Ally Limke

Large language models (LLMs) are rapidly reshaping software development, but their impact across the full software development lifecycle is underexplored. Existing work tends to focus on isolated activities such as code generation or testing, leaving open questions about how LLMs affect developers, processes, products, and the broader software ecosystem. We address this gap through semi-structured interviews with sixteen early-adopter software professionals who integrated LLM-based tools into their day-to-day work in early to mid-2023. We treat these interviews as early empirical evidence and compare participants’ accounts with recent work on LLMs in software engineering, noting which early patterns persist or shift. Using thematic analysis, we organize our findings around four dimensions: people, process, product, and society. Developers reported substantial productivity gains from reducing mundane tasks, streamlining search, and accelerating debugging, but also described a productivity-quality paradox: they frequently discarded generated code and shifted effort from writing code to critically evaluating and integrating it. LLM use was highly phase-dependent, with strong uptake in implementation and debugging but limited influence on requirements gathering and collaborative work. Participants developed new competencies to use LLMs effectively, including prompt engineering strategies, multi-layered verification, and security-conscious integration to protect proprietary data. They also anticipated changes in hiring expectations, team practices, and computing education, while emphasizing that human judgment and foundational software engineering skills remain essential. Our findings, consistent with evidence from large-scale studies, offer actionable implications for developers, organizations, educators, and tool designers seeking to integrate LLMs responsibly into professional software practice.

AI-based chatbots have the potential to accelerate learning and teaching, but may also have counterproductive consequences without thoughtful design and scaffolding. To better understand teachers’ perspectives on large language model (LLM) based chatbots, we conducted a study with 11 teams of middle-school teachers using chatbots for a science and computational thinking activity within a block-based programming environment. Based on a qualitative analysis of audio transcripts and chatbot interactions, we propose three profiles: explorer, frustrated, and mixed that reflect diverse scaffolding needs. In their discussions, we found that teachers perceived chatbot benefits such as building prompting skills and self confidence alongside risks including potential declines in learning and critical thinking. Key design recommendations include scaffolding the introduction to chatbots, facilitating teacher control of chatbot features, and suggesting when and how chatbots should be used. Our contribution informs the design of chatbots to support teachers and learners in middle school coding activities.

Tutoring systems improve learning through tailored interventions, such as worked examples, but often suffer from the aptitude-treatment interaction effect where low prior knowledge learners benefit more. We applied the ICAP learning theory to design two new types of worked examples, Buggy (students fix bugs), and Guided (students complete missing rules), requiring varying levels of cognitive engagement, and investigated their impact on learning in a controlled experiment with 155 undergraduate students in a logic problem solving tutor. Students in the Buggy and Guided examples groups performed significantly better on the posttest than those receiving passive worked examples. Buggy problems helped high prior knowledge learners whereas Guided problems helped low prior knowledge learners. Behavior analysis showed that Buggy produced more exploration-revision cycles, while Guided led to more help-seeking and fewer errors. This research contributes to the design of interventions in logic problem solving for varied levels of learner knowledge and a novel application of behavior analysis to compare learner interactions with the tutor.

This article examines US K-12 computing teacher needs for a programming learning system. We surveyed 39 K-12 teachers about the necessity of programming learning system features. We found that teachers needed to view student code remotely, student code auto-save, differentiation of student assignments, and a tutorial library for students to learn about the programming environment. In addition to rating feature usefulness, we also asked teachers to list features or needs that the survey did not address. Through qualitative responses, we found that teachers wanted cheating prevention and detection, the ability to freeze and project code onto student screens, and student and classroom-level analytics. We also compare the needs of teachers who teach computing as the main subject in their classroom to the needs of teachers who integrate computing into another discipline. This research can inform the development of programming learning systems to better support teachers and their students.

Affective state, referring to an individual's feeling, can impact students' confidence and retention in CS, particularly for novice programmers. However, little research has been conducted to examine how moments that occur during programming impact students' affective states in real-time. In this pilot study, seven undergraduate students in an introductory block-based programming course completed a programming assignment and were surveyed and interviewed about their experience and self-efficacy as programmers. While programming, students periodically recorded their affective states via a popup in the programming environment. We performed retrospective think-aloud interviews with students afterward, asking them to watch and reflect on recordings of their programming. We subsequently analyzed student interviews using thematic analysis to derive 206 codes. These codes were grouped into three areas that impacted affect: the environment, objective progress, and perceptions during programming. To explore why students responded as they did to moment occurrence, we further categorized students based on four dimensions: programming experience, assignment completion, confidence, and the impact of the programming session on self-efficacy. Our initial results suggest that while certain moments elicit similar affective states among students, the interaction of the aforementioned four dimensions may have a higher impact on novices' affective states during programming. We conclude with recommendations for educators to improve students' affective states during and after programming.

In computing classrooms, building an open-ended programming project engages students in the process of designing and implementing an idea of their own choice. An explicit planning process has been shown to help students build more complex and ambitious open-ended projects. However, novices encounter difficulties in exploring and creatively expressing ideas during planning. We present Idea Builder, a storyboarding-based planning system to help novices visually express their ideas. Idea Builder includes three features: 1) storyboards to help students express a variety of ideas that map easily to programming code, 2) animated example mechanics with example actors to help students explore the space of possible ideas supported by the programming environments, and 3) synthesized starter code to help students easily transition from planning to programming. Through two studies with high school coding workshops, we found that students self-reported as feeling creative and feeling easy to communicate ideas; having access to animated example mechanics of an actor help students to build those actors in their plans and projects; and that most students perceived the synthesized starter code from Idea Builder as helpful and time-saving.