Enhancing Software Development with Context-Aware Conversational Agents: A User Study on Developer Interactions with Chatbots

TL;DR

This paper investigates how context-aware conversational agents can support software developers by understanding their needs for task automation, version control, and personalized assistance, based on a user study with 29 developers.

Contribution

It provides empirical insights into developer preferences for chatbot features and highlights the importance of contextual understanding and personalization in CA design for software engineering.

Findings

Developers value task automation and version control support.

Contextual adaptability enhances developer satisfaction.

Personalized assistance for different experience levels is crucial.

Abstract

Software development is a cognitively intensive process requiring multitasking, adherence to evolving workflows, and continuous learning. With the rise of large language model (LLM)-based tools, such as conversational agents (CAs), there is growing interest in supporting developers through natural language interaction. However, little is known about the specific features developers seek in these systems. We conducted a user study with 29 developers using a prototype text-based chatbot to investigate preferred functionalities. Our findings reveal strong interest in task automation, version control support, and contextual adaptability, especially the need to tailor assistance for both novice and experienced users. We highlight the importance of deep contextual understanding, historical interaction awareness, and personalized support in CA design. This study contributes to the development of context-aware chatbots that enhance productivity and satisfaction, and it outlines opportunities for future research on human-AI collaboration in software engineering.