Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas
For users of LLM-based conversational interfaces, this work addresses the limitation of linear chat in supporting exploration and management of long-running interactions.
CanvasConvo transforms linear LLM chat into a branching conversation tree on a spatial canvas, enabling parallel exploration of alternatives. In a 5-7 day field study with 24 participants, it supported exploratory workflows and non-linear interaction.
Conversational interfaces powered by large language models (LLMs) are widely used for ideation and analysis, yet their linear structure limits exploration of alternatives and management of long-running interactions. We present CanvasConvo, a conversational interface concept that transforms linear chat into a branching conversation tree embedded in a spatial canvas. CanvasConvo enables users to explore what-if scenarios by branching directly from conversational content, supporting parallel development of alternative directions. These branches are visualized on a canvas while remaining integrated with a familiar chat interface, allowing users to switch between linear and non-linear interaction. Features such as timeline-based navigation, automatic tagging and summarization, and context-aware controls (e.g., goals, reusable prompts) support structured interaction and continuity. We evaluated CanvasConvo in a 5-7 day field study with 24 participants. Our findings highlight how non-linear conversational structures support exploratory workflows and different interactions in LLM-based work.