IntentWeave: A Progressive Entry Ladder for Multi-Surface Browser Agents in Cloud Portals

TL;DR

IntentWeave introduces a multi-surface design space for browser agents, enabling progressive integration from micro-interventions to dedicated workspaces, improving user satisfaction and control in cloud portal browsing.

Contribution

This work presents a novel design space and implementation for multi-surface browser agents, demonstrating how different spatial strategies impact user experience and control.

Findings

Workspace-heavy strategies reduce task completion time.

Micro-only strategies preserve user control.

Mixed strategies increase user satisfaction.

Abstract

Browser agents built on LLMs can act in web interfaces, yet most remain confined to a single chat surface (e.g., a sidebar). This mismatch with real browsing can increase context-switching and reduce user control. We introduce \textbf{IntentWeave}, a design space of ten spatial paradigms for embedding agentic assistance across a browser, organized as a progressive entry ladder from micro-interventions to dedicated workspaces. We implement IntentWeave as a browser-extension prototype on the Alibaba Cloud website and compare three entry strategies in a within-subjects study (N=16). Workspace-heavy strategies reduced completion time but lowered perceived control; micro-only strategies preserved control but were often insufficient; a mixed sidecar approach achieved the highest satisfaction. We conclude with guidance for escalating and retreating agent surfaces without disrupting user agency.