Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

TL;DR

The paper addresses persistent inefficiencies in workplace meetings by proposing AI-assisted prospective reflection to surface why a meeting is needed and what could happen. It introduces the Meeting Purpose Assistant (MPA), a Generative AI technology probe, deployed with 18 employees to coach articulation of meeting purpose, challenges, and success criteria. Through a participatory prompting method, the study demonstrates how AI-facilitated reflection clarifies goals, shifts perspectives, improves preparation, and leads to actionable changes in meeting plans, while identifying social, temporal, and technical barriers. The work contributes design guidelines for AI-assisted reflection in meetings and broader workflows, highlighting how contextualized, adaptive prompting and reflection summaries can be embedded into organizational routines.

Abstract

Despite decades of HCI and Meeting Science research, complaints about ineffective meetings are still pervasive. We argue that meeting technologies lack support for prospective reflection, that is, thinking about why a meeting is needed and what might happen. To explore this, we designed a Meeting Purpose Assistant (MPA) technology probe to coach users to articulate their meeting's purpose and challenges, and act accordingly. The MPA used Generative AI to support personalized and actionable prospective reflection across the diversity of meeting contexts. Using a participatory prompting methodology, 18 employees of a global technology company reflected with the MPA on upcoming meetings. Observed impacts were: clarifying meeting purposes, challenges, and success conditions; changing perspectives and flexibility; improving preparation and communication; and proposing changed plans. We also identify perceived social, temporal, and technological barriers to using the MPA. We present system and workflow design considerations for developing AI-assisted reflection support for meetings.

What Does Success Look Like? Catalyzing Meeting Intentionality with AI-Assisted Prospective Reflection

TL;DR

The paper addresses persistent inefficiencies in workplace meetings by proposing AI-assisted prospective reflection to surface why a meeting is needed and what could happen. It introduces the Meeting Purpose Assistant (MPA), a Generative AI technology probe, deployed with 18 employees to coach articulation of meeting purpose, challenges, and success criteria. Through a participatory prompting method, the study demonstrates how AI-facilitated reflection clarifies goals, shifts perspectives, improves preparation, and leads to actionable changes in meeting plans, while identifying social, temporal, and technical barriers. The work contributes design guidelines for AI-assisted reflection in meetings and broader workflows, highlighting how contextualized, adaptive prompting and reflection summaries can be embedded into organizational routines.

Abstract

Despite decades of HCI and Meeting Science research, complaints about ineffective meetings are still pervasive. We argue that meeting technologies lack support for prospective reflection, that is, thinking about why a meeting is needed and what might happen. To explore this, we designed a Meeting Purpose Assistant (MPA) technology probe to coach users to articulate their meeting's purpose and challenges, and act accordingly. The MPA used Generative AI to support personalized and actionable prospective reflection across the diversity of meeting contexts. Using a participatory prompting methodology, 18 employees of a global technology company reflected with the MPA on upcoming meetings. Observed impacts were: clarifying meeting purposes, challenges, and success conditions; changing perspectives and flexibility; improving preparation and communication; and proposing changed plans. We also identify perceived social, temporal, and technological barriers to using the MPA. We present system and workflow design considerations for developing AI-assisted reflection support for meetings.

Paper Structure

This paper contains 81 sections, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Prior Work
  3. Understanding and Designing for Meetings
  4. Reflection to Catalyze Intentionality and Change Routines
  5. Designing for Reflection and Intentionality
  6. Generative AI as a Flexible Technology for Reflection
  7. Research Questions
  8. Methods
  9. Technology Probe: The Meeting Purpose Assistant
  10. Technical details
  11. Participants
  12. Protocol
  13. Onboarding Survey and Sample Meeting Details
  14. Participatory Prompting Session
  15. Follow-up Survey
  16. ...and 66 more sections

Figures (2)

  • Figure 1: The Meeting Purpose Assistant technology probe consisted of a chat interface (left), powered by GPT-4 Turbo, that participants interacted with, and a Reflection Summary (right) of their conversation that participants could obtain by clicking the 'summarize' button. The MPA had basic context about the meeting from information uploaded in advance by the researcher.
  • Figure 2: System diagram for the Meeting Purpose Assistant. The client machine (left) interacted with the assistants on OpenAI server (right) through our node.js server (center) behind an enterprise firewall. The figure shows how the components that make up the interface in Figure \ref{['fig:mpa']} (greyed out here for clarity) interact with the three Assistants. All data was stored locally on our server, accessible only to the research team.