InquiryBits: Sharing AI Conversation Traces to Support Collaboration Within Trust Boundaries

2026-06-01

AI Summary

This study addresses how AI-powered chat tools shift problem-solving into private human-AI interactions, thereby undermining shared team cognition and collaborative efficiency. To counter this, the authors propose InquiryBits, a novel system grounded in a “trust boundary”–centric design paradigm rather than conventional information granularity. InquiryBits generates configurable, minimal summaries of AI dialogues, enabling selective sharing of interaction traces while preserving privacy. A user study with 80 professionals reveals that participants are willing to share AI conversations within close-knit teams to avoid redundant effort and enhance collaboration; however, their willingness declines markedly as the audience expands. These findings validate that a trust-boundary-based sharing mechanism better aligns with real-world collaborative needs.

Abstract

AI chat tools are shifting problem-solving and brainstorming conversations away from colleagues and into private AI interactions, reducing the shared awareness that supports team coordination. We introduce InquiryBits, a system that shares minimal summaries of AI conversations within configurable trust boundaries, separating AI-only analysis from human-visible sharing. In a study with 80 professionals, we find that people are broadly willing to share these traces to support collaboration and avoid duplicating work - but only within bounded groups. Comfort drops sharply as audience expands beyond close teams; the level of detail shared matters less than who can see it, with a preference for more detail over less within trusted groups. These findings suggest that trust boundaries, more than information granularity, may be the most impactful design parameter.

Problem

• AI collaboration
• trust boundaries
• conversation sharing
• team coordination
• shared awareness

Innovation

• trust boundaries
• AI conversation sharing
• collaboration support
• privacy-aware design
• InquiryBits