GlassMail: Towards Personalised Wearable Assistant for On-the-Go Email Creation on Smart Glasses

Optical See-through Head-Mounted Displays (OHMDs) ofer new opportunities for completing complex information processing tasks on the go. We introduce GlassMail, a Large Language Models (LLMs)-based wearable assistant on OHMDs for mobile email creation. Our formative study identifed two challenges of the LLM-based wearable email assistant: (i) achieving efcient and accurate understanding of user intentions, and (ii) ensuring efective information presentation for email processes. Through two empirical studies, we developed a "Single Turn with Optional Clarifcation" approach for accurate user intention recognition and a "Fade Context with Optional Audio" mode for efective email processing. An observation study then evaluated GlassMail’s feasibility in composing formal and semi-formal emails, supporting the usefulness and efectiveness of GlassMail in simple scenarios and yielding insights into potential future improvements for complex scenarios. We further discuss the design implications for the future development of wearable AI-enabled assistants.