Senior architects are pivotal in shaping architectural projects, yet integrating Generative AI (GenAI) into their workflows presents notable challenges. A formative study (N=11) identified key pain points in their early concept design process. To address these, we developed EarlyArchi, a GenAI-driven system supporting automated concept generation and evaluation. In a within-subject study (N=13), participants used EarlyArchi for early-stage design tasks. Results showed enhanced perceived creativity, improved design competency, and more efficient ideation. However, concerns emerged regarding controllability and domain-specific accuracy, highlighting the need for features that preserve professional autonomy and trust. Further analysis revealed three GenAI involvement modes—fully AI-driven, GenAI-led, and human-led—emphasizing the importance of adaptive role allocation in balancing creative exploration with expert leadership. These findings offer insights into supporting senior architects through GenAI while identifying key considerations for designing future human–AI co-creation systems.
Professional self-representation involves constructing identities that reflect personal values while aligning with the norms of professional communities. Many people turn to generative AI for help, but misalignments between LLM outputs and self-understanding hinder authenticity and accuracy of the content. To explore how LLMs can support co-creation aligned, authentic self-representational content, we designed LL.me, a web-based probe based on bi-directional alignment that utilizes users’ resumes and guides them through iterative cycles of refining AI-generated self-representations. Our user study with 14 participants showed users engaged in identity work with the tool, re-framing content to emphasize their personal values, imparting tacit knowledge from their communities of practice, and leveraging system explainability features as a proxy for how the representation would be perceived by others. We demonstrate how LLM-based tools can facilitate a co-constructive process of identity formation, helping individuals actively shape their professional self-representations in collaboration with the AI.
LLM-infused tools have entered the newsroom, transforming journalistic work practices. A few studies have investigated how LLMs influence journalistic practices, but there is a lack of research on how to design LLM-infused tools to support trustworthy journalism. In this paper, we explore how prototyping within a defined design space can help identify and explore the challenges of trustworthy LLM integration in journalism. We conduct eight interviews with news industry stakeholders and identify five challenges for trustworthy journalism arising with the introduction of LLMs: factuality, neutrality, autonomy, efficiency, and AI literacy. Based on these challenges, we map a design space and iteratively explore four prototypes of interactive interfaces promoting trustworthy LLM-infused journalism, which are evaluated with news industry stakeholders. We discuss opportunities and conflicts within the design space, how interactive interfaces can be used to concretize guidelines for AI use, and challenges in incorporating Explainable AI into everyday tools for journalists.
Spoken English proficiency is a powerful driver of economic mobility for low-income Indian youth, yet opportunities for spoken practice remain scarce in schools. We investigate the deployment of a voice-based chatbot for English conversation practice across four low-resource schools in Delhi. Through a six-day field study combining observations and interviews, we captured the perspectives of students, teachers, and principals. Findings confirm high demand across all groups, with notable gains in student speaking confidence. Our multi-stakeholder analysis surfaced a tension in long-term adoption vision: students favored open-ended conversational practice, while administrators emphasized curriculum-aligned assessment. We offer design recommendations for voice-enabled chatbots in low-resource multilingual contexts, highlighting the need for more intelligible speech output for non-native learners, one-tap interactions with simplified interfaces, and actionable analytics for educators. Beyond language learning, our findings inform the co-design of future AI-based educational technologies that are socially sustainable within the complex ecosystem of low-resource schools.
Vibe Coding is conceptualised as a co-constituted form of programming through which humans and AI tools engage in the mutual shaping of a piece of code. Using design provocations in the form of three different programming assistants, we examine how intentions, control, and outcomes emerge through mutual shaping between programmers, AI-tools, code, and visual sketches. The analysis reveals a set of interrelated themes that foreground the tensions that emerge in participants’ interactions with the programming assistants. A set of design configurations is identified in relation to how these programming processes unfold. We use this to outline how vibe coding can be understood as a decentered form of programming that emphasises the mutual co-constitution and shifting boundaries among humans and AI. We argue that this suggests a reconfiguration of how AI-based programming is understood - emphasising the evolving, co-creative interactions in which intention and control are mutually shaped.
AI tools are increasingly used for UI evaluation, yet most treat evaluation as a single-pass, black-box process that limits both effective model reasoning and human involvement. Grounded in Situation Awareness (SA) theory, we reframe single-screen heuristic evaluation of mobile UIs as stagewise human--AI co-critique, structuring evaluation into three editable stages: Perception (what is on the screen), Comprehension (what elements mean and do), and Projection (what problems and fixes follow). We instantiate this framing in Criticmate, an interactive system that exposes intermediate reasoning artifacts for intervention. Across offline benchmarks and a controlled user study, we show that stagewise co-critique yields more expert-like and better balanced critiques than single-pass approaches, while supporting higher trust and engagement without reducing perceived autonomy.
The proliferation of efficiency-focused AI tools in creative processes threatens to undermine critical, reflective practices foundational to design education. This approach can lead to creativity exhaustion and diminished agency among designers and students. As an antidote, we propose Reflective AI: an approach grounded in slow technology principles that reframes AI not as a production tool, but as a medium for reflecting on the creative process itself. This paper presents the Objective Portrait Workshop where design students engaged in slowed data collection, annotation, and model finetuning. Our contribution is threefold: we (1) document a methodology for implementing Reflective AI in design education; (2) provide empirical evidence that slow engagement cultivates reflection on creative processes and technical understanding of AI; and (3) propose material and temporal disentanglement as core mechanisms for Reflective AI practice. This work offers a practical alternative to "fast'' AI, providing methodology that cultivates critical capabilities essential to design.