{
 "@context": "https://schema.org",
 "@type": "ScholarlyArticle",
 "@id": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.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": "Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings",
 "author": [
  {
   "@type": "Person",
   "name": "Xinyue Chen"
  },
  {
   "@type": "Person",
   "name": "Lev Tankelevitch"
  },
  {
   "@type": "Person",
   "name": "Rishi Vanukuru"
  },
  {
   "@type": "Person",
   "name": "Ava Elizabeth Scott"
  },
  {
   "@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"
   ]
  }
 ],
 "datePublished": "2025-04",
 "doi": "10.1145/3706598.3714052",
 "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html",
 "citation": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052",
 "bibtex": "@inproceedings{chen2025are,\nauthor = {Chen, Xinyue and Tankelevitch, Lev and Vanukuru, Rishi and Scott, Ava Elizabeth and Panda, Payod and Rintel, Sean},\ntitle = {Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings},\nbooktitle = {CHI 2025},\nyear = {2025},\nmonth = {April},\npublisher = {ACM},\nurl = {https://doi.org/10.1145/3706598.3714052},\ndoi = {10.1145/3706598.3714052},\n}",
 "abstract": "Meetings often suffer from a lack of intentionality, such as unclear goals and straying off-topic. Identifying goals and maintaining their clarity throughout a meeting is challenging, as discussions and uncertainties evolve. Yet meeting technologies predominantly fail to support meeting intentionality. AI-assisted reflection is a promising approach. To explore this, we conducted a technology probe study with 15 knowledge workers, integrating their real meeting data into two AI-assisted reflection probes: a passive and active design. Participants identified goal clarification as a foundational aspect of reflection. Goal clarity enabled people to assess when their meetings were off-track and reprioritize accordingly. Passive AI intervention helped participants maintain focus through non-intrusive feedback, while active AI intervention, though effective at triggering immediate reflection and action, risked disrupting the conversation flow. We identify three key design dimensions for AI-assisted reflection systems, and provide insights into design trade-offs, emphasizing the need to adapt intervention intensity and timing, balance democratic input with efficiency, and offer user control to foster intentional, goal-oriented behavior during meetings and beyond. KEYWORDS: videoconferencing, meeting, goal, intentionality, generative AI, probe, active, passive, intervention, interruption",
 "fullTextSources": [
  {
   "kind": "freeAccess",
   "url": "https://dl.acm.org/doi/epdf/10.1145/3706598.3714052",
   "label": "DOI (Free Access)"
  },
  {
   "kind": "freeAccess",
   "url": "https://doi.org/10.1145/3706598.3714052",
   "label": "DOI (Free Access)"
  },
  {
   "kind": "freeAccess",
   "url": "https://arxiv.org/pdf/2504.01082",
   "label": "Preprint (arXiv - Free Access)"
  }
 ],
 "fullTextAvailable": true,
 "takeaway": "During meetings, AI-assisted goal reflection can support meeting intentionality (knowing why you meet), because people felt explicit goals help them spot drift. Passive goal displays were easily overlooked, though, and direct questions risked interrupting the meeting.",
 "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": "Meetings often run on purposes nobody has stated",
    "role": "core evidence",
    "url": "https://seanrintel.com/better-meetings.html#m1"
   },
   {
    "claim": "AI that asks what a meeting is for gets people thinking it through themselves",
    "role": "core evidence",
    "url": "https://seanrintel.com/better-meetings.html#m2"
   },
   {
    "claim": "Help with meeting goals should start where people are, and go deeper only for meetings that need it",
    "role": "core evidence",
    "url": "https://seanrintel.com/better-meetings.html#m3"
   },
   {
    "claim": "A meeting's purpose is everyone's job, but asking what it is can feel risky, especially for junior staff",
    "role": "core evidence",
    "url": "https://seanrintel.com/better-meetings.html#m4"
   },
   {
    "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": "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": "System design: AI-mediated shared workspaces",
    "title": "Stund: Activity-Enriched Collaborative Workspaces Mediated by Artificial Intelligence",
    "page": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.html",
    "researchBrief": "https://seanrintel.com/publications/stund-activity-enriched-collaborative-workspaces-mediated-by-artificial-intelligence.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": "Meeting research and tools have focused on procedure, such as agendas, or on surface-level real-time feedback, and have mostly been tested in simulated meetings.",
   "quote": "tools have been evaluated primarily in low ecological validity conditions-unfamiliar participants discuss pre-determined tasks in simulated meetings-failing to capture the complexities of real-world workplace meetings",
   "location": "§2.2, p. 3"
  },
  "contribution": {
   "summary": "A technology probe study using participants' own recorded meetings to compare passive and active AI-assisted goal reflection, yielding three design dimensions and implementation considerations.",
   "quote": "Design dimensions and implementation suggestions that optimize the role of AI in fostering intentional, goal-oriented behavior during meetings, with broader implications for AIdriven meeting support technologies.",
   "location": "§1, p. 2"
  },
  "whoCares": {
   "summary": "Designers and researchers building AI meeting support and videoconferencing tools, and the knowledge workers, organisers and managers who run and attend meetings."
  }
 },
 "researchQuestions": [
  "RQ1. How do individuals currently maintain intentionality in meetings, and what challenges do they face?",
  "RQ2. What are user perceptions of AI-assisted reflection during meetings?",
  "RQ3. How should AI be designed to support intentional and effective meetings?"
 ],
 "concepts": [
  {
   "term": "Meeting intentionality",
   "definition": "The aim that agenda-focused meeting tools fail to foster:",
   "quote": "they focus on procedure rather than fostering intentionality-knowing why a meeting is occurring and focusing activity on that purpose",
   "location": "§1, p. 2"
  },
  {
   "term": "Reflection-in-action",
   "definition": "Schön's distinction. Meetings demand the first kind:",
   "quote": "Schön [82] distinguishes between reflection-in-action, involving real-time adjustments, and reflection-on-action, which occurs post-event.",
   "location": "§2.3, p. 3"
  },
  {
   "term": "Engagement level and extent of AI interpretation",
   "definition": "The two probe design dimensions: how actively the AI engages users (passive ambient vs active intermittent), and how much it interprets on their behalf (presenting conclusions vs asking questions).",
   "quote": "This dimension pertains to howmuch the AI interprets and processes information on behalf of the user.",
   "location": "§3.2, p. 4"
  },
  {
   "term": "Subjective timing",
   "definition": "The authors' proposed lens, distinct from objective (clock) and relative timing:",
   "quote": "We propose subjective timing as a lens to determine when participants are in need of support and can accommodate interventions without disruption.",
   "location": "§7.2, p. 17"
  }
 ],
 "method": {
  "design": "Technology probe study with two working AI probes, one passive and one active (see Prototype). The authors adapted video-stimulated recall: each participant's own recorded meeting played through both probes while they imagined being in it, with semi-structured interviews throughout, and probe order was counterbalanced.",
  "prototype": "Two working prototypes built into a simulated meeting window that played back the participant's own meeting recording, sending each turn of the transcript to GPT-4 (Node.js back end, D3.js graphics). Ambient Visualization is a passive sidebar. As the meeting plays, it lists the topics discussed on the left and the goals the AI infers on the right, joined by coloured flows showing which topic serves which goal. Users can click a topic for detail but never have to respond. Interactive Questioning is an active pop-up. When no goal has been set early in the meeting, or the AI judges the discussion has drifted from its goal, it asks a question tailored to the meeting (for example, what success would look like). It offers three options: vote for group reflection, agree but skip it, or disagree. If most vote to reflect, the AI listens and summarises the discussion (vote and summary were simulated). Each participant tried both.",
  "prototypeFigure": {
   "n": 1,
   "crop": [
    0,
    0,
    0.61,
    0.355
   ],
   "panel": "Panel A of Figure 1, Technology Probe Design: the two probes, Ambient Visualization and Interactive Questioning, placed by how much the AI interprets and how much engagement it asks for.",
   "alt": "A chart placing Ambient Visualization high in AI interpretation and low in engagement, and Interactive Questioning lower in interpretation and higher in engagement, beside screenshots of each probe in a recorded meeting."
  },
  "setting": "Remote sessions over videoconferencing. Participants' own recorded workplace meetings, with the consent of all attendees, were pre-processed and played through the probes to simulate real-time AI support.",
  "sample": "Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).",
  "n": 15,
  "duration": "Sessions of approximately 60 minutes. 2-3 meeting segments of approximately 5 minutes each per meeting.",
  "analysis": "Thematic analysis of interviews (open coding by the primary author, refined with the team), plus coding of the meeting data for goal communication, monitoring and adjustment, mapped against the interviews."
 },
 "findings": [
  {
   "headline": "Agendas, but rarely goals.",
   "summary": "In the 12 real workplace meetings that participants shared, most had an agenda but few stated what the meeting should achieve. Junior staff and people not running the meeting often noticed drift but felt it was not their place to say so.",
   "quote": "I noticed that we were diverging from the topic, but since I wasn't leading the meeting, I didn't feel it was my place to bring it up.",
   "location": "§4.3, p. 8",
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s4-3-p-8",
   "cite": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052 (§4.3, p. 8)"
  },
  {
   "headline": "Clarifying goals came first.",
   "summary": "Watching their own meetings with either AI probe, most participants reflected first on what the meeting was for. They asked themselves what it should achieve, or checked the goals the AI picked out against their own.",
   "quote": "Normally you have like some goals in your mind, and then the AI summarized the goals from your discussion, then you can sort of like calibrate your thoughts on what actually the goals are",
   "location": "§5.2.1, p. 10",
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-2-1-p-10",
   "cite": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052 (§5.2.1, p. 10)"
  },
  {
   "headline": "A quiet display revealed drift.",
   "summary": "The passive display of topics and goals helped participants notice off-track discussion and time spent on unimportant topics, without interrupting anyone. But some found its continuous stream overloading, and others ignored it as background.",
   "quote": "I think one thing that I didn't notice was that we were spending a lot of time on determining the computation...which I don't think was actually super important here.",
   "location": "§5.1.3, p. 10",
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-1-3-p-10",
   "cite": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052 (§5.1.3, p. 10)"
  },
  {
   "headline": "Questions prompted action, at a cost.",
   "summary": "Compared with the passive display, pop-up questions made participants more likely to say they would act in the moment, for example by steering the conversation back or reprioritising. But some found them intrusive or felt pressure to answer.",
   "quote": "It actually creates interruptions in the meeting. I felt like I had to answer when the AI questioned something.",
   "location": "§5.3.2, p. 11",
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-3-2-p-11",
   "cite": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052 (§5.3.2, p. 11)"
  },
  {
   "headline": "Shared steering, but fear of exposure.",
   "summary": "Participants saw AI-prompted reflection as spreading the job of keeping a meeting on track across everyone, instead of leaving it to whoever dares to interrupt. Yet individual contributors feared being publicly flagged as off-topic.",
   "quote": "Instead of one person bearing the responsibility to interrupt, the system fosters a shared awareness among everyone knowing there are still three topics to cover.",
   "location": "§5.2.3, p. 11",
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-2-3-p-11",
   "cite": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052 (§5.2.3, p. 11)"
  },
  {
   "headline": "Not every meeting needs deep reflection.",
   "summary": "Much reflection research treats deeper reflection as better. In fast-paced meetings, participants did not always want it, which suggests support that escalates or de-escalates with how much help people need.",
   "quote": "lower levels of reflection (e.g., in the passive Viz probe), though not always motivating immediate action, were also shown to help maintain focus and alignment without overwhelming participants",
   "location": "§7.1, p. 16",
   "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s7-1-p-16",
   "cite": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052 (§7.1, p. 16)"
  }
 ],
 "questions": [
  {
   "question": "Why do meetings drift off track?",
   "answer": "Partly because their goals are rarely stated. Agendas list topics rather than outcomes, and goals evolve as discussion unfolds. People who are not running the meeting often notice drift but do not feel it is their place to say so.",
   "source": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052",
   "basedOn": [
    {
     "location": "§4.3, p. 8",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s4-3-p-8"
    }
   ]
  },
  {
   "question": "Can AI help a meeting stay on track?",
   "answer": "Mostly by making goals explicit, which supports meeting intentionality (knowing why a meeting is happening). Goals often stay in people's heads. When AI showed what a meeting seemed to be for, people checked it against their own view. They said clear goals would help them spot drift and reprioritise.",
   "source": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052",
   "basedOn": [
    {
     "location": "§5.2.1, p. 10",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-2-1-p-10"
    },
    {
     "location": "§5.1.3, p. 10",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-1-3-p-10"
    }
   ]
  },
  {
   "question": "Should a meeting AI interrupt with questions or quietly show information?",
   "answer": "Neither is right all the time. Ambient displays avoid interrupting but are easily ignored when help is most needed, and add load when it is not. Direct questions prompt action but disrupt the conversation if mistimed. The right strength depends on how much help people need at that moment.",
   "source": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052",
   "basedOn": [
    {
     "location": "§5.1.3, p. 10",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-1-3-p-10"
    },
    {
     "location": "§5.3.2, p. 11",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-3-2-p-11"
    },
    {
     "location": "§7.1, p. 16",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s7-1-p-16"
    }
   ]
  },
  {
   "question": "Would people want an AI to flag them for going off-topic in a meeting?",
   "answer": "Many would not, at least not publicly. Individual contributors feared being judged and called out in front of colleagues, and some preferred private nudges. Managers worried that leaving the decision to reflect to them alone could silence junior staff.",
   "source": "Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052",
   "basedOn": [
    {
     "location": "§5.2.3, p. 11",
     "url": "https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html#at-s5-2-3-p-11"
    }
   ]
  }
 ],
 "cites": [
  {
   "url": "https://seanrintel.com/publications/comparing-the-agency-of-hybrid-meeting-remote-users-in-2d-and-3d-interfaces-of-the-hybridge-system.html",
   "title": "Comparing the Agency of Hybrid Meeting Remote Users in 2D and 3D Interfaces of the Hybridge System",
   "location": "p. 21"
  },
  {
   "url": "https://seanrintel.com/publications/large-scale-analysis-of-multitasking-behavior-during-remote-meetings.html",
   "title": "Large Scale Analysis of Multitasking Behavior During Remote Meetings",
   "location": "p. 19"
  },
  {
   "url": "https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.html",
   "title": "Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies",
   "location": "p. 21"
  },
  {
   "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. 20"
  },
  {
   "url": "https://seanrintel.com/publications/the-metacognitive-demands-and-opportunities-of-generative-ai.html",
   "title": "The Metacognitive Demands and Opportunities of Generative AI",
   "location": "p. 21"
  },
  {
   "url": "https://seanrintel.com/publications/meetingcoach-an-intelligent-dashboard-for-supporting-effective-inclusive-meetings.html",
   "title": "MeetingCoach: An Intelligent Dashboard for Supporting Effective and Inclusive Meetings",
   "location": "p. 21"
  }
 ],
 "quantitative": [
  {
   "measure": "Participants and meetings",
   "value": "n = 12 meetings, n = 15 participants",
   "location": "§3.5, p. 7"
  },
  {
   "measure": "Meetings with explicitly articulated goals",
   "value": "4 of 12 meetings",
   "location": "§4.1, p. 8"
  },
  {
   "measure": "Meetings found to be off-target in meeting data analysis",
   "value": "3 out of 12 meetings",
   "location": "§4.2, p. 8"
  },
  {
   "measure": "Participants for whom clarifying goals was the primary value",
   "value": "11/15",
   "location": "§5.1, p. 9"
  },
  {
   "measure": "Participants who saw AI reflection as fostering shared responsibility",
   "value": "9/15",
   "location": "§5.2, p. 11"
  },
  {
   "measure": "With active reflection, began by asking what the meeting was trying to achieve",
   "value": "13/15",
   "location": "§5.1.1, p. 9"
  },
  {
   "measure": "With the passive display, first interpreted the AI-generated goals rather than forming their own",
   "value": "10/15",
   "location": "§5.1.1, p. 9"
  },
  {
   "measure": "Initially took the AI-generated goals as accurate, then found discrepancies on further questioning",
   "value": "6 participants",
   "location": "§5.3.3, p. 11"
  },
  {
   "measure": "Meetings that referred back to their goals during the meeting (code count; meeting count)",
   "value": "3 codes; 1 meeting",
   "location": "Appendix A, p. 22"
  }
 ],
 "implications": [
  {
   "summary": "Design for what to reflect on (descriptive, contextual, analytical, actionable), when to reflect (objective, subjective, relative timing), and who should reflect (roles, visibility, collectiveness)."
  },
  {
   "summary": "Adapt intervention intensity to need, from ambient through lightweight to strong.",
   "quote": "AI systems should dynamically adjust intervention intensity between different intervention levels, from ambient through light-weight to strong intervention",
   "location": "§7.2, p. 17"
  },
  {
   "summary": "Balance democratic input with efficiency, for example letting an organiser make the call on whether the team reflects.",
   "quote": "the key is to find a balanced mechanism that encourages democratic input while allowing an accountable member, such as the facilitator or organizer, to make the call",
   "location": "§7.2, p. 18"
  },
  {
   "summary": "Give users control over goals and AI corrections, and explain AI nudges."
  },
  {
   "summary": "Treat generative AI as a tool for thought rather than automation.",
   "quote": "Rather than using GenAI as a tool to automate away the mundane procedures of meetings, we believe in developing GenAI as a tool for thought to make meetings more effective.",
   "location": "§8, p. 19"
  }
 ],
 "limitations": [
  {
   "summary": "Participants came from one global technology company, and the sample was not gender-balanced and had few managers.",
   "quote": "Our participants were recruited from one global technology company.",
   "location": "§7.4, pp. 18–19"
  },
  {
   "summary": "Probes ran on recordings, not live meetings, so feedback was retrospective.",
   "quote": "meant that participants provided retrospective feedback",
   "location": "§7.4, p. 19"
  },
  {
   "summary": "The quality of the AI-generated content was not formally evaluated.",
   "quote": "we did not formally evaluate the quality of the AI-generated content",
   "location": "§7.4, p. 19"
  }
 ],
 "figures": [
  {
   "src": "https://seanrintel.com/publications/figures/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings/fig-1.webp",
   "caption": "Figure 1: Overview of the study and findings. Based on insights from interviews with participants using two technology probes, we explore how knowledge workers maintain goal alignment in meetings (RQ1), uncover the perceptions, benefits, and concerns of AI-assisted meeting reflection (RQ2), and propose design dimensions and implementation considerations to optimize the role of AI in fostering intentional, goal-oriented behavior during meetings (RQ3).",
   "alt": "Overview in three panels: the two technology probes, Ambient Visualization and Interactive Questioning, placed by AI interpretation and engagement, the study design, and the findings for three research questions.",
   "location": "Figure 1, p. 1",
   "credit": "Figure 1 from Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052"
  },
  {
   "src": "https://seanrintel.com/publications/figures/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings/fig-2.webp",
   "caption": "Figure 2: Ambient Visualization: The visualization evolves over time as users observe it at different moments during the meeting (e.g., panels A-C), with the content becoming richer as the discussion progresses",
   "alt": "Three snapshots of the Ambient Visualization at the start, during and end of a meeting: a topic timeline on the left, goals on the right, expandable topic details, and coloured flows linking each topic to a goal.",
   "location": "Fig. 2, p. 5",
   "credit": "Figure 2 from Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052"
  },
  {
   "src": "https://seanrintel.com/publications/figures/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings/fig-5.webp",
   "caption": "Figure 5: Design dimensions-what to reflect on, when to reflect, and who should reflect-and implementation considerations for accommodating users' needs for in-meeting reflection.",
   "alt": "Diagram: what to reflect on (descriptive, contextual, analytical, actionable), when (objective, subjective, relative timing) and who (roles, visibility, collectiveness), linked to four implementation considerations.",
   "location": "Fig. 5, p. 13",
   "credit": "Figure 5 from Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052"
  },
  {
   "src": "https://seanrintel.com/publications/figures/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings/fig-6.webp",
   "caption": "Figure 6: (A) 'Strong' intermittent interventions are much more direct and can provoke immediate action. However, they risk becoming disruptive if not timed properly. (B) 'Light' ambient interventions are more subtle. However, when subjective assistance needs are high, they may fail to capture attention. Conversely, when assistance needs are very low, even a light ambient intervention may unnecessarily add to users' cognitive load.",
   "alt": "Two curves of one user's assistance needs over a meeting. A: strong interventions disrupt when mistimed or delayed. B: a constant light ambient band is insufficient at peaks and excessive at troughs.",
   "location": "Fig. 6, p. 18",
   "credit": "Figure 6 from Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, and Sean Rintel. 2025. Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings. CHI 2025. https://doi.org/10.1145/3706598.3714052"
  }
 ],
 "pageNumbersReferTo": "https://arxiv.org/pdf/2504.01082",
 "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",
   "summary": "Technology probe study with 15 employees of a global technology company. Each watched parts of their own recorded workplace meeting through two AI probes, in a remote session of about 60 minutes.",
   "steps": [
    {
     "label": "12 real meetings",
     "detail": "The 15 employees shared 12 recorded workplace meetings, with the consent of all attendees."
    },
    {
     "label": "Replay with both probes",
     "detail": "Each participant watched 2 to 3 meeting segments of about 5 minutes through both probes, with the order of probes varied."
    },
    {
     "label": "Interviews throughout",
     "detail": "Participants imagined being in the meeting and were interviewed as it played."
    },
    {
     "label": "Analysis",
     "detail": "Interviews were analysed for themes, and the meetings were coded for how goals were communicated, monitored and adjusted."
    }
   ]
  },
  "tool": {
   "heading": "The two probes",
   "steps": [
    {
     "title": "Play back the meeting",
     "text": "As the participant's recorded meeting plays, each turn of its transcript is sent to GPT-4."
    },
    {
     "title": "Show topics and goals",
     "text": "The passive probe lists the topics discussed and the goals the AI infers, joined by coloured flows. No one has to respond.",
     "fields": [
      "topics discussed",
      "inferred goals"
     ],
     "part": true
    },
    {
     "title": "Watch for missing goals or drift",
     "text": "The active probe checks whether a goal was set early in the meeting, and whether talk has drifted from it.",
     "part": true
    },
    {
     "title": "Ask a tailored question",
     "text": "A pop-up asks a question that fits the meeting, such as what success would look like.",
     "fields": [
      "vote to reflect as a group",
      "agree but skip",
      "disagree"
     ],
     "part": true
    },
    {
     "title": "Summarise the reflection",
     "text": "If most vote to reflect, the AI listens and summarises the discussion."
    }
   ],
   "note": "Step 2 is the passive probe, Ambient Visualization. Steps 3 to 5 are the active probe, Interactive Questioning. The vote and summary were simulated, and each participant tried both probes."
  },
  "findings": {
   "legend": null,
   "stages": [
    {
     "title": "In the shared meetings",
     "sub": "how goals appeared in participants' own recorded meetings",
     "items": [
      {
       "dir": "none",
       "text": "Of 12 shared workplace meetings, 4 stated their goals explicitly.",
       "detail": "Most had an agenda. Participants who were junior or not leading described noticing drift but feeling it was not their place to raise it.",
       "evidence": [
        "quantitative[1]",
        "findings[0]"
       ]
      }
     ]
    },
    {
     "title": "Watching with the probes",
     "sub": "what participants reflected on with each probe",
     "items": [
      {
       "dir": "none",
       "text": "Of 15 participants, 11 said clarifying a meeting's goals was the main value.",
       "detail": "With the active probe, 13 of 15 began by asking what the meeting was trying to achieve.",
       "evidence": [
        "quantitative[3]",
        "quantitative[5]",
        "findings[1]"
       ]
      },
      {
       "dir": "none",
       "text": "Of 15 participants, 10 first read the passive probe's goals before forming their own.",
       "detail": "Six participants first took the AI's goals as accurate, then found discrepancies when questioned further.",
       "evidence": [
        "quantitative[6]",
        "quantitative[7]"
       ]
      },
      {
       "dir": "none",
       "text": "Participants said the passive display revealed drift without interrupting anyone.",
       "detail": "It showed off-track talk and time spent on unimportant topics. Some found its continuous stream overloading, and others ignored it as background.",
       "evidence": [
        "findings[2]"
       ]
      },
      {
       "dir": "none",
       "text": "Participants said pop-up questions made them likelier to act in the moment than the display did.",
       "detail": "Examples were steering the conversation back or reprioritising. Some participants found the questions intrusive or felt pressure to answer.",
       "evidence": [
        "findings[3]"
       ]
      }
     ]
    },
    {
     "title": "Who keeps a meeting on track",
     "sub": "views on shared responsibility, exposure and depth",
     "items": [
      {
       "dir": "none",
       "text": "Of 15 participants, 9 saw AI-prompted reflection as sharing the job of keeping on track.",
       "detail": "Otherwise the job falls to whoever dares to interrupt. Individual contributors feared being publicly flagged as off-topic.",
       "evidence": [
        "quantitative[4]",
        "findings[4]"
       ]
      },
      {
       "dir": "none",
       "text": "Participants did not always want deep reflection in fast-paced meetings.",
       "detail": "The paper suggests AI support that steps up or down with how much help people need at the time.",
       "evidence": [
        "findings[5]"
       ]
      }
     ]
    }
   ]
  },
  "keyTerm": [
   "meeting intentionality",
   "reflection"
  ],
  "takeaway": "AI that prompts reflection on goals during a meeting can support meeting intentionality by helping people notice drift and refocus. Support may need to vary, since quiet displays can be missed and questions can interrupt."
 }
}