conduct human-centered design

Current assistive and augmentative communication (AAC) system design suffers from insufficient user involvement and low process accessibility, particularly for individuals with communication disabilities. Method: This study proposes a two-stage participatory design methodology specifically tailored for AAC users. It integrates closed-loop user feedback, accessibility-specific evaluation, and iterative human–computer interaction (HCI) design techniques—focusing on optimizing task structure, interaction modalities, and collaborative mechanisms to align with users’ cognitive, perceptual, and motor capabilities. Contribution/Results: The work introduces the first AAC-dedicated participatory framework that balances structural rigor with methodological flexibility. Empirical validation confirms its feasibility and demonstrates significant improvements in depth of user engagement, expressive efficacy, and influence of user input on design decisions. This approach advances inclusive HCI by delivering a reusable methodological foundation and actionable implementation pathway for equitable, user-centered AAC development.

This study addresses the challenge of meaningfully integrating adolescents as equitable co-designers—not merely subjects—into high school computer science curriculum development within generative AI education, with a focus on algorithmic auditing as a critical pedagogical practice. Method: Employing participatory design, co-facilitated workshops, and reflexive dialogue, researchers collaborated with teachers and adolescent participants to iteratively develop classroom activities and systematically identify design features that foster adolescent agency and epistemic authority. Contribution/Results: The work advances a novel intergenerational co-design paradigm, empirically demonstrating adolescents’ situated, experience-based expertise in critiquing sociotechnical systems. It yields actionable, theory-informed design principles for cross-generational curriculum co-creation, resulting in demonstrably enhanced criticality, contextual relevance, and pedagogical efficacy of AI literacy instruction.

This study addresses the limitations of traditional participatory design in developing external human-machine interfaces for autonomous vehicles—namely its small scale and high cost, which hinder effective capture of diverse user needs. To overcome these constraints, the authors propose a scalable, crowdsourced collaborative design paradigm that integrates high-frequency public ideation, structured participation mechanisms, and expert feedback through an iterative process to generate multimodal, context-aware interaction concepts. By combining video-based simulation evaluations, crowdsourced idea collection, and expert review, the resulting public-preference designs significantly outperform baseline and alternative approaches in terms of understandability and user experience. Moreover, hybrid solutions refined by experts also demonstrate strong performance, collectively validating the effectiveness and innovation of the proposed methodology.

This study investigates the pedagogical impact of generative AI (GenAI) when spontaneously adopted by graduate students in human–computer interaction (HCI) courses for interactive device design. Drawing on 12 post-class focus groups, behavioral coding, and pattern induction, we develop the first taxonomy of GenAI-mediated co-design behaviors—identifying four prototypical usage patterns. Results indicate that GenAI substantially enhances prototyping efficiency and ideational divergence but risks promoting superficial learning during problem framing and reflective synthesis. Crucially, *how* GenAI is used—not the task type—determines learning outcomes. Based on these findings, we propose “creative co-design” as a novel pedagogical paradigm for HCI education and provide empirically grounded, actionable instructional interventions to align curricula with GenAI-era design practice and competency development.

This paper addresses the challenge of operationalizing generative AI within collaborative software engineering teams. Drawing on a design study with 39 industry experts—including field observations, semi-structured interviews, and multi-role workshops—we systematically investigate how prompt engineering supports cross-functional AI prototyping and iterative co-design. Our study is the first to characterize three core phenomena in collaborative prompt prototyping: (1) the emergent construction of shared coordination norms, (2) dynamic role evolution across developers, domain experts, and AI specialists, and (3) context-sensitive evaluation mechanisms for prompt efficacy. We propose a generative-content-feature-driven rapid iteration paradigm and distill a reusable prompt prototyping strategy framework. Key technical challenges—including model opacity and example overfitting—are empirically identified. The findings provide both methodological grounding and actionable practice guidelines for industrial software teams, advancing the shift from generative AI as a technical capability to a collaborative design enabler.

This study addresses the design of agentic AI systems from a citizen-centered perspective, aiming to align such systems with societal values and ensure responsible development. Through three participatory workshops conducted in 2025, the research engaged diverse stakeholders using constructive design research methods, inviting the public to explore the potential community impacts of AI agency via narrative scenarios and low-fidelity prototypes. The work identifies three core design challenges: establishing sustained public engagement mechanisms, developing a shared language between experts and citizens, and translating speculative visions into implementable systems. The findings offer both actionable pathways and theoretical grounding for advancing reflective, long-term-oriented citizen-centered AI development.

This study addresses the persistent challenge designers face in understanding and operationalizing children’s agency within child–AI interaction design, a domain lacking dedicated support tools. To bridge this gap, the work proposes the first design framework explicitly centered on children’s agency. Developed through participatory workshops integrating qualitative analysis and design thinking methods, the framework enables designers to surface and articulate their implicit assumptions about agency and systematically navigate complex design trade-offs. By making tacit judgments explicit and structuring ethical deliberation, the framework not only fills a critical practical void in ethical child–AI design but also demonstrably enhances designers’ conceptual understanding of children’s agency, offering a concrete, actionable pathway for embedding ethical considerations into complex AI systems for young users.

This study addresses the risk of generative AI unilaterally shaping educational practice by engaging eleventh-grade Latinx students and high school teachers in a five-week participatory design process to collaboratively explore AI applications and pedagogical strategies. Centering youth voices, the project cultivated three critical AI literacy practices: collectively interrogating AI assumptions, co-learning through complementary expertise, and critically engaging AI through culturally grounded knowledge and creativity. Qualitative analysis of video recordings and design artifacts demonstrates that teacher–student collaboration not only enabled the co-construction of ethical and practical norms for AI use but also yielded a transferable framework of reflective practices. These findings offer an innovative pathway for integrating emerging technologies into education in ways that are equitable, contextually responsive, and critically informed.

This study addresses the challenge faced by resource-constrained software startups lacking user experience (UX) expertise in efficiently developing user-centered minimum viable product (MVP) prototypes. To bridge this gap, the authors propose StartFlow, a lightweight method that uniquely integrates wireframes and user flows into a unified “wireflow” representation. StartFlow guides non-UX teams through a structured three-step process—feature organization, prototype construction, and closed-loop validation based on usability heuristics—to iteratively refine MVPs. Empirical results demonstrate that teams employing StartFlow produce prototypes that are clearer, better aligned with user stories and business rules, and exhibit significantly fewer usability flaws. Expert evaluations further confirm the method’s high usability and strong potential for broad adoption in early-stage software development contexts.

Co-design is an increasingly popular approach in HCI and visualization, yet there is little guidance on how to effectively apply this method in visualization contexts. In this paper, we visually present our experience of a two-and-a-half-year co-design project with the local arts community. Focusing on facilitating community exploration and sense-making around arts funding distribution, the project involved a series of co-design sessions between visualization researchers and members of the arts community. Through these iterative sessions, we built shared understanding and developed visualization prototypes tailored to community needs. However, the practice is far from complete, and we found ourselves continually returning to the"fuzzy front end"of the co-design process. We share this ongoing story through comic-style visuals and reflect on three fuzzy front ends that we encountered during the project. By sharing these experiences with the visualization community, we hope to offer insights that others can draw on in their own community-engaged co-design work.