Dynamite: Real-Time Debriefing Slide Authoring through AI-Enhanced Multimodal Interaction

TL;DR

Dynamite is an AI-powered system that helps instructors create and update debriefing slides in real-time during classroom discussions by linking discussion data to slides and providing relevant revision suggestions.

Contribution

The paper introduces Dynamite, a novel AI-assisted tool that enables real-time, semantic-based slide authoring and updating during live classroom debriefings, enhancing accuracy and efficiency.

Findings

Dynamite outperformed a text-based AI baseline in content accuracy.

Participants effectively used voice and sketch inputs for rapid organization.

The system improved the quality of real-time debriefing slide content.

Abstract

Facilitating class-wide debriefings after small-group discussions is a common strategy in ethics education. Instructor interviews revealed that effective debriefings should highlight frequently discussed themes and surface underrepresented viewpoints, making accurate representations of insight occurrence essential. Yet authoring presentations in real time is cognitively overwhelming due to the volume of data and tight time constraints. We present Dynamite, an AI-assisted system that enables semantic updates to instructor-authored slides during live classroom discussions. These updates are powered by semantic data binding, which links slide content to evolving discussion data, and semantic suggestions, which offer revision options aligned with pedagogical goals. In a within-subject in-lab study with 12 participants, Dynamite outperformed a text-based AI baseline in content accuracy and quality. Participants used voice and sketch input to quickly organize semantic blocks, then applied suggestions to accelerate refinement as data stabilized.