Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

TL;DR

The paper investigates how Generative AI can support intentionality in planning and running video meetings by introducing CoExplorer, an adaptive interface that generates meeting goals and phases from invitations, surfaces attendee needs via a focus tool, and dynamically arranges phase-specific window layouts. Through a technology probe with 26 participants, the authors identify concrete benefits in attendee alignment and reduced task load, while also exposing concerns about agency, trust, and potential disruption to meeting norms. Key contributions include the CoExplorer prototype, empirical insights into user perceptions and design implications for adaptive windowing and HOTL interactions, and a set of prompts to reproduce the system. Overall, the work highlights both the potential and challenges of GenAI-enabled meeting systems and provides practical guidance for balancing efficiency, agency, and sociality in future designs.

Abstract

Effective meetings are effortful, but traditional videoconferencing systems offer little support for reducing this effort across the meeting lifecycle. Generative AI (GenAI) has the potential to radically redefine meetings by augmenting intentional meeting behaviors. CoExplorer, our novel adaptive meeting prototype, preemptively generates likely phases that meetings would undergo, tools that allow capturing attendees' thoughts before the meeting, and for each phase, window layouts, and appropriate applications and files. Using CoExplorer as a technology probe in a guided walkthrough, we studied its potential in a sample of participants from a global technology company. Our findings suggest that GenAI has the potential to help meetings stay on track and reduce workload, although concerns were raised about users' agency, trust, and possible disruption to traditional meeting norms. We discuss these concerns and their design implications for the development of GenAI meeting technology.

The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings

TL;DR

The paper investigates how Generative AI can support intentionality in planning and running video meetings by introducing CoExplorer, an adaptive interface that generates meeting goals and phases from invitations, surfaces attendee needs via a focus tool, and dynamically arranges phase-specific window layouts. Through a technology probe with 26 participants, the authors identify concrete benefits in attendee alignment and reduced task load, while also exposing concerns about agency, trust, and potential disruption to meeting norms. Key contributions include the CoExplorer prototype, empirical insights into user perceptions and design implications for adaptive windowing and HOTL interactions, and a set of prompts to reproduce the system. Overall, the work highlights both the potential and challenges of GenAI-enabled meeting systems and provides practical guidance for balancing efficiency, agency, and sociality in future designs.

Abstract

Effective meetings are effortful, but traditional videoconferencing systems offer little support for reducing this effort across the meeting lifecycle. Generative AI (GenAI) has the potential to radically redefine meetings by augmenting intentional meeting behaviors. CoExplorer, our novel adaptive meeting prototype, preemptively generates likely phases that meetings would undergo, tools that allow capturing attendees' thoughts before the meeting, and for each phase, window layouts, and appropriate applications and files. Using CoExplorer as a technology probe in a guided walkthrough, we studied its potential in a sample of participants from a global technology company. Our findings suggest that GenAI has the potential to help meetings stay on track and reduce workload, although concerns were raised about users' agency, trust, and possible disruption to traditional meeting norms. We discuss these concerns and their design implications for the development of GenAI meeting technology.
Paper Structure (49 sections, 6 figures)

This paper contains 49 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Meetings and effectiveness
  4. Using AI to Improve the Effectiveness and Adaptability of Video Meetings
  5. Adaptive User Interfaces
  6. Research questions
  7. Designing CoExplorer
  8. Design Strategies for GenAI interventions
  9. How CoExplorer Facilitates Meetings
  10. Formulating the Initial Phases of the Meeting
  11. Dynamic Window Management
  12. User Study Methods
  13. Participants
  14. System
  15. Study Process
  16. ...and 34 more sections

Figures (6)

  • Figure 1: This framework shows the pre-, during, and post- meeting stages and identifies pain points (initiating focused discussion; resource management for each phase), and suggests points of intervention (meeting focus tool; adaptive phase definitions; layouts tailored to each phase).
  • Figure 2: Upon recognition of a phase transition, CoExplorer notifies users and modifies the display to accommodate the new phase.
  • Figure 3: (A) Sequence of phases and tool for determining meeting focus. (B) Participants in the meeting employ the focus tool to select preferred features. (C) CoExplorer uses the aggregated preferences to adjust the meeting's objective and flow.
  • Figure 4: An example human-in-the-loop design for verifying app selections
  • Figure 5: List of generated initially generated phases (left) and the refined phases (right). After refinement, the phases became more focused and realistic for the given timeframe.
  • ...and 1 more figures