We introduce the concept of code shaping, an interaction paradigm for editing code using free-form sketch annotations directly on top of the code and console output. To evaluate this concept, we conducted a three-stage design study with 18 different programmers to investigate how sketches can communicate intended code edits to an AI model for interpretation and execution. The results show how different sketches are used, the strategies programmers employ during iterative interactions with AI interpretations, and interaction design principles that support the reconciliation between the code editor and sketches. Finally, we demonstrate the practical application of the code shaping concept with two use case scenarios, illustrating design implications from the study.

Programmers now use both generative AI (GenAI) and traditional web search for information-seeking, yet how these tools are used individually or in combination remains unclear. To answer this, we conducted a multi-phase investigation, including retrospective interviews to identify foraging behaviours and challenges and an observational study with a technology probe to analyze how contextual information flows across tools. Our findings reveal that effective information-seeking requires adaptable strategies and varying levels of contextual detail. Building on these insights, we propose five design dimensions for developing tools that integrate web search, GenAI, and code editors. We further demonstrated the generative power of these design dimensions with a proof-of-concept prototype, validated through a user study, offering actionable design implications for enhancing integrated information-seeking workflows across web search and GenAI in programming.

This paper adopted an iterative design process to gain insights into programmers’ strategies when using LLMs for programming. We proposed CoLadder, a novel system that supports programmers by facilitating hierarchical task decomposition, direct code segment manipulation, and result evaluation during prompt authoring. A user study with 12 experienced programmers showed that CoLadder is effective in helping programmers externalize their problem-solving intentions flexibly, improving their ability to evaluate and modify code across various abstraction levels, from their task’s goal to final code implementation.

The convergence of generative AI and web search is reshaping problem-solving for programmers. However, the lack of understanding regarding their interplay in the information-seeking process often leads programmers to perceive them as alternatives rather than complementary tools. To analyze this interaction and explore their synergy, we conducted an interview study with eight experienced programmers. Drawing from the results and literature, we have identified three major challenges and proposed three decision-making stages, each with its own relevant factors. Additionally, we present a comprehensive process model that captures programmers' interaction patterns. This model encompasses decision-making stages, the information-foraging loop, and cognitive activities during system interaction, offering a holistic framework to comprehend and optimize the use of these convergent tools in programming.

This workshop provides a forum to discuss, brainstorm, and prototype the next generation of interfaces that leverage the dynamic experiences enabled by recent advances in AI and the generative capabilities of foundation models. These models simplify complex tasks by generating outputs in various representations (e.g., text, images, videos) through diverse input modalities like natural language, voice, and sketch. They interpret user intent to generate and transform representations, potentially changing how we interact with information and express ideas. Inspired by this potential, technologists, theorists, and researchers are exploring new forms of interaction by building demos and communities dedicated to concretizing and advancing the vision of working with dynamic abstractions. This UIST workshop provides a timely space to discuss AI’s impact on how we might design and use cognitive tools (e.g., languages, notations, diagrams). We will explore the challenges, critiques, and opportunities of this space by thinking through and prototyping use cases across various domains.

Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and context-switching among programmers from varying backgrounds. However, programmers may face challenges during prompt engineering in a collaborative setting as they need to actively keep aware of their collaborators' progress and intents. In this paper, we aim to investigate ways to assist programmers' prompt engineering in a collaborative context. We first conducted a formative study to understand the workflows and challenges of programmers when using NL for collaborative programming. Based on our findings, we implemented a prototype, CoPrompt, to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. Our user study indicates that CoPrompt assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs.

We present an initial step towards building a system for programmers to edit code using free-form sketch annotations drawn directly onto editor and output windows. Using a working prototype system as a technical probe, an exploratory study (N = 6) examines how programmers sketch to annotate Python code to communicate edits for an AI model to perform. The results reveal personalized workflow strategies and how similar annotations vary in abstractness and intention across different scenarios and users.

As users engage more frequently with AI conversational agents, conversations may exceed their “memory” capacity, leading to failures in correctly leveraging certain memories for tailored responses. However, in finding past memories that can be reused or referenced, users need to retrieve relevant information in various conversations and articulate to the AI their intention to reuse these memories. To support this process, we introduce Memolet, an interactive object that reifies memory reuse. Users can directly manipulate Memolet to specify which memories to reuse and how to use them. We developed a system demonstrating Memolet’s interaction across various memory reuse stages, including memory extraction, organization, prompt articulation, and generation refinement. We examine the system’s usefulness with an N=12 within-subject study and provide design implications for future systems that support user-AI conversational memory reusing.

Walking is a cyclic pattern of alternating footstep strikes, with each pair of steps forming a stride, and a series of strides forming a gait. We conduct a systematic examination of different kinds of intentional variations from a normal gait that could be used as input actions without interrupting overall walking progress. A design space of 22 candidate Gait Gestures is generated by adapting previous standing foot input actions and identifying new actions possible in a walking context. A formative study (n=25) examines movement easiness, social acceptability, and walking compatibility with foot movement logging to calculate temporal and spatial characteristics. Using a categorization of these results, 7 gestures are selected for a wizard-of-oz prototype demonstrating an AR interface controlled by Gait Gestures for ordering food and audio playback while walking. As a technical proof-of-concept, a gait gesture recognizer is developed and tested using the formative study data.

Programmers increasingly rely on Large Language Models (LLMs) for code generation. However, misalignment between programmers' goals and generated code complicates the code evaluation process and demands frequent switching between prompt authoring and code evaluation. Yet, current LLM-driven code assistants lack sufficient scaffolding to help programmers format intentions from their overarching goals, a crucial step before translating these intentions into natural language prompts. To address this gap, we adopted an iterative design process to gain insights into programmers' strategies when using LLMs for programming. Building on our findings, we created CoLadder, a system that supports programmers by facilitating hierarchical task decomposition, direct code segment manipulation, and result evaluation during prompt authoring. A user study with 12 experienced programmers showed that CoLadder is effective in helping programmers externalize their problem-solving intentions flexibly, improving their ability to evaluate and modify code across various abstraction levels, from goal to final code implementation.

Live streaming platforms and existing viewer participation tools enable users to interact and engage with an online community, but the anonymity and scale of chat usually result in the spread of negative comments. However, only a few existing moderation tools investigate the influence of proactive moderation on viewers' engagement and prosocial behavior. To address this, we developed StoryChat, a narrative-based viewer participation tool that utilizes a dynamic graphical plot to reflect chatroom negativity. We crafted the narrative through a viewer-centered (N=65) iterative design process and evaluated the tool with 48 experienced viewers in a deployment study. We discovered that StoryChat encouraged viewers to contribute prosocial comments, increased viewer engagement, and fostered viewers' sense of community. Viewers reported a closer connection between streamers and other viewers because of the narrative design, suggesting that narrative-based viewer engagement tools have the potential to encourage community engagement and prosocial behaviors.