# Better Meetings > A meeting's purpose is usually implicit, unevenly held and easily lost. Putting it into words helps when the timing and social risk are right, and AI helps most as a coach and carrier. This page brings together seven studies by Sean Rintel and colleagues, published from 2024 to 2026, on meeting intentionality. That is how people work out what a meeting is for, keep it on purpose and carry it forward, and how AI can help. The studies used interviews, prototypes people tried, recordings of real meetings and a preregistered field experiment, all at one global technology company. Each study has a research brief with its findings, quotes and figures, checked against the paper. Source page: https://seanrintel.com/better-meetings.html. Structured data: https://seanrintel.com/overviews/better-meetings.json. Updated 2026-10-27. Drafted with AI assistance (Claude, by Anthropic) from the verified research briefs, and edited and published by Sean Rintel. Every claim rests on the papers' verified research briefs, whose quotes and numbers were checked against the full texts. **Meeting intentionality.** Meeting intentionality is knowing why a meeting is occurring and focusing activity on that purpose. ## How to use and cite this - Start with thesis and model for the argument, then claims for what the papers show together. - Each claim has evidenceSummary and doesNotShow. State the limit whenever you state the claim. - evidenceProfile gives each paper's role: 'core' is a main source of evidence, 'supports' adds to it, 'complicates' qualifies it. - For quotes or numbers, use papers[].researchBrief, which gives verbatim quotes with page locations, or papers[].keyNumbers here. - Follow accurateUse when describing this work. Name every author when citing a paper. - 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. Each paper's seanRintelRole field follows this rule. - Cite as: Rintel, S. (2026). Better Meetings. seanrintel.com. Updated 2026-10-27. https://seanrintel.com/better-meetings.html. For findings, cite the papers themselves. ## Describing this work accurately - Say that a preregistered field experiment with 361 employees found no measurable gain in rated meeting effectiveness from adding a pre-meeting goal prompt. - Do not say that goal prompts are proven to make meetings more effective. - Say that people reported clearer, better-communicated goals over two weeks of rating their meetings, with or without the prompt, and that this is self-reported. - Describe the probe studies as qualitative studies with 15 to 26 employees each, about how people responded to prototypes, not as tests of effectiveness. - Say that all seven studies were done at one global technology company, so findings may not transfer to other sectors. - Credit each study's lead author. Sean Rintel is senior author on all seven. ## How a meeting's purpose gets lost, or kept Read left to right. A meeting's purpose starts implicit and has to be put into words, shared, supported and carried forward. Timing and dose run underneath every step. Each box links to the claim behind it. 1. **Implicit**: Purpose goes unstated, and topic lists stand in for it (claim c1) 2. **Articulated**: Putting it into words makes it real (claim c3) 3. **Shared**: Organisers and attendees hold it unevenly (claim c2) 4. **Supported**: AI coaches and assists, people decide (claim c5) 5. **Carried forward**: Goals flow from invitation to recap to the next meeting (claim c6) - Underneath every step, **Timing and dose**: Too late, too often or too loud, and support backfires ## What the seven studies show together ### c1. Meeting purpose is usually implicit, and its stand-ins hide it Across interviews, recorded meetings and a field experiment, people rarely said what a meeting was for. Topic lists and standing agendas stood in for goals, saying what would be discussed but not why. - Evidence: Interviews, recordings of real meetings and open-text survey answers, all at one global technology company. - Does not show: How common unstated purpose is outside one technology company, or in other kinds of organisation. - core: Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies (2024). Many people treated a topic list or a recurring meeting's standing agenda as its goal, which hides why the meeting exists. Design: Exploratory, formative qualitative interview study, with an exploratory probe asking participants to consider a 'meeting goals' field in calendar invitations.. Sample: A purposive sample of 21 employees across six work areas, selected for diversity of gender, age, location, work area, seniority, hybrid work status and managerial status.. Brief: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json - core: Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings (2025). Only 4 of 12 recorded team meetings stated what they should achieve, though most had an agenda. Design: Technology probe study with two working AI probes, one passive and one active (see Prototype). We 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.. Sample: Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).. Brief: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json - supports: What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection (2025). A recurring meeting rarely had specific goals for any one instance, so reflection on it felt too general. Design: Exploratory, qualitative participatory prompting study using the Meeting Purpose Assistant as a technology probe. It had three parts: an onboarding survey, a moderated session with the MPA, and a follow-up survey after the meetings. The onboarding survey asked about three upcoming meetings (a familiar one they organised, an unfamiliar one they organised, and one they attended and expected to be ineffective).. Sample: A purposive sample of 19 participants from six work areas, including prior research participants who had indicated interest in future studies and four volunteers from adjacent research groups. One excluded, leaving 18 (10 women, 8 men).. Brief: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json - supports: Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment (2026). Lack of time before meetings was the most common barrier to thinking about goals, for organisers and attendees alike. Design: Preregistered (AsPredicted #194719) two-week randomised field experiment. Treatment: pre-meeting goal-reflection surveys plus post-meeting effectiveness surveys. Control: post-meeting surveys only.. Sample: 361 employees (treatment = 163, control = 198) and 7196 meetings.. Brief: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json ### c2. Purpose is held unevenly, so intentionality is a social problem, not an individual one Who may ask why, who notices drift and who can change a meeting all differ by role. Organisers and attendees wait on each other, so support has to be reciprocal and safe, not aimed only at organisers. - Evidence: Interviews and technology probes, with open-text answers from a field experiment, at one company. - Does not show: Whether changing roles or norms would make people more willing to ask why or to flag drift. - core: Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies (2024). Invitees avoided asking organisers what a meeting was for, for fear of seeming impolite, critical or ignorant. Design: Exploratory, formative qualitative interview study, with an exploratory probe asking participants to consider a 'meeting goals' field in calendar invitations.. Sample: A purposive sample of 21 employees across six work areas, selected for diversity of gender, age, location, work area, seniority, hybrid work status and managerial status.. Brief: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json - core: Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings (2025). Junior staff and people not running the meeting noticed drift but felt it was not their place to say so, and feared being flagged publicly. Design: Technology probe study with two working AI probes, one passive and one active (see Prototype). We 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.. Sample: Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).. Brief: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json - core: Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment (2026). Attendees felt unable to change meetings they had not organised, and organisers assumed attendees would not read goals. Each waited on the other. Design: Preregistered (AsPredicted #194719) two-week randomised field experiment. Treatment: pre-meeting goal-reflection surveys plus post-meeting effectiveness surveys. Control: post-meeting surveys only.. Sample: 361 employees (treatment = 163, control = 198) and 7196 meetings.. Brief: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json - supports: What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection (2025). Attendees often felt they could not act on any solution in a meeting someone else organised. Design: Exploratory, qualitative participatory prompting study using the Meeting Purpose Assistant as a technology probe. It had three parts: an onboarding survey, a moderated session with the MPA, and a follow-up survey after the meetings. The onboarding survey asked about three upcoming meetings (a familiar one they organised, an unfamiliar one they organised, and one they attended and expected to be ineffective).. Sample: A purposive sample of 19 participants from six work areas, including prior research participants who had indicated interest in future studies and four volunteers from adjacent research groups. One excluded, leaving 18 (10 women, 8 men).. Brief: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json - supports: The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings (2024). People wanted AI changes to the plan to go through the organiser, and some worried dominant speakers could steer the meeting. Design: Technology probe study: a guided walkthrough of the CoExplorer prototype in a simulated meeting, with a semi-structured interview and think-aloud.. Sample: 26 employees of a large global technology company (18 males and 8 females) in roles including project manager, software engineer, hardware engineer, designer and researcher.. Brief: https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.json ### c3. Putting purpose into words is the active ingredient, and repetition seems to train it Whenever people stated or checked a meeting's purpose, they reported clearer goals and better preparation. The one field experiment found no gain in rated effectiveness, so the benefit rests on people's own accounts. - Evidence: Technology probes and a preregistered field experiment with 361 employees and 7,196 meetings, with self-reported outcomes. - Does not show: That articulating purpose makes meetings more effective. The field experiment found no gain in rated effectiveness, and there was no group without any survey. - core: What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection (2025). Putting implicit goals into words helped people focus, warm up and arrive with a plan, and some then shared summaries or agendas. Design: Exploratory, qualitative participatory prompting study using the Meeting Purpose Assistant as a technology probe. It had three parts: an onboarding survey, a moderated session with the MPA, and a follow-up survey after the meetings. The onboarding survey asked about three upcoming meetings (a familiar one they organised, an unfamiliar one they organised, and one they attended and expected to be ineffective).. Sample: A purposive sample of 19 participants from six work areas, including prior research participants who had indicated interest in future studies and four volunteers from adjacent research groups. One excluded, leaving 18 (10 women, 8 men).. Brief: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json - core: Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment (2026). Goals got clearer and better communicated over two weeks of rating meetings, as if repetition were micro-training. An extra pre-meeting prompt added no measurable gain in rated effectiveness. Design: Preregistered (AsPredicted #194719) two-week randomised field experiment. Treatment: pre-meeting goal-reflection surveys plus post-meeting effectiveness surveys. Control: post-meeting surveys only.. Sample: 361 employees (treatment = 163, control = 198) and 7196 meetings.. Brief: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json - supports: Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings (2025). Watching their own meetings with AI support, most people first asked themselves what the meeting was for. Design: Technology probe study with two working AI probes, one passive and one active (see Prototype). We 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.. Sample: Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).. Brief: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json - supports: Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies (2024). Supporting intentionality is about reflection, not forcing explicit goals onto every meeting. Design: Exploratory, formative qualitative interview study, with an exploratory probe asking participants to consider a 'meeting goals' field in calendar invitations.. Sample: A purposive sample of 21 employees across six work areas, selected for diversity of gender, age, location, work area, seniority, hybrid work status and managerial status.. Brief: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json ### c4. Timing and dose decide whether support helps or hurts Support helped when it came early, matched the stakes and stayed in the background until needed. Prompts that came too late, too often or too loudly were ignored or resented, and some meetings work better without fixed goals. - Evidence: The strongest convergence: interviews, three technology probes and a field experiment point the same way. - Does not show: The best timing or frequency for prompts. Studies compared few options, and most evidence is self-reported. - core: Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment (2026). Prompts five minutes before a meeting were often too late to act on, and prompting every meeting caused survey fatigue. Design: Preregistered (AsPredicted #194719) two-week randomised field experiment. Treatment: pre-meeting goal-reflection surveys plus post-meeting effectiveness surveys. Control: post-meeting surveys only.. Sample: 361 employees (treatment = 163, control = 198) and 7196 meetings.. Brief: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json - core: What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection (2025). People saw important, uncertain meetings as the best candidates for reflection, and reflecting on every familiar recurring meeting as excessive. Design: Exploratory, qualitative participatory prompting study using the Meeting Purpose Assistant as a technology probe. It had three parts: an onboarding survey, a moderated session with the MPA, and a follow-up survey after the meetings. The onboarding survey asked about three upcoming meetings (a familiar one they organised, an unfamiliar one they organised, and one they attended and expected to be ineffective).. Sample: A purposive sample of 19 participants from six work areas, including prior research participants who had indicated interest in future studies and four volunteers from adjacent research groups. One excluded, leaving 18 (10 women, 8 men).. Brief: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json - core: Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings (2025). A passive display of goals was easily overlooked, while pop-up questions prompted action but could intrude. Design: Technology probe study with two working AI probes, one passive and one active (see Prototype). We 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.. Sample: Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).. Brief: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json - supports: The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings (2024). People wanted the AI to ask before showing files or apps, yet wanted fewer prompts during the meeting. Design: Technology probe study: a guided walkthrough of the CoExplorer prototype in a simulated meeting, with a semi-structured interview and think-aloud.. Sample: 26 employees of a large global technology company (18 males and 8 females) in roles including project manager, software engineer, hardware engineer, designer and researcher.. Brief: https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.json - complicates: Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies (2024). Goals cut both ways. Goal-light meetings allowed discovery and connection, and stated goals could feel like pressure. Design: Exploratory, formative qualitative interview study, with an exploratory probe asking participants to consider a 'meeting goals' field in calendar invitations.. Sample: A purposive sample of 21 employees across six work areas, selected for diversity of gender, age, location, work area, seniority, hybrid work status and managerial status.. Brief: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json ### c5. AI helps most as a coach and an assistant, not as a decider People valued AI that asked good questions, drafted structure and surfaced drift, but distrusted AI that acted on its own. Keeping people in charge, and checking the AI's output, came up in every study that built a system. - Evidence: Technology probes and design prototypes. The quality of AI output was not formally evaluated. - Does not show: How well the AI performed. Its outputs were not formally evaluated, and most probes used simulations or recordings. - core: What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection (2025). An assistant that asked questions rather than giving answers made people think for themselves, though solution-minded people wanted recommendations. Design: Exploratory, qualitative participatory prompting study using the Meeting Purpose Assistant as a technology probe. It had three parts: an onboarding survey, a moderated session with the MPA, and a follow-up survey after the meetings. The onboarding survey asked about three upcoming meetings (a familiar one they organised, an unfamiliar one they organised, and one they attended and expected to be ineffective).. Sample: A purposive sample of 19 participants from six work areas, including prior research participants who had indicated interest in future studies and four volunteers from adjacent research groups. One excluded, leaving 18 (10 women, 8 men).. Brief: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json - core: The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings (2024). People were sceptical of AI-generated content before it made any mistake, and wanted the organiser to keep the final say. Design: Technology probe study: a guided walkthrough of the CoExplorer prototype in a simulated meeting, with a semi-structured interview and think-aloud.. Sample: 26 employees of a large global technology company (18 males and 8 females) in roles including project manager, software engineer, hardware engineer, designer and researcher.. Brief: https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.json - supports: CoExplorer: Generative AI Powered 2D and 3D Adaptive Interfaces to Support Intentionality in Video Meetings (2024). Generative AI could draft a meeting's aim and phases from a short invitation, but tended to propose changes when none were needed. Design: Design and implementation of two technology probes, shaped by three design approaches: collective feedback on objectives, clarifying needs and resources for each phase, and human-on-the-loop control.. Sample: No user study. The probes were demonstrated on the scenario.. Brief: https://seanrintel.com/publications/coexplorer-generative-ai-powered-2d-and-3d-adaptive-interfaces-to-support-intentionality-in-video-meetings.json - supports: Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings (2025). People wanted control over goals and over AI corrections, and explanations for AI nudges. Design: Technology probe study with two working AI probes, one passive and one active (see Prototype). We 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.. Sample: Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).. Brief: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json - supports: Designing Interfaces that Support Temporal Work Across Meetings with Generative AI (2025). In early, unevaluated trials, an AI model found many of the links between meetings that our own analysis had found. Design: Exploratory analysis of recorded recurring meetings, followed by framework development and a design and prototyping exercise using a purpose-built research tool (see Prototype).. Sample: Eight recorded meetings, each lasting 38 minutes to an hour, 6 hours and 45 minutes in total (Table 1 gives participants per meeting).. Brief: https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.json ### c6. Purpose has to travel, across the meeting lifecycle and from one meeting to the next A meeting's purpose is set when it is scheduled, tested during it and needed again afterwards and at the next meeting. Today's tools keep each moment separate, so goals should flow from invitation to facilitation to recap. - Evidence: Analysis of recorded meetings, interviews and design prototypes. The proposed designs have not yet been tested with users. - Does not show: That chained recaps and handoffs help teams. These designs have not yet been tested with users. - core: Designing Interfaces that Support Temporal Work Across Meetings with Generative AI (2025). People looked back and ahead throughout their weekly meetings, yet existing tools covered only a narrow slice of time. Design: Exploratory analysis of recorded recurring meetings, followed by framework development and a design and prototyping exercise using a purpose-built research tool (see Prototype).. Sample: Eight recorded meetings, each lasting 38 minutes to an hour, 6 hours and 45 minutes in total (Table 1 gives participants per meeting).. Brief: https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.json - core: Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies (2024). Tools scatter a meeting's context across scheduling, chat and meeting apps, so goals should surface from scheduling onward. Design: Exploratory, formative qualitative interview study, with an exploratory probe asking participants to consider a 'meeting goals' field in calendar invitations.. Sample: A purposive sample of 21 employees across six work areas, selected for diversity of gender, age, location, work area, seniority, hybrid work status and managerial status.. Brief: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json - supports: Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment (2026). People said stated goals tied their work together, and saw them as useful input for AI meeting tools. Design: Preregistered (AsPredicted #194719) two-week randomised field experiment. Treatment: pre-meeting goal-reflection surveys plus post-meeting effectiveness surveys. Control: post-meeting surveys only.. Sample: 361 employees (treatment = 163, control = 198) and 7196 meetings.. Brief: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json - supports: CoExplorer: Generative AI Powered 2D and 3D Adaptive Interfaces to Support Intentionality in Video Meetings (2024). AI could carry the plan into the meeting, bringing up each phase's files and apps as the talk moves on. Design: Design and implementation of two technology probes, shaped by three design approaches: collective feedback on objectives, clarifying needs and resources for each phase, and human-on-the-loop control.. Sample: No user study. The probes were demonstrated on the scenario.. Brief: https://seanrintel.com/publications/coexplorer-generative-ai-powered-2d-and-3d-adaptive-interfaces-to-support-intentionality-in-video-meetings.json - supports: The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings (2024). Design should span the whole meeting lifecycle and the wider project, for example sharing the focus tool well in advance. Design: Technology probe study: a guided walkthrough of the CoExplorer prototype in a simulated meeting, with a semi-structured interview and think-aloud.. Sample: 26 employees of a large global technology company (18 males and 8 females) in roles including project manager, software engineer, hardware engineer, designer and researcher.. Brief: https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.json ## For research: What we still need to study **Does the field experiment show that goal prompts do not work?** Not quite. Adding a pre-meeting prompt to post-meeting ratings brought no measurable gain in rated effectiveness, p = 0.36. But people reported clearer goals over two weeks, with or without the prompt, and most described new awareness or habits. With no group that went without surveys, we cannot tell whether rating meetings, the study itself or time explains this. A no-survey control is the next design. **When and how often should goal reflection be prompted?** We do not know yet. Five minutes before a meeting was often too late, and prompting every meeting caused survey fatigue. People saw important, uncertain meetings as the best candidates. During meetings, a passive display was easily ignored and pop-up questions could intrude. Studies should compare timing, frequency and intensity, including support that steps up only when a meeting drifts. **How can meeting intentionality be measured beyond self-report?** Our outcomes were mostly self-reported, and the field experiment suggests measuring meetings may itself prompt reflection. Future work needs behavioural measures, such as goals appearing in invitations or talk returning to the goal. Our coding of recorded meetings for goal communication, monitoring and adjustment offers one starting point. AI-generated content also needs formal evaluation. ## For industry: Research-informed practice and what to design next **Should a meeting tool ask organisers for a goal when scheduling?** Our studies point that way, with care. Interviewees liked the idea of a goals field in invitations but feared pressure or neglect. In the field experiment, prompts five minutes before were often too late, yet over two-thirds of people were interested in a future goal prompt. Ask at scheduling, target important or uncertain meetings, and let organisers skip it. **How much should an AI meeting assistant act on its own?** Mostly with people's approval. In our CoExplorer study, 21 of 26 people said the system should consult people before showing files or apps, yet they also wanted fewer prompts during meetings. Move approval checks to quieter moments, such as before the meeting. Let organisers keep the final say, and explain why the AI suggests a change. **What should AI do with meeting goals once they are stated?** Carry them forward. Stated goals can feed invitations, pre-reads, AI facilitation and recaps. Teams in our recorded meetings repeatedly linked one meeting to others by looking back and ahead. Our design work proposes instant recaps when a meeting ends and handoffs to the next one. These designs have not been tested with users, so pilot them before any rollout. ## For government: How this research relates to policy **What can this research inform about public-service meeting practice?** Mainly low-cost habits. Meetings in our studies often lacked stated goals, and agendas said what would be discussed but not why. People said being asked what success would look like helped them focus. The research cannot say what this does for productivity, and none of it was done in the public sector. We would welcome a conversation about testing it there. **How do AI meeting tools bear on consulting workers about AI?** Our studies did not examine consultation but show what it could cover. Staff feared being publicly flagged as off-topic by AI, and most wanted to be asked before AI showed files or apps. Our work also warns that reflections exposed to employers could deepen power gaps. The Australian Senate Select Committee on Adopting Artificial Intelligence recommended that employers consult employees on AI use at work. (Relates to: Australian Senate Select Committee on Adopting Artificial Intelligence, final report, November 2024.) **Does this research support requiring goal prompts across a public service?** No. Adding a pre-meeting goal prompt brought no measurable gain in rated effectiveness, and prompting every meeting caused fatigue. Over two-thirds of people were interested in a future goal prompt, which points to optional, targeted use. Whether to require stated goals is a choice for agencies and staff. Any trial should include a group with no survey at all. ## What we don't know yet - Does rating meetings afterwards, on its own, lead to clearer goals? (partly studied) Goals got clearer with or without the extra prompt, but nobody went without surveys. - Do goal prompts change what happens in live meetings? (not yet studied) Probes ran on recordings or simulations, and field outcomes were self-reported. - Does prompting only important or uncertain meetings work better than prompting all? (not yet studied) Prompts five minutes before were often too late, and prompting every meeting caused survey fatigue. - Do AI meeting plans, recaps and handoffs help real teams over time? (not yet studied) These designs were tested only in a simulation or not with users. - How can organisers and attendees share the work of reflecting on goals? (partly studied) Attendees felt unable to change meetings, and organisers assumed attendees would not read goals. - Do these findings hold outside one global technology company? (not yet studied) Everyone in our studies came from one global technology company. ## The seven studies, and what each contributes ### Mental Models of Meeting Goals: Supporting Intentionality in Meeting Technologies Ava Elizabeth Scott, Lev Tankelevitch, Sean Rintel. CHI 2024, 2024. DOI: https://doi.org/10.1145/3613904.3642670 Sean Rintel: senior author. Page: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.html. Research brief: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.json. PDF: https://seanrintel.com/publications/mental-models-of-meeting-goals-supporting-intentionality-in-meeting-technologies.pdf. Takeaway: People hold two mental models of meeting goals (meetings as means to an end, or as ends in themselves for connection and discovery). Misaligned goals can create tension between organizers and attendees, so meeting intentionality (knowing why you meet) needs tools that surface goals across the meeting lifecycle, from scheduling. Role here: Interviews showing how people think about meeting goals and why they go unstated. Feeds claims: c1 (core), c2 (core), c3 (supports), c4 (complicates), c6 (core). Method: Design: Exploratory, formative qualitative interview study, with an exploratory probe asking participants to consider a 'meeting goals' field in calendar invitations.. Sample: A purposive sample of 21 employees across six work areas, selected for diversity of gender, age, location, work area, seniority, hybrid work status and managerial status.. Setting: A global technology company. Interviews held as recorded Microsoft Teams video meetings.. - Limitation: All participants came from one global technology firm. - Limitation: Seventy percent of participants were from the US, and meeting practices differ across cultures, so findings may not fully generalize. - Limitation: Participants self-selected from people who had taken part in earlier meeting research and may be more thoughtful about meetings than most. ### What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection Ava Elizabeth Scott, Lev Tankelevitch, Payod Panda, Rishi Vanukuru, Xinyue Chen, Sean Rintel. CHIWORK 2025, 2025. DOI: https://doi.org/10.1145/3729176.3729204 Sean Rintel: senior author. Page: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.html. Research brief: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.json. PDF: https://seanrintel.com/publications/what-does-success-look-like-catalyzing-meeting-intentionality-with-ai-assisted-prospective-reflection.pdf. Takeaway: Before meetings, AI can build meeting intentionality by coaching prospective reflection (asking why a meeting is needed, what success looks like and what could derail it). People clarified goals, prepared, shared agendas and rethought recurring meetings. It suits important, uncertain meetings, building a skill instant AI answers would bypass. Role here: Probe study of an AI assistant asking what success looks like before meetings. Feeds claims: c1 (supports), c2 (supports), c3 (core), c4 (core), c5 (core). Method: Design: Exploratory, qualitative participatory prompting study using the Meeting Purpose Assistant as a technology probe. It had three parts: an onboarding survey, a moderated session with the MPA, and a follow-up survey after the meetings. The onboarding survey asked about three upcoming meetings (a familiar one they organised, an unfamiliar one they organised, and one they attended and expected to be ineffective).. Sample: A purposive sample of 19 participants from six work areas, including prior research participants who had indicated interest in future studies and four volunteers from adjacent research groups. One excluded, leaving 18 (10 women, 8 men).. Setting: A global technology company. Sessions held as video meetings with the participant sharing their screen.. - Limitation: Self-selected sample from one company. Participants may have been more thoughtful about meetings than others. - Limitation: Participatory prompting mixes human and AI-driven reflection, and the researcher's presence may have created demand characteristics. - Limitation: Some interactions were cut short, and each participant was seen for only about an hour rather than longitudinally. ### The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings Gun Woo (Warren) Park, Payod Panda, Lev Tankelevitch, Sean Rintel. DIS 2024, 2024. DOI: https://doi.org/10.1145/3643834.3661507 Sean Rintel: senior author. 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. Research brief: https://seanrintel.com/publications/the-coexplorer-technology-probe-a-generative-ai-powered-adaptive-interface-to-support-intentionality-in-planning-and-running-video-meetings.json. Takeaway: Generative AI can ease meeting intentionality (knowing why you meet). From the invitation, AI can generate a goal, meeting phases and a poll of where attendees agree, focusing discussion on differences. Then an adaptive interface can open apps and files as talk changes phase. Role here: Technology probe where AI drafted meeting plans and polled attendees before a simulated meeting. Feeds claims: c2 (supports), c4 (supports), c5 (core), c6 (supports). Method: Design: Technology probe study: a guided walkthrough of the CoExplorer prototype in a simulated meeting, with a semi-structured interview and think-aloud.. Sample: 26 employees of a large global technology company (18 males and 8 females) in roles including project manager, software engineer, hardware engineer, designer and researcher.. Setting: One-hour one-to-one sessions over Microsoft Teams, on participants' own laptops. A fictional scenario in which a cross-functional product team decides features for a new version of headphones, using fictitious documents. The other attendees were simulated, with contrasting opinions assigned to them.. - Participants: 26 employees; 18 males and 8 females (§4.1, p. 8) - Found capturing attendees' preferences in advance helpful: 24 of 26 (§5.2, p. 9) - Trusted the curated contents (often conditionally): 17 of 26 (§5.4, p. 10) - Expected a way to recall windows the system closed: 20 of 26 (§5.4, p. 10) - Said the system should consult humans before showing files or apps; before phase changes: 21 of 26; 16 of 26 (§5.4.1, p. 10) - Limitation: Participants came from a single company and the pool was not gender-balanced. - Limitation: Confidentiality meant fictitious documents rather than participants' real work files. - Limitation: The study did not validate generated phases and tools or compare GenAI with people creating interfaces or running meetings. ### CoExplorer: Generative AI Powered 2D and 3D Adaptive Interfaces to Support Intentionality in Video Meetings Gun Woo (Warren) Park, Payod Panda, Lev Tankelevitch, Sean Rintel. CHI EA 2024, 2024. DOI: https://doi.org/10.1145/3613905.3650797 Sean Rintel: senior author. Page: https://seanrintel.com/publications/coexplorer-generative-ai-powered-2d-and-3d-adaptive-interfaces-to-support-intentionality-in-video-meetings.html. Research brief: https://seanrintel.com/publications/coexplorer-generative-ai-powered-2d-and-3d-adaptive-interfaces-to-support-intentionality-in-video-meetings.json. PDF: https://seanrintel.com/publications/coexplorer-generative-ai-powered-2d-and-3d-adaptive-interfaces-to-support-intentionality-in-video-meetings.pdf. Takeaway: Before and during meetings, generative AI adaptive interfaces could support meeting intentionality by reducing effort. They could infer goals and implicit phases from the invitation, focus discussion where attendees disagree, and bring up apps and files, in 2D or VR, as talk changes phase. Role here: Design paper describing the CoExplorer prototypes on screen and in virtual reality. Feeds claims: c5 (supports), c6 (supports). Method: Design: Design and implementation of two technology probes, shaped by three design approaches: collective feedback on objectives, clarifying needs and resources for each phase, and human-on-the-loop control.. Sample: No user study. The probes were demonstrated on the scenario.. Setting: A fictional decision-making meeting of a cross-functional product team choosing features for the "Strata Headphones 3".. - Limitation: We did not formally evaluate the system's capabilities or their effect on meeting effectiveness. - Limitation: Due to time limitations we did not complete the full meeting scenario in CoExplorer2D. - Limitation: Generative AI tends to over-respond, producing changes where none are needed. ### Are We On Track? AI-Assisted Active and Passive Goal Reflection During Meetings Xinyue Chen, Lev Tankelevitch, Rishi Vanukuru, Ava Elizabeth Scott, Payod Panda, Sean Rintel. CHI 2025, 2025. DOI: https://doi.org/10.1145/3706598.3714052 Sean Rintel: senior author. Page: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.html. Research brief: https://seanrintel.com/publications/are-we-on-track-ai-assisted-active-and-passive-goal-reflection-during-meetings.json. 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. Role here: Probe study comparing passive and active AI goal reflection during replayed meetings. Feeds claims: c1 (core), c2 (core), c3 (supports), c4 (core), c5 (supports). Method: Design: Technology probe study with two working AI probes, one passive and one active (see Prototype). We 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.. Sample: Purposive sample of 15 employees of a global technology company, contributing 12 meetings (several participants attended the same meetings).. 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.. - Participants and meetings: n = 12 meetings, n = 15 participants (§3.5, p. 7) - Meetings with explicitly articulated goals: 4 of 12 meetings (§4.1, p. 8) - Meetings found to be off-target in meeting data analysis: 3 out of 12 meetings (§4.2, p. 8) - Participants for whom clarifying goals was the primary value: 11/15 (§5.1, p. 9) - Participants who saw AI reflection as fostering shared responsibility: 9/15 (§5.2, p. 11) - Limitation: Participants came from one global technology company, and the sample was not gender-balanced and had few managers. - Limitation: Probes ran on recordings, not live meetings, so feedback was retrospective. - Limitation: The quality of the AI-generated content was not formally evaluated. ### Designing Interfaces that Support Temporal Work Across Meetings with Generative AI Rishi Vanukuru, Payod Panda, Xinyue Chen, Ava Elizabeth Scott, Lev Tankelevitch, Sean Rintel. DIS2025, 2025. DOI: https://doi.org/10.1145/3715336.3735833 Sean Rintel: senior author. Page: https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.html. Research brief: https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.json. PDF: https://seanrintel.com/publications/designing-interfaces-that-support-temporal-work-across-meetings-with-generative-ai.pdf. Takeaway: Meeting intentionality spans a series of meetings. People's temporal work (looking back and ahead) links them, yet today's tools cover only a narrow slice of time. So generative AI should carry goals and context between meetings, for example through instant recaps, handoffs to the next meeting and project browsers. Role here: Analysis of recorded meetings and designs for carrying goals across meetings. Feeds claims: c5 (supports), c6 (core). Method: Design: Exploratory analysis of recorded recurring meetings, followed by framework development and a design and prototyping exercise using a purpose-built research tool (see Prototype).. Sample: Eight recorded meetings, each lasting 38 minutes to an hour, 6 hours and 45 minutes in total (Table 1 gives participants per meeting).. Setting: Two research teams (A and B) in a large technology company, in consecutive weekly hybrid meetings over the same four weeks following an internal conference.. - Limitation: Engineering and design research meetings in one company, in a similar timeframe and after a major internal event. - Limitation: Only four weeks of meetings. - Limitation: Individual identities and contributions within meetings were not analysed, and the concepts focus on individual rather than collaborative use. ### Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field Experiment Lev Tankelevitch, Ava Elizabeth Scott, Nagaravind Challakere, Payod Panda, Sean Rintel. CHI 2026, 2026. DOI: https://doi.org/10.1145/3772318.3791199 Sean Rintel: senior author. Page: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.html. Research brief: https://seanrintel.com/publications/nudging-attention-to-workplace-meeting-goals-a-large-scale-preregistered-field-experiment.json. Takeaway: Brief goal-reflection surveys can build meeting intentionality whether they come before and after meetings or only after. Either way, people reported clearer, better-communicated goals, and most felt their meetings improved, perhaps because repeated reflection acted as micro-training. Adding pre-meeting prompts brought no further measurable gain in rated effectiveness. Role here: Preregistered field experiment testing a pre-meeting goal prompt at scale. Feeds claims: c1 (supports), c2 (core), c3 (core), c4 (core), c6 (supports). Method: Design: Preregistered (AsPredicted #194719) two-week randomised field experiment. Treatment: pre-meeting goal-reflection surveys plus post-meeting effectiveness surveys. Control: post-meeting surveys only.. Sample: 361 employees (treatment = 163, control = 198) and 7196 meetings.. Setting: A global technology company, inside participants' everyday collaboration platform (Microsoft Teams).. - Sample: 361 participants (treatment = 163, control = 198); 7196 meetings (§4.2, p. 4) - Treatment effect on per-meeting effectiveness (intention to treat): p = 0.36 (not significant) (§5.2.1, p. 8) - Treatment effect for compliant meetings (CACE, exploratory): p = 0.6 (not significant) (§5.2.1, p. 8) - Said study participation increased meeting effectiveness: 57% treatment vs 52% control; p = 0.13 (not significant) (§5.2.2, p. 8) - Said study participation increased engagement: 43% treatment vs 34% control; p = 0.05 (not significant) (§5.2.2, p. 8) - Limitation: No truly passive control group, so the causal effect of the post-meeting surveys cannot be isolated. - Limitation: All outcomes are self-reported and subject to measurement reactivity and social desirability. - Limitation: Many surveys were completed late or not at all, especially in the treatment group, which reduces statistical power. ## Glossary - **Meeting intentionality**: Meeting intentionality is knowing why a meeting is occurring and focusing activity on that purpose. - **Meetings as a means to an end**: A mental model in which a meeting's goals are specific and knowable: - **Meetings as an end in themselves**: A mental model in which the act of meeting is itself the purpose, which can also mean simply blocking time: - **Meeting goals versus agendas**: Goals and agendas are related but distinct: an agenda is a plan for reaching a goal. - **Intentionality across the meeting lifecycle**: The purpose behind a meeting, which can be catalyzed or obstructed at different moments from setting it up to holding it. - **Prospective reflection**: The kind of reflection studied, covering a meeting's purpose, success and challenges: - **Reflection**: Intentionality requires reflection, broadly defined in prior work as: - **Meeting Purpose Assistant (MPA)**: Our technology probe: a chat interface powered by GPT-4 Turbo that asks about a meeting's purpose, success and challenges, plus a Reflection Summary. - **Reflection Summary**: The MPA's structured record of the conversation, which participants could reuse in meeting invitations or chats. - **Participatory prompting**: The study method: - **Meeting phases**: Locally organised, activity-oriented stretches of a meeting that may match, split or span agenda items and need different resources. - **Human-on-the-loop (HOTL)**: The system acts on its own and humans can only abort its decisions, unlike human-in-the-loop, where actions need prior approval. - **Meeting Focus Tool**: A generated pre-meeting tool in which attendees state preferences, used to refine goals and phases towards points of disagreement. - **Technology probe**: A working prototype used to elicit users' reactions to design concepts rather than to evaluate performance. - **Implicit meeting phases**: The stages a meeting actually moves through, which may match, span or subdivide agenda items, and which each need different files and apps. - **Spatial context**: The paper's definition, which CoExplorerVR uses when placing windows around a virtual room: - **Reflection-in-action**: Schön's distinction. Meetings demand the first kind: - **Engagement level and extent of AI interpretation**: 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). - **Subjective timing**: Our proposed lens, distinct from objective (clock) and relative timing: - **Temporal work**: Looking back (retrospection) and ahead (prospection) to make sense of and act in the present, individually and as a team. - **Objective and subjective time**: Shipp and Jansen's distinction, which gives our framework its two axes: - **Prospection and retrospection forms**: Four forms of looking ahead (intention, planning, prediction, simulation) and two of looking back (recollecting, reflecting), taken from prior taxonomies and used to tag the meetings. - **Chain of intentionality**: Linked interfaces that carry reflection and intentions from one meeting to the next and across projects. - **Nudge plus**: A nudge that adds a moment of reflection rather than relying only on fast, habitual responses. - **Workplace reflection**: Reflection shaped by organisational context. - **Measurement reactivity**: When measuring a behaviour changes it. Here, the post-meeting effectiveness surveys may have acted as a reflection prompt for the control group too. Related overview: [Better Thinking With AI](https://seanrintel.com/better-thinking-with-ai.html). The same work of stating and checking purpose, for people using generative AI on their own.