{
 "@context": "https://schema.org",
 "@type": "ScholarlyArticle",
 "@id": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#paper",
 "aboutThisFile": {
  "whatThisIs": "A research brief: a structured summary of one paper, prepared for seanrintel.com from the paper's full text.",
  "howItWasMade": "This brief was prepared with AI assistance and published by Sean Rintel. It is not the authors' published text.",
  "whatIsVerbatim": "Only 'quote' fields, figure captions and 'abstract' are the authors' own words. Research questions follow the paper's wording where it states them. Takeaway, summaries, answers, definitions and method are the site's plain-language paraphrase.",
  "howItIsChecked": "Before publication every quote is matched against the paper and every number in the brief is found in it. 'verified' is the date of the last check.",
  "howToUse": [
   "For a quick answer, use 'takeaway' and 'questions'. For evidence, use 'findings' (each has a verbatim quote, its location in the paper and a 'url' anchored to that finding on the paper's page).",
   "Locations such as '§5.2, p. 9' refer to the version at 'pageNumbersReferTo'.",
   "For anything not covered here, read the paper itself: 'fullTextSources' lists free versions first.",
   "If 'researchOverview' is present, the paper is part of one of Sean Rintel's research overviews: it gives the overview's thesis, the claims this paper is evidence for and its role in each, and the other papers in the overview.",
   "To find other papers by Sean Rintel, use the catalogue at https://seanrintel.com/publications/index.json."
  ],
  "authorship": "Sean Rintel's role on each paper: lead author when he is first author, sole author when he is the only author, and otherwise senior author. Senior author here means the senior researcher on the team, whatever his position in the author list.",
  "howToCite": "Cite the paper, not this file: use 'citation' or the ready-made 'bibtex' (DOI where given) and name every author. Attribute paraphrase to the paper's findings, and use quotation marks only for 'quote' text."
 },
 "name": "Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence",
 "author": [
  {
   "@type": "Person",
   "name": "Marcel Borowski"
  },
  {
   "@type": "Person",
   "name": "Janus Bager Kristensen"
  },
  {
   "@type": "Person",
   "name": "Payod Panda"
  },
  {
   "@type": "Person",
   "@id": "https://seanrintel.com/#sean-rintel",
   "name": "Sean Rintel",
   "url": "https://seanrintel.com/",
   "sameAs": [
    "https://orcid.org/0000-0003-0840-0546",
    "https://scholar.google.com/citations?user=xc25GRgAAAAJ",
    "https://www.wikidata.org/wiki/Q102369654",
    "https://www.microsoft.com/en-us/research/people/serintel/",
    "https://www.linkedin.com/in/seanrintel"
   ]
  },
  {
   "@type": "Person",
   "name": "Niklas Elmqvist"
  },
  {
   "@type": "Person",
   "name": "Jens Emil Sloth Grønbæk"
  },
  {
   "@type": "Person",
   "name": "Clemens Nylandsted Klokmose"
  }
 ],
 "datePublished": "2026",
 "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html",
 "citation": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026.",
 "bibtex": "@inproceedings{borowski2026stund,\nauthor = {Borowski, Marcel and Kristensen, Janus Bager and Panda, Payod and Rintel, Sean and Elmqvist, Niklas and Grønbæk, Jens Emil Sloth and Klokmose, Clemens Nylandsted},\ntitle = {Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence},\nbooktitle = {UIST 2026},\nyear = {2026},\npublisher = {ACM},\nurl = {https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html},\n}",
 "abstract": "Time is a second-class citizen in most collaborative software: activity traces are fragmented across tools or entirely ephemeral. We introduce Stund, an activity-enriched collaborative workspace where all activities—voice, video, interactions, and content edits—leave traces that become part of the medium of the ongoing collaboration. Unlike traditional chatbots or meeting assistants, artificial intelligence (AI) is embedded in the medium as well, allowing users to directly leverage traces through it. We demonstrate this through scenarios such as: spontaneously creating an instrument during the meeting to play back the recorded conversation around a particular spreadsheet edit; automatically detecting when someone is absent to summarize what was missed when they return; or detecting and resurfacing when sticky notes have been shaken in excitement when ideas are presented. The entire workspace is queryable, transformable, and reified through AI. Stund introduces a new approach to malleable collaborative software, where activity traces and AI are an integral part of the workspace medium.",
 "fullTextSources": [
  {
   "kind": "freeAccess",
   "url": "https://pure.au.dk/ws/portalfiles/portal/472319208/StundUIST2026AuthorsCopy.pdf",
   "label": "Author's Version"
  }
 ],
 "fullTextAvailable": true,
 "takeaway": "Collaborative software can become malleable by remembering how work happened. When every voice, video and edit leaves a trace that AI can query, history becomes working material. Teams could build tools mid-meeting, like replaying talk behind a spreadsheet edit or catching up a returning colleague.",
 "researchOverview": {
  "name": "Better Meetings",
  "page": "https://seanrintel.com/better-meetings.html",
  "json": "https://seanrintel.com/overviews/better-meetings.json",
  "markdown": "https://seanrintel.com/overviews/better-meetings.md",
  "thesis": "A meeting's purpose should shape everything about it, yet many meetings run without one stated. Good help with meeting goals moves people from wherever they start, with depth that fits the meeting.",
  "claimsThisPaperFeeds": [
   {
    "claim": "A meeting's purpose is easily lost between meetings unless something carries it forward",
    "role": "supporting evidence",
    "url": "https://seanrintel.com/better-meetings.html#m5"
   }
  ],
  "otherPapers": [
   {
    "study": "Interviews: how people hold meeting goals",
    "title": "Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies",
    "page": "https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.html",
    "researchBrief": "https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json"
   },
   {
    "study": "Probe study: AI-drafted meeting plans",
    "title": "The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings",
    "page": "https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.json"
   },
   {
    "study": "Coaching study: an AI coach before real meetings",
    "title": "What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection",
    "page": "https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.html",
    "researchBrief": "https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json"
   },
   {
    "study": "Probe study: goal check-ins during meetings",
    "title": "Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings",
    "page": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json"
   },
   {
    "study": "Recordings and design: looking back and ahead in meetings",
    "title": "Designing Interfaces that Support Temporal Work Across Meetings with Generative AI",
    "page": "https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.html",
    "researchBrief": "https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.json"
   },
   {
    "study": "Field experiment: nudging attention to meeting goals",
    "title": "Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment",
    "page": "https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.html",
    "researchBrief": "https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json"
   },
   {
    "study": "Position paper: goals in human-AI work",
    "title": "Goals as First-Class Abstractions in Human-AI Collaboration",
    "page": "https://seanrintel.com/publications/goals-as-first-class-abstractions-in-human-ai-collaboration.html",
    "researchBrief": "https://seanrintel.com/publications/goals-as-first-class-abstractions-in-human-ai-collaboration.json"
   },
   {
    "study": "Conversation analysis: designing for the meeting",
    "title": "(Re)Configuring Hybrid Meetings: Moving from User-Centered Design to Meeting-Centered Design",
    "page": "https://seanrintel.com/publications/reconfiguring-hybrid-meetings-moving-from-user-centered-design-to-meeting-centered-design.html",
    "researchBrief": "https://seanrintel.com/publications/reconfiguring-hybrid-meetings-moving-from-user-centered-design-to-meeting-centered-design.json"
   },
   {
    "study": "Interviews and narration: what attention in video is for",
    "title": "Classification of Functional Attention in Video Meetings",
    "page": "https://seanrintel.com/publications/classification-of-functional-attention-in-video-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/classification-of-functional-attention-in-video-meetings.json"
   },
   {
    "study": "Interviews: low engagement as a choice",
    "title": "Low Engagement As a Deliberate Practice of Remote Participants in Video Meetings",
    "page": "https://seanrintel.com/publications/low-engagement-as-a-deliberate-practice-of-remote-participants-in-video-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/low-engagement-as-a-deliberate-practice-of-remote-participants-in-video-meetings.json"
   },
   {
    "study": "Research synthesis: collaboration and meetings",
    "title": "Collaboration and Meetings – Chapter 1 of the 2021 New Future of Work report",
    "page": "https://seanrintel.com/publications/collaboration-and-meetings.html"
   },
   {
    "study": "Telemetry and diaries: multitasking in remote meetings",
    "title": "Large Scale Analysis of Multitasking Behavior During Remote Meetings",
    "page": "https://seanrintel.com/publications/large-scale-analysis-of-multitasking-behavior-during-remote-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/large-scale-analysis-of-multitasking-behavior-during-remote-meetings.json"
   },
   {
    "study": "Survey and dashboard study: feedback on inclusive meetings",
    "title": "MeetingCoach: An Intelligent Dashboard for Supporting Effective and Inclusive Meetings",
    "page": "https://seanrintel.com/publications/meetingcoach-an-intelligent-dashboard-for-supporting-effective-inclusive-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/meetingcoach-an-intelligent-dashboard-for-supporting-effective-inclusive-meetings.json"
   },
   {
    "study": "Survey and diaries: chat alongside video meetings",
    "title": "The Promise and Peril of Parallel Chat in Video Meetings for Work",
    "page": "https://seanrintel.com/publications/the-promise-and-peril-of-parallel-chat-in-video-meetings-for-work.html",
    "researchBrief": "https://seanrintel.com/publications/the-promise-and-peril-of-parallel-chat-in-video-meetings-for-work.json"
   },
   {
    "study": "Diary study: video meetings in the pandemic",
    "title": "Meeting (the) Pandemic: Videoconferencing  Fatigue and Evolving Tensions of Sociality  in Enterprise Video Meetings During  COVID-19",
    "page": "https://seanrintel.com/publications/meeting-the-pandemic-videoconferencing-fatigue-and-evolving-tensions-of-sociality-in-enterprise-video-meetings-during-covid-19.html",
    "researchBrief": "https://seanrintel.com/publications/meeting-the-pandemic-videoconferencing-fatigue-and-evolving-tensions-of-sociality-in-enterprise-video-meetings-during-covid-19.json"
   },
   {
    "study": "Survey and telemetry: chat and voice in meetings",
    "title": "Virtual voices: Exploring individual differences in chat and verbal participation in virtual meetings",
    "page": "https://seanrintel.com/publications/virtual-voices-exploring-individual-differences-in-chat-and-verbal-participation-in-virtual-meetings.html",
    "researchBrief": "https://seanrintel.com/publications/virtual-voices-exploring-individual-differences-in-chat-and-verbal-participation-in-virtual-meetings.json"
   }
  ]
 },
 "whyItMatters": {
  "stateOfTheArt": {
   "summary": "Most software treats activity history as an afterthought, and AI meeting tools work on single modalities such as transcripts, detached from what is happening in the shared workspace.",
   "quote": "Existing AI-assisted meeting systems-commercial or research-operate on single modalities or treat AI as a conversational layer detached fromworkspace state.",
   "location": "§2.2, p. 3"
  },
  "contribution": {
   "summary": "Rather than adding another AI assistant beside the workspace, the authors make the workspace's whole recorded history part of the medium, building on the theory of interaction substrates. The authors demonstrate this with a working system and a five-part scenario.",
   "quote": "This accumulation of content, context, and bespoke capability growing together in AI-mediated substrates is, we argue, what distinguishes AECWs from existing collaborative tools",
   "location": "§5.6, p. 8"
  },
  "whoCares": {
   "summary": "Researchers and designers of collaborative, malleable and AI-enabled software, and teams who meet and work together remotely. The paper also flags the privacy and surveillance stakes for participants.",
   "quote": "We see Stund as an experimental platform that enables research to explore these tensions empirically",
   "location": "§7.3, p. 11"
  }
 },
 "researchQuestions": [
  "How can collaborative workspaces make activity history (voice, video, interactions and content edits) a first-class resource that collaborators can query and build on during their work?",
  "What becomes possible when AI is embedded in the workspace medium, rather than acting as a separate assistant, to turn activity traces into bespoke instruments?"
 ],
 "concepts": [
  {
   "term": "Activity-enriched collaborative workspace (AECW)",
   "definition": "The authors' concept, inspired by Hollan's vision of activity-enriched computing:",
   "quote": "computer-mediated collaboration spaces where heterogeneous activity traces from both communication and interaction are captured as part of the workspace",
   "location": "§1, p. 2"
  },
  {
   "term": "Material and temporal substrates",
   "definition": "The two substrates of an AECW, after Mackay and Beaudouin-Lafon. The difference between them:",
   "quote": "State in the material substrate is mutable, i.e., commands can manipulate it, while activity traces are immutable, making the temporal substrate append-only.",
   "location": "§3, p. 4"
  },
  {
   "term": "Reification",
   "definition": "Turning commands and effects into reusable instruments. For example,",
   "quote": "the command to create four sticky notes in different colors can be reified into a \"create-four-sticky-notes\" instrument",
   "location": "§3.1, p. 4"
  },
  {
   "term": "AI-as-medium",
   "definition": "AI doing clerical, custodial and creational work inside the workspace, rather than acting as a separate assistant, tool or teammate:",
   "quote": "This approach represents an \"AI-as-medium\" view of integrating generative AI into software, where AI is part of the computational fabric of the workspace",
   "location": "§1, p. 2"
  }
 ],
 "method": {
  "design": "Systems contribution: a conceptual model, a functional implementation, and a five-part use scenario demonstrating its capabilities (no user study).",
  "prototype": "Stund, a web-based shared infinite canvas (built on Webstrates, Codestrates and the tldraw canvas) holding live video feeds, sticky notes, documents and shapes, with an AI chat sidebar. As people talk and work, Stund records their audio, video, canvas actions and chats as time-stamped traces on a Java server and transcribes speech automatically. Users can select items and ask the chat about past activity ('What did this mean?') or have it arrange content. They can also have it write 'processors' that derive new traces (for example, detecting a shaken note or someone leaving the camera) and 'widgets' (small interactive tools on the canvas such as a note counter or a catch-up summary). Widgets can be shared and recombined through a repository. The chat passes requests to specialised AI 'experts', which can use different models, such as frontier models for writing code. There was no comparison in a study. A table contrasts Stund's capabilities with those of a basic chatbot given transcripts and interaction logs.",
  "prototypeFigure": 2,
  "setting": "Remote collaboration on a shared online canvas with audio and video. The scenario follows a team writing a grant proposal over a day.",
  "sample": "Scenario of three remote collaborators (Anna, Bo and Carl) writing a grant proposal over a day. The authors also used Stund in their own meetings and other domains.",
  "analysis": "Demonstration of capabilities through the scenario, a capabilities overview comparing Stund's components with a basic LLM chatbot baseline (Table 1), and informal testing of models and costs."
 },
 "findings": [
  {
   "headline": "Asking why a note exists.",
   "summary": "In the authors' scenario, three remote collaborators writing a grant proposal selected a sticky note nobody could explain and asked the system what it meant. It found the conversation in which the note was made, which the authors know of no current system doing.",
   "quote": "the system responds that they made a reference to the zoning colors in the classic computer game SimCity (1989) when talking about mixed residential and commercial neighborhoods",
   "location": "§5.1, p. 6",
   "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-1-p-6",
   "cite": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026. (§5.1, p. 6)"
  },
  {
   "headline": "Inventing new awareness on the spot.",
   "summary": "In the authors' scenario, one collaborator had the AI build a detector for a team habit during a coffee break, along with a widget listing what it caught. This is a new kind of activity awareness defined by the team itself.",
   "quote": "Bo notices that they tend to shake sticky notes for emphasis.",
   "location": "§5.2, p. 6",
   "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-2-p-6",
   "cite": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026. (§5.2, p. 6)"
  },
  {
   "headline": "Catch-up tools built live.",
   "summary": "When a collaborator caring for a sick child asked what he had missed, a colleague had the AI build a widget that summarises the last few minutes of talk and activity. It was assembled from live recordings rather than after the meeting.",
   "quote": "Carl suggests extending the widget to also rely on activity traces from a video processor to detect when someone has stepped away from the camera and automatically adjust the summary duration.",
   "location": "§5.3, p. 7",
   "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-3-p-7",
   "cite": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026. (§5.3, p. 7)"
  },
  {
   "headline": "Tools that recombine.",
   "summary": "Widgets could be shared, reused and combined. In the authors' scenario, the team linked a spreadsheet's edit history to the conversation at the time of each edit, with playback of the voice recording.",
   "quote": "they realize that they cannot remember why the operating budget was lower in year three",
   "location": "§5.4, p. 7",
   "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-4-p-7",
   "cite": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026. (§5.4, p. 7)"
  },
  {
   "headline": "Writing tools needs big models.",
   "summary": "In the authors' informal use, smaller AI models handled most organising and summarising, but writing widget code ran smoothly only with a frontier model, and an open-source model needed more iteration.",
   "quote": "When we have used frontier models such as Claude Opus 4.6 for developing widgets, the token cost could reach several USD per widget.",
   "location": "§7.2, p. 10",
   "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s7-2-p-10",
   "cite": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026. (§7.2, p. 10)"
  },
  {
   "headline": "Awareness or surveillance.",
   "summary": "The activity traces that make past work useful can also enable surveillance. What matters is who controls what is captured, and why.",
   "quote": "One cannot know how past actions may be reinterpreted by a processor that does not yet exist.",
   "location": "§7.3, pp. 10–11",
   "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s7-3-pp-10-11",
   "cite": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026. (§7.3, pp. 10–11)"
  }
 ],
 "questions": [
  {
   "question": "Can AI explain why something is on a shared whiteboard?",
   "answer": "It can, if the workspace records what was said as well as what was edited. AI can then find when a note was made, retrieve the talk around that moment and explain it. A chatbot given only transcripts might answer too, but without the link back to the note.",
   "source": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026.",
   "basedOn": [
    {
     "location": "§5.1, p. 6",
     "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-1-p-6"
    }
   ]
  },
  {
   "question": "Can people build their own meeting tools during a meeting with AI?",
   "answer": "In principle. In a demonstration scenario, collaborators ask the workspace's AI chat to write small tools on the shared canvas. Examples are a note counter, a detector for a team habit and a catch-up summary, which they then reuse and combine. Whether real teams can do this is untested.",
   "source": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026.",
   "basedOn": [
    {
     "location": "§5.2, p. 6",
     "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-2-p-6"
    },
    {
     "location": "§5.3, p. 7",
     "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-3-p-7"
    },
    {
     "location": "§5.4, p. 7",
     "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s5-4-p-7"
    }
   ]
  },
  {
   "question": "Which AI models are needed to build tools inside a collaborative workspace?",
   "answer": "In informal testing, smaller models handled most organising and summarising, but writing widget code ran smoothly only with a frontier model. An open-source model could get similar results with more iteration.",
   "source": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026.",
   "basedOn": [
    {
     "location": "§7.2, p. 10",
     "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s7-2-p-10"
    }
   ]
  },
  {
   "question": "Is recording everything in a shared workspace a privacy risk?",
   "answer": "Yes. The activity history that makes past work useful can also enable surveillance, and past actions could be reinterpreted by analyses that do not yet exist. Monitoring that workers control may constrain them less than imposed monitoring. Letting individuals switch off their own recording may partly help.",
   "source": "Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026.",
   "basedOn": [
    {
     "location": "§7.3, pp. 10–11",
     "url": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html#at-s7-3-pp-10-11"
    }
   ]
  }
 ],
 "cites": [
  {
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html",
   "title": "Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings",
   "location": "p. 12"
  },
  {
   "url": "https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.html",
   "title": "Designing Interfaces that Support Temporal Work Across Meetings with Generative AI",
   "location": "p. 13"
  },
  {
   "url": "https://seanrintel.com/publications/making-space-for-social-time-supporting-conversational-transitions-before-during-and-after-video-meetings.html",
   "title": "Making Space for Social Time: Supporting Conversational Transitions Before, During, and After Video Meetings",
   "location": "p. 12"
  },
  {
   "url": "https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.html",
   "title": "The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings",
   "location": "p. 12"
  }
 ],
 "quantitative": [
  {
   "measure": "Cost of simple retrieval queries with Claude Sonnet 4.6",
   "value": "usually less than 0.05 USD each",
   "location": "§7.2, p. 10"
  }
 ],
 "implications": [
  {
   "summary": "Treat activity history as a first-class resource in collaborative software, with AI woven into the workspace rather than added as a further silo."
  },
  {
   "summary": "The conceptual model does not depend on current AI limitations.",
   "quote": "is not a workaround for limitations of current AI",
   "location": "§7.2, p. 10"
  },
  {
   "summary": "Stund may shift who bridges the socio-technical gap, letting users act as designers of their own workspace.",
   "quote": "Its malleability may shift the challenge of bridging the socio-technical gap: it is no longer solely the designer's responsibility but also that of the users",
   "location": "§7.1, p. 9"
  }
 ],
 "limitations": [
  {
   "summary": "No evaluation with users yet.",
   "quote": "we have not demonstrated whether such a system is comprehensible to users or provides value in actual collaborative work",
   "location": "§7.4, p. 11"
  },
  {
   "summary": "Instrumentation is limited to processors and rectangular widgets.",
   "quote": "Instrumentation is only possible through processors and widgets confined to rectangles.",
   "location": "§7.4, p. 11"
  },
  {
   "summary": "Prototype constraints include one session per workspace, nightly flushing of history, minimal sandboxing, and resource-heavy LLM vision processors.",
   "quote": "Widgets and processors currently have minimal sandboxing; such security measures would be needed for production.",
   "location": "§7.4, p. 11"
  },
  {
   "summary": "The canvas and chat give low discoverability of Stund's capabilities."
  }
 ],
 "figures": [
  {
   "src": "https://seanrintel.com/publications/figures/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence/fig-1.webp",
   "caption": "Figure 1: Activity-Enriched Collaborative Workspaces. A workspace consists of a material substrate where collaborative activity happens, and a temporal substrate where this activity leaves traces over time. In Stund, the material substrate is a collaborative canvas that includes notes, video feeds, and user-made interactive widgets such as a custom spreadsheet widget for a grant budget or a situational widget showing a list of notes that have recently been shaken to indicate importance. Audio/video feeds, canvas interactions, widgets, and the chat all leave traces in the temporal substrate. Activity traces can be derived from others. Transcripts are derived from audio feeds, and a user-made processor may derive shake traces from a note being moved back and forth in rapid succession. In a sidebar chat, users can issue commands to query activity traces (\"Why is this here?\"), manipulate the canvas (\"Put to-dos in red notes beside our notes.\"), or create processors (\"Detect when a note is shaken.\") and widgets (\"Show a live-updating list of recently shaken notes.\").",
   "alt": "Left: timeline of activity trace tracks over time (video, person present, audio, transcripts, topics, AI chats, element moved, shaken and edited, spreadsheet edited). Right: the shared canvas with notes, video feeds, widgets and chat.",
   "location": "Fig. 1, p. 1",
   "credit": "Figure 1 from Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026."
  },
  {
   "src": "https://seanrintel.com/publications/figures/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence/fig-2.webp",
   "caption": "Figure 2: Stund Interface. The interface is structured around a shared canvas and a chat sidebar. Custom elements, including documents, widgets, and video feeds, can be placed along regular elements (here notes, images, arrows, shared cursors) in the canvas (paper cover image by [31]). The chat supports multiple tabs-local or shared-where shared tabs show presence indicators and can be collaboratively authored. Chat messages can include elements or images in their context. Here, the chat summarizes the contents of the spreadsheet widget, with its reply displayed in the context of that element. The chat has toggles to activate the write-access abilities: canvas, widget, and processor. A sidebar on the right gives access to control panels for model selection, repository dialogues, and buttons to start or stop media streams.",
   "alt": "Annotated screenshot of Stund: a canvas with a video feed, spreadsheet widget, document, sticky notes and search widget, a chat sidebar with tabs and ability toggles, and a right-hand bar of repositories and media controls.",
   "location": "Fig. 2, p. 5",
   "credit": "Figure 2 from Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026."
  },
  {
   "src": "https://seanrintel.com/publications/figures/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence/fig-4.webp",
   "caption": "Figure 4: Stund's Client-Server Architecture. Active code components are colored orange and passive data components are colored green. The client collects data with recorders and sends them via WebRTC to the ingest module, which unpacks and stores the data. The processing module creates a raw activity model, which is filtered by the model module. The client model is streamed to the activity session manager of the client via WebSocket. From there it is used by the AI chat and widgets. The experts of the AI chat have read/write access to elements and widgets on the canvas and to custom processor schemas. The latter can be used to add new processors to a session via WebSocket calls.",
   "alt": "Architecture diagram: client recorders send traces via WebRTC to the server's ingest and processing modules, and a filtered client model streams back via WebSocket to the activity session manager, used by the AI chat experts and widgets.",
   "location": "Fig. 4, p. 9",
   "credit": "Figure 4 from Marcel Borowski, Janus Bager Kristensen, Payod Panda, Sean Rintel, Niklas Elmqvist, Jens Emil Sloth Grønbæk, and Clemens Nylandsted Klokmose. 2026. Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence. UIST 2026."
  }
 ],
 "pageNumbersReferTo": "https://pure.au.dk/ws/portalfiles/portal/472319208/StundUIST2026AuthorsCopy.pdf",
 "verified": "2026-10-25",
 "studyFigure": {
  "about": "The opening figure on this paper's page, made for the site with AI assistance from this verified brief. It is not the paper's own figure. Evidence entries index this file's quantitative, findings and limitations arrays.",
  "study": {
   "kind": "single",
   "heading": "The paper",
   "summary": "A systems paper presenting Stund, a working shared online workspace that records how a team works and lets AI build on that history. It is demonstrated through a scenario and has not yet been tested with users.",
   "steps": [
    {
     "label": "A concept",
     "detail": "The authors define activity-enriched collaborative workspaces, which capture talk and actions as part of the workspace itself."
    },
    {
     "label": "A working system",
     "detail": "Stund was built as a shared online canvas with live video, sticky notes, documents and an AI chat."
    },
    {
     "label": "A scenario",
     "detail": "Three remote colleagues write a grant proposal over a day, using the system's capabilities."
    },
    {
     "label": "Comparison and testing",
     "detail": "A table contrasts Stund with a basic chatbot given transcripts and logs. The authors also tested AI models and costs informally."
    }
   ]
  },
  "tool": {
   "heading": "The system",
   "steps": [
    {
     "title": "Record activity",
     "text": "As people talk and work, Stund stores audio, video, canvas actions and chats as time-stamped traces, and transcribes speech.",
     "part": true
    },
    {
     "title": "Ask about the past",
     "text": "People select items and ask the AI chat about past activity, such as what a note meant, or have it arrange content."
    },
    {
     "title": "Derive new traces",
     "text": "On request, the AI writes processors that detect events in the traces, such as a shaken note or someone leaving the camera.",
     "part": true
    },
    {
     "title": "Build widgets",
     "text": "The AI also writes widgets, small interactive tools on the canvas such as a note counter or a catch-up summary.",
     "part": true
    },
    {
     "title": "Share and recombine",
     "text": "Widgets can be shared and recombined through a repository."
    }
   ],
   "note": "The chat passes requests to specialised AI experts, which can use different models. There was no user study."
  },
  "findings": {
   "heading": "What the paper proposes",
   "legend": null,
   "stages": [
    {
     "title": "In the scenario",
     "sub": "what the system did for three remote colleagues",
     "items": [
      {
       "dir": "none",
       "text": "In the scenario, the AI explained an unclear note by finding the talk that produced it.",
       "detail": "The authors know of no current system that links a note back to the conversation in which it was made.",
       "evidence": [
        "findings[0]"
       ]
      },
      {
       "dir": "none",
       "text": "In the scenario, a colleague had the AI build a detector for a team habit.",
       "detail": "During a coffee break, the AI made a detector for shaken sticky notes and a widget listing what it caught. The team defined this kind of awareness itself.",
       "evidence": [
        "findings[1]"
       ]
      },
      {
       "dir": "none",
       "text": "In the scenario, the AI built a catch-up tool for a colleague who had stepped away.",
       "detail": "The widget summarises the last few minutes of talk and activity, assembled from live recordings rather than after the meeting.",
       "evidence": [
        "findings[2]"
       ]
      },
      {
       "dir": "none",
       "text": "In the scenario, the team linked spreadsheet edits to the talk behind each edit.",
       "detail": "Combining shared widgets let the team play back the voice recording behind an edit, such as why a budget figure was lower.",
       "evidence": [
        "findings[3]"
       ]
      }
     ]
    },
    {
     "title": "Informal testing and open questions",
     "sub": "the authors' own use and the paper's discussion",
     "items": [
      {
       "dir": "none",
       "text": "In the authors' informal use, only a frontier model wrote widget code smoothly.",
       "detail": "A frontier model is among the most capable AI models. Smaller models handled most organising and summarising. Simple retrieval queries usually cost less than 0.05 USD each.",
       "evidence": [
        "findings[4]",
        "quantitative[0]"
       ]
      },
      {
       "dir": "none",
       "text": "The paper argues the same activity traces could also enable surveillance.",
       "detail": "What matters is who controls what is captured, and why. Past actions could be reinterpreted by processors that do not yet exist.",
       "evidence": [
        "findings[5]"
       ]
      }
     ]
    }
   ]
  },
  "keyTerm": "activity-enriched collaborative workspace",
  "takeaway": "Activity-enriched collaborative workspaces could let teams use AI to build their own tools from how work happened. The same records raise questions about who controls what is captured."
 }
}