Search for: All records

Abstract Software projects frequently use automation tools to perform repetitive activities in the distributed software development process. Recently, GitHub introducedGitHub Actions, a feature providing automated workflows for software projects. Understanding and anticipating the effects of adopting such technology is important for planning and management. Our research investigates how projects useGitHub Actions, what the developers discuss about them, and how project activity indicators change after their adoption. Our results indicate that 1,489 out of 5,000 most popular repositories (almost 30% of our sample) adoptGitHub Actionsand that developers frequently ask for help implementing them. Our findings also suggest that the adoption ofGitHub Actionsleads to more rejections of pull requests (PRs), more communication in accepted PRs and less communication in rejected PRs, fewer commits in accepted PRs and more commits in rejected PRs, and more time to accept a PR. We found similar results when segmenting our results by categories ofGitHub Actions. We suggest practitioners consider these effects when adoptingGitHub Actionson their projects. 

Novice programming students frequently engage in help-seeking to find information and learn about programming concepts. Among the available resources, generative AI (GenAI) chatbots appear resourceful, widely accessible, and less intimidating than human tutors. Programming instructors are actively integrating these tools into classrooms. However, our understanding of how novice programming students trust GenAI chatbots-and the factors influencing their usage-remains limited. To address this gap, we investigated the learning resource selection process of 20 novice programming students tasked with studying a programming topic. We split our participants into two groups: one using ChatGPT (n=10) and the other using a human tutor via Discord (n=10). We found that participants held strong positive perceptions of ChatGPT's speed and convenience but were wary of its inconsistent accuracy, making them reluctant to rely on it for learning entirely new topics. Accordingly, they generally preferred more trustworthy resources for learning (e.g., instructors, tutors), preferring ChatGPT for low-stakes situations or more introductory and common topics. We conclude by offering guidance to instructors on integrating LLM-based chatbots into their curricula-emphasizing verification and situational use-and to developers on designing chatbots that better address novices' trust and reliability concerns. 

Large Language Model (LLM) conversational agents are increasingly used in programming education, yet we still lack insight into how novices engage with them for conceptual learning compared with human tutoring. This mixed‑methods study compared learning outcomes and interaction strategies of novices using ChatGPT or human tutors. A controlled lab study with 20 students enrolled in introductory programming courses revealed that students employ markedly different interaction strategies with AI versus human tutors: ChatGPT users relied on brief, zero‑shot prompts and received lengthy, context‑rich responses but showed minimal prompt refinement, while those working with human tutors provided more contextual information and received targeted explanations. Although students distrusted ChatGPT’s accuracy, they paradoxically preferred it for basic conceptual questions due to reduced social anxiety. We offer empirically grounded recommendations for developing AI literacy in computer science education and designing learning‑focused conversational agents that balance trust‑building with maintaining the social safety that facilitates uninhibited inquiry. 

Artificial intelligence (AI), including large language models and generative AI, is emerging as a significant force in software development, offering developers powerful tools that span the entire development lifecycle. Although software engineering research has extensively studied AI tools in software development, the specific types of interactions between developers and these AI-powered tools have only recently begun to receive attention. Understanding and improving these interactions has the potential to enhance productivity, trust, and efficiency in AI-driven workflows. In this paper, we propose a taxonomy of interaction types between developers and AI tools, identifying eleven distinct interaction types, such as auto-complete code suggestions, command-driven actions, and conversational assistance. Building on this taxonomy, we outline a research agenda focused on optimizing AI interactions, improving developer control, and addressing trust and usability challenges in AI-assisted development. By establishing a structured foundation for studying developer-AI interactions, this paper aims to stimulate research on creating more effective, adaptive AI tools for software development. 

Newcomers onboarding to Open Source Software (OSS) projects face many challenges. Large Language Models (LLMs), like ChatGPT, have emerged as potential resources for answering questions and providing guidance, with many developers now turning to ChatGPT over traditional Q&A sites like Stack Overflow. Nonetheless, LLMs may carry biases in presenting information, which can be especially impactful for newcomers whose problem-solving styles may not be broadly represented. This raises important questions about the accessibility of AI-driven support for newcomers to OSS projects. This vision paper outlines the potential of adapting AI responses to various problem-solving styles to avoid privileging a particular subgroup. We discuss the potential of AI persona-based prompt engineering as a strategy for interacting with AI. This study invites further research to refine AI-based tools to better support contributions to OSS projects. 

Generative AI (genAI) tools (e.g., ChatGPT, Copilot) have become ubiquitous in software engineering (SE). As SE educators, it behooves us to understand the consequences of genAI usage among SE students and to create a holistic view of where these tools can be successfully used. Through 16 reflective interviews with SE students, we explored their academic experiences of using genAI tools to complement SE learning and implementations. We uncover the contexts where these tools are helpful and where they pose challenges, along with examining why these challenges arise and how they impact students. We validated our findings through member checking and triangulation with instructors. Our findings provide practical considerations of where and why genAI should (not) be used in the context of supporting SE students. 

Generative AI (genAI) tools, such as ChatGPT or Copilot, are advertised to improve developer productivity and are being integrated into software development. However, misaligned trust, skepticism, and usability concerns can impede the adoption of such tools. Research also indicates that AI can be exclusionary, failing to support diverse users adequately. One such aspect of diversity is cognitive diversity -- variations in users' cognitive styles -- that leads to divergence in perspectives and interaction styles. When an individual's cognitive style is unsupported, it creates barriers to technology adoption. Therefore, to understand how to effectively integrate genAI tools into software development, it is first important to model what factors affect developers' trust and intentions to adopt genAI tools in practice? We developed a theoretically grounded statistical model to (1) identify factors that influence developers' trust in genAI tools and (2) examine the relationship between developers' trust, cognitive styles, and their intentions to use these tools in their work. We surveyed software developers (N=238) at two major global tech organizations: GitHub Inc. and Microsoft; and employed Partial Least Squares-Structural Equation Modeling (PLS-SEM) to evaluate our model. Our findings reveal that genAI's system/output quality, functional value, and goal maintenance significantly influence developers' trust in these tools. Furthermore, developers' trust and cognitive styles influence their intentions to use these tools in their work. We offer practical suggestions for designing genAI tools for effective use and inclusive user experience. 

Artificial intelligence (AI), including large language models and generative AI, is emerging as a significant force in software development, offering developers powerful tools that span the entire development lifecycle. Although software engineering research has extensively studied AI tools in software development, the specific types of interactions between developers and these AI-powered tools have only recently begun to receive attention. Understanding and improving these interactions has the potential to enhance productivity, trust, and efficiency in AI-driven workflows. In this paper, we propose a taxonomy of interaction types between developers and AI tools, identifying eleven distinct interaction types, such as auto-complete code suggestions, command-driven actions, and conversational assistance. Building on this taxonomy, we outline a research agenda focused on optimizing AI interactions, improving developer control, and addressing trust and usability challenges in AI-assisted development. By establishing a structured foundation for studying developer-AI interactions, this paper aims to stimulate research on creating more effective, adaptive AI tools for software development. 

Generative AI (genAI) tools (e.g., ChatGPT, Copilot) have become ubiquitous in software engineering (SE). As SE educators, it behooves us to understand the consequences of genAI usage among SE students and to create a holistic view of where these tools can be successfully used. Through 16 reflective interviews with SE students, we explored their academic experiences of using genAI tools to complement SE learning and implementations. We uncover the contexts where these tools are helpful and where they pose challenges, along with examining why these challenges arise and how they impact students. We validated our findings through member checking and triangulation with instructors. Our findings provide practical considerations of where and why genAI should (not) be used in the context of supporting SE students.