasks without compromising code quality; however, in high-complexity systems, direct integration of AI-generated code increases architectural coupling and maintenance risks. Such challenges necessitate architect-led problem decomposition and manual integration. Based on these findings, the study proposes a “human–AI layered collaboration” model: AI handles module-level implementation, while humans retain responsibility for architectural design and cross-module integration. This model preserves productivity gains while mitigating AI’s adverse effects on long-term software quality, offering a practical governance framework for AI-augmented software engineering.
📝 Abstract
AI-powered software tools are widely used to assist software engineers. However, there is still a need to understand the productivity benefits of such tools for software engineers. In addition to short-term benefits, there is a question of how adopting AI-generated solutions affects the quality of software over time (e.g., maintainability and extendability).
To provide some insight on these questions, we conducted a survey among software practitioners who use AI tools. Based on the data collected from our survey, we conclude that AI tools significantly increase the productivity of software engineers. However, the productivity benefits of using AI tools reduce as projects become more complex. The results also show that there are no significant negative influences of adopting AI-generated solutions on software quality, as long as those solutions are limited to smaller code snippets. However, when solving larger and more complex problems, AI tools generate solutions of a lower quality, indicating the need for architects to perform problem decomposition and solution integration.