Human-AI Collaboration in Software Engineering: Lessons Learned from a Hands-On Workshop

This paper investigates the dynamics of human-AI collaboration in software engineering, focusing on the use of ChatGPT. Through a thematic analysis of a hands-on workshop in which 22 professional software engineers collaborated for three hours with ChatGPT, we explore the transition of AI from a mere tool to a collaborative partner. The study identifies key themes such as the evolving nature of human-AI interaction, the capabilities of AI in software engineering tasks, and the challenges and limitations of integrating AI in this domain. The findings show that while AI, particularly ChatGPT, improves the efficiency of code generation and optimization, human oversight remains crucial, especially in areas requiring complex problem-solving and security considerations. This research contributes to the theoretical understanding of human-AI collaboration in software engineering and provides practical insights for effectively integrating AI tools into development processes. It highlights the need for clear role allocation, effective communication, and balanced AI-human collaboration to realize the full potential of AI in software engineering.