Despite the prevalence of sleep-tracking devices, many individuals struggle to translate data into actionable improvements in sleep health. Current methods often provide data-driven suggestions but may not be feasible and adaptive to real-life constraints and individual contexts. We present HealthGuru, a novel large language model-powered chatbot to enhance sleep health through data-driven, theory-guided, and adaptive recommendations with conversational behavior change support. HealthGuru's multi-agent framework integrates wearable device data, contextual information, and a contextual multi-armed bandit model to suggest tailored sleep-enhancing activities. The system facilitates natural conversations while incorporating data-driven insights and theoretical behavior change techniques. Our eight-week in-the-wild deployment study with 16 participants compared HealthGuru to a baseline chatbot. Results show improved metrics like sleep duration and activity scores, higher quality responses, and increased user motivation for behavior change with HealthGuru. We also identify challenges and design considerations for personalization and user engagement in health chatbots.

Adobe has acquired Uru, a computer vision company that helps marketers understand how they could leverage advertising inside videos, according to a post on the New York-based startup's website today. Uru isn't exactly a household name: the company has been fairly quiet about its activities. Its software is supposed to understand the content of a video and then dynamically insert logos and other advertisements that match both the content of the video and look like they were embedded there all along. One of the company's demos from late 2016 shows a logo seemingly painted onto a ping-pong table that was simply digitally edited to be there. The Uru team will be working on Adobe Sensei, a nebulous umbrella encompassing all of the company's work with AI across its entire suite of products.