Gonzalo Ramos

Jeevana Priya Inala, Chenglong Wang, Steven Drucker et al. · microsoft-research

This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow by translating high-level user intentions into executable code, charts, and insights. We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps. Finally, we discuss the research challenges that impede the development of these AI-based systems such as enhancing model capabilities, evaluating and benchmarking, and understanding end-user needs.

Javier Hernandez, Jina Suh, Judith Amores et al.

The rise of AI conversational agents has broadened opportunities to enhance human capabilities across various domains. As these agents become more prevalent, it is crucial to investigate the impact of different affective abilities on their performance and user experience. In this study, we surveyed 745 respondents to understand the expectations and preferences regarding affective skills in various applications. Specifically, we assessed preferences concerning AI agents that can perceive, respond to, and simulate emotions across 32 distinct scenarios. Our results indicate a preference for scenarios that involve human interaction, emotional support, and creative tasks, with influences from factors such as emotional reappraisal and personality traits. Overall, the desired affective skills in AI agents depend largely on the application's context and nature, emphasizing the need for adaptability and context-awareness in the design of affective AI conversational agents.

Catherine Yeh, Gonzalo Ramos, Rachel Ng et al. · microsoft-research

Large language models (LLMs) have become ubiquitous in providing different forms of writing assistance to different writers. However, LLM-powered writing systems often fall short in capturing the nuanced personalization and control needed to effectively support users -- particularly for those who lack experience with prompt engineering. To address these challenges, we introduce GhostWriter, an AI-enhanced design probe that enables users to exercise enhanced agency and personalization during writing. GhostWriter leverages LLMs to implicitly learn the user's intended writing style for seamless personalization, while exposing explicit teaching moments for style refinement and reflection. We study 18 participants who use GhostWriter on two distinct writing tasks, observing that it helps users craft personalized text generations and empowers them by providing multiple ways to control the system's writing style. Based on this study, we present insights on how specific design choices can promote greater user agency in AI-assisted writing and discuss people's evolving relationships with such systems. We conclude by offering design recommendations for future work.

Mohit Chandra, Suchismita Naik, Denae Ford et al. · gatech

Recent gains in popularity of AI conversational agents have led to their increased use for improving productivity and supporting well-being. While previous research has aimed to understand the risks associated with interactions with AI conversational agents, these studies often fall short in capturing the lived experiences of individuals. Additionally, psychological risks have often been presented as a sub-category within broader AI-related risks in past taxonomy works, leading to under-representation of the impact of psychological risks of AI use. To address these challenges, our work presents a novel risk taxonomy focusing on psychological risks of using AI gathered through the lived experiences of individuals. We employed a mixed-method approach, involving a comprehensive survey with 283 people with lived mental health experience and workshops involving experts with lived experience to develop a psychological risk taxonomy. Our taxonomy features 19 AI behaviors, 21 negative psychological impacts, and 15 contexts related to individuals. Additionally, we propose a novel multi-path vignette-based framework for understanding the complex interplay between AI behaviors, psychological impacts, and individual user contexts. Finally, based on the feedback obtained from the workshop sessions, we present design recommendations for developing safer and more robust AI agents. Our work offers an in-depth understanding of the psychological risks associated with AI conversational agents and provides actionable recommendations for policymakers, researchers, and developers.

Mohit Chandra, Javier Hernandez, Gonzalo Ramos et al. · gatech

Development in digital technologies has continuously reshaped how individuals seek and receive social and emotional support. While online platforms and communities have long served this need, the increased integration of general-purpose conversational AI into daily lives has introduced new dynamics in how support is provided and experienced. Existing research has highlighted both benefits (e.g., wider access to well-being resources) and potential risks (e.g., over-reliance) of using AI for support seeking. In this five-week, exploratory study, we recruited 149 participants divided into two usage groups: a baseline usage group (BU, n=60) that used the internet and AI as usual, and an active usage group (AU, n=89) encouraged to use one of four commercially available AI tools (Microsoft Copilot, Google Gemini, PI AI, ChatGPT) for social and emotional interactions. Our analysis revealed significant increases in perceived attachment towards AI (32.99 percentage points), perceived AI empathy (25.8 p.p.), and motivation to use AI for entertainment (22.90 p.p.) among the AU group. We also observed that individual differences (e.g., gender identity, prior AI usage) influenced perceptions of AI empathy and attachment. Lastly, the AU group expressed higher comfort in seeking personal help, managing stress, obtaining social support, and talking about health with AI, indicating potential for broader emotional support while highlighting the need for safeguards against problematic usage. Overall, our exploratory findings underscore the importance of developing consumer-facing AI tools that support emotional well-being responsibly, while empowering users to understand the limitations of these tools.

Subigya Nepal, Javier Hernandez, Talie Massachi et al.

Information workers increasingly struggle with productivity challenges in modern workplaces, facing difficulties in managing time and effectively utilizing workplace analytics data for behavioral improvement. Despite the availability of productivity metrics through enterprise tools, workers often fail to translate this data into actionable insights. We present a comprehensive, user-centric approach to address these challenges through AI-based productivity agents tailored to users' needs. Utilizing a two-phase method, we first conducted a survey with 363 participants, exploring various aspects of productivity, communication style, agent approach, personality traits, personalization, and privacy. Drawing on the survey insights, we developed a GPT-4 powered personalized productivity agent that utilizes telemetry data gathered via Viva Insights from information workers to provide tailored assistance. We compared its performance with alternative productivity-assistive tools, such as dashboard and narrative, in a study involving 40 participants. Our findings highlight the importance of user-centric design, adaptability, and the balance between personalization and privacy in AI-assisted productivity tools. By building on these insights, our work provides important guidance for developing more effective productivity solutions, ultimately leading to optimized efficiency and user experiences for information workers.

Priyan Vaithilingam, Elena L. Glassman, Nathalie Henry Riche et al.

People working with data often move their data across multiple applications, because they rely on these apps' complementing user experiences to best complete their tasks. Since traditional copy-and-paste approaches do not accommodate diverse table representations adopted by different apps, users spend considerable effort to reconstruct data formats and visual representations, making cross-app workflows costly. For example, when transferring a spreadsheet table with conditional formatting to a markup document, users spend substantial time translating its structure into appropriate tags and manually reformat color. This paper introduces MagicCopy, an AI-powered cross-app copy-and-paste, leveraging source and target contexts and user-specified instructions in natural language to automatically extract, parse, transform, and (re)format data from one app to another. In a study with sixteen participants, users quickly learned and applied MagicCopy to move data across three pairs of tools. Participants further explored diverse applications of MagicCopy to support more streamlined crossed-application interaction in their workflows.

Jina Suh, Lindy Le, Erfan Shayegani et al.

Empathy is increasingly recognized as a key factor in human-AI communication, yet conventional approaches to "digital empathy" often focus on simulating internal, human-like emotional states while overlooking the inherently subjective, contextual, and relational facets of empathy as perceived by users. In this work, we propose a human-centered taxonomy that emphasizes observable empathic behaviors and introduce a new dataset, Sense-7, of real-world conversations between information workers and Large Language Models (LLMs), which includes per-turn empathy annotations directly from the users, along with user characteristics, and contextual details, offering a more user-grounded representation of empathy. Analysis of 695 conversations from 109 participants reveals that empathy judgments are highly individualized, context-sensitive, and vulnerable to disruption when conversational continuity fails or user expectations go unmet. To promote further research, we provide a subset of 672 anonymized conversation and provide exploratory classification analysis, showing that an LLM-based classifier can recognize 5 levels of empathy with an encouraging average Spearman $ρ$=0.369 and Accuracy=0.487 over this set. Overall, our findings underscore the need for AI designs that dynamically tailor empathic behaviors to user contexts and goals, offering a roadmap for future research and practical development of socially attuned, human-centered artificial agents.

Lev Tankelevitch, Elena L. Glassman, Jessica He et al. · microsoft-research

Generative AI (GenAI) radically expands the scope and capability of automation for work, education, and everyday tasks, a transformation posing both risks and opportunities for human cognition. How will human cognition change, and what opportunities are there for GenAI to augment it? Which theories, metrics, and other tools are needed to address these questions? The CHI 2025 workshop on Tools for Thought aimed to bridge an emerging science of how the use of GenAI affects human thought, from metacognition to critical thinking, memory, and creativity, with an emerging design practice for building GenAI tools that both protect and augment human thought. Fifty-six researchers, designers, and thinkers from across disciplines as well as industry and academia, along with 34 papers and portfolios, seeded a day of discussion, ideation, and community-building. We synthesize this material here to begin mapping the space of research and design opportunities and to catalyze a multidisciplinary community around this pressing area of research.

Srishti Palani, Gonzalo Ramos · microsoft-research

Context is critical for meaningful interactions between people and Generative AI (GenAI). Yet mainstream tools offer limited means to orchestrate it, particularly across workflows that span multiple interactions, sessions, and models, as often occurs in creative projects. Re specifying prior details, juggling diverse artifacts, and dealing with context drift overwhelm users, obscure intent, and curtail creativity. To address these challenges, we present Orchid, a system that gives its users affordances to specify, reference, and monitor context throughout evolving workflows. Specifically, Orchid enables users to (1) specify context related to the project, themselves, and different styles, (2) reference these via explicit mentions, inline selection, or implicit grounding, and (3) monitor context assigned to different interactions across the workflow. In a within-subjects study (n=12), participants using Orchid to execute creative tasks (compared to a baseline toolkit of web search, LLM-based chat, and digital notebooks) produced more novel and feasible outcomes, reporting greater alignment between their intent and the AI's responses, higher perceived control, and increased transparency. By prioritizing context orchestration, Orchid offers an actionable step toward next generation GenAI tools that support complex, iterative workflows - enabling creators and AI to stay aligned and augment their creative potential.

Hayeong Song, Gonzalo Ramos, Peter Bodik

Creating Computer Vision (CV) models remains a complex practice, despite their ubiquity. Access to data, the requirement for ML expertise, and model opacity are just a few points of complexity that limit the ability of end-users to build, inspect, and improve these models. Interactive ML perspectives have helped address some of these issues by considering a teacher in the loop where planning, teaching, and evaluating tasks take place. We present and evaluate two interactive visualizations in the context of Sprite, a system for creating CV classification and detection models for images originating from videos. We study how these visualizations help Sprite's users identify (evaluate) and select (plan) images where a model is struggling and can lead to improved performance, compared to a baseline condition where users used a query language. We found that users who had used the visualizations found more images across a wider set of potential types of model errors.

Ahmed Elgohary, Christopher Meek, Matthew Richardson et al.

We study semantic parsing in an interactive setting in which users correct errors with natural language feedback. We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors. We show that NL-EDIT can boost the accuracy of existing text-to-SQL parsers by up to 20% with only one turn of correction. We analyze the limitations of the model and discuss directions for improvement and evaluation. The code and datasets used in this paper are publicly available at http://aka.ms/NLEdit.

Alex Mariakakis, Sifang Chen, Bichlien Nguyen et al.

Environmental hazards often go unnoticed because they are invisible to the naked eye, posing risks to our health over time. Project Calico aims to raise awareness of these risks by augmenting everyday fashion with color-changing chemical sensors that can be observed at a glance or captured by a smartphone camera. Project Calico leverages existing cosmetic and fabrication processes to democratize environmental sensing, enabling creators to make their own accessories. We present two fashionable instantiations of Project Calico involving UV irradiation. EcoHair, created by hair treatment, is UV-sensitive hair that intensifies in color saturation depending on the UV intensity. EcoPatches, created by inkjet printing, can be worn as temporary tattoos that change their color to reflect cumulative UV exposure over time. We present findings from two focus groups regarding the Project Calico vision and gathered insights from their overall impressions and projected use patterns.

Patrice Y. Simard, Saleema Amershi, David M. Chickering et al.

The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch between the demand for machine learning systems and the ability for organizations to build them. We believe that in order to meet this growing demand for machine learning systems we must significantly increase the number of individuals that can teach machines. We postulate that we can achieve this goal by making the process of teaching machines easy, fast and above all, universally accessible. While machine learning focuses on creating new algorithms and improving the accuracy of "learners", the machine teaching discipline focuses on the efficacy of the "teachers". Machine teaching as a discipline is a paradigm shift that follows and extends principles of software engineering and programming languages. We put a strong emphasis on the teacher and the teacher's interaction with data, as well as crucial components such as techniques and design principles of interaction and visualization. In this paper, we present our position regarding the discipline of machine teaching and articulate fundamental machine teaching principles. We also describe how, by decoupling knowledge about machine learning algorithms from the process of teaching, we can accelerate innovation and empower millions of new uses for machine learning models.