Feedstack: Layering Structured Representations over Unstructured Feedback to Scaffold Human AI Conversation

TL;DR

Feedstack is a novel interface that enhances human-AI conversations by adding layered, structured feedback tools to improve exploration, reflection, and shared understanding, representing an early step in this research area.

Contribution

This work introduces Feedstack, a new layered feedback interface for conversational systems, and provides formative insights from user studies to guide future development.

Findings

Users engaged with layered feedback structures to organize conversations.

Feedstack revealed user intent and design principles through shared representations.

The system served as a design probe for future conversational feedback tools.

Abstract

Many conversational user interfaces facilitate linear conversations with turn-based dialogue, similar to face-to-face conversations between people. However, digital conversations can afford more than simple back-and-forth; they can be layered with interaction techniques and structured representations that scaffold exploration, reflection, and shared understanding between users and AI systems. We introduce Feedstack, a speculative interface that augments feedback conversations with layered affordances for organizing, navigating, and externalizing feedback. These layered structures serve as a shared representation of the conversation that can surface user intent and reveal underlying design principles. This work represents an early exploration of this vision using a research-through-design approach. We describe system features and design rationale, and present insights from two formative (n=8, n=8) studies to examine how novice designers engage with these layered supports. Rather than presenting a conclusive evaluation, we reflect on Feedstack as a design probe that opens up new directions for conversational feedback systems.