InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings
2026-08-31 • Human-Computer Interaction
Human-Computer InteractionInformation Retrieval
AI summaryⓘ
The authors created InsightToast, a tool that listens to what people say during meetings and quickly finds helpful information to share without interrupting the flow of conversation. It uses advanced language models to gather facts and show them briefly as easy-to-understand notes and charts on the side. They tested it with 16 people making policy decisions and found it helped keep discussions smooth while providing useful background information. This can make meetings more informed without distracting participants.
mixed-initiative systemslarge language models (LLM)retrieval-augmented generation (RAG)real-time discourse monitoringinformation retrievaluser interfaceknowledge basesdecision-makinglegislative documentsinteractive visualization
Authors
Mohammad Abolnejadian, Matthew Brehmer
Abstract
Missing institutional context during meetings can impede effective participation. Retrieving relevant information, often scattered across heterogeneous internal and external sources, requires costly task-switching that disrupts both individual focus and collective conversational flow, particularly detrimental during cognitively demanding tasks such as decision-making. We introduce InsightToast, a mixed-initiative application that monitors verbal discourse in real time, identifies topics and informational needs as they emerge, and proactively retrieves relevant information through a multi-agent large language model (LLM)-based pipeline integrating retrieval-augmented generation (RAG) to produce source-grounded insights as succinct text and glanceable interactive charts, delivered through a peripheral interface as ephemeral toasts in the conversation's side channel. To demonstrate the potential for yielding serendipitous insights, we showcase a usage scenario involving a knowledge base of legislative documents as the meeting's context. We then report on a comparative study (N=16), in which participants arrived at informed policy decisions while maintaining natural conversation flow.