Google is using Gemini for health coaching, with a system designed to answer questions such as, “Do I get better sleep after exercising?” by analyzing sleep and activity data and turning it into personalized guidance.
The approach relies on numerical reasoning over physiological time series data. For questions like this, the coach checks recent data availability, selects the right metrics, compares relevant days, places results against personal baselines and population-level statistics, considers prior interactions with the coach, and then uses that analysis to provide tailored answers and insights.
Google says it also uses a multi-agent framework to coordinate expert sub-agents and produce clear, consistent and holistic support. The framework includes a conversational agent for multi-turn conversations, intent understanding, agent orchestration, context gathering and response generation.
It also includes a data science agent that iteratively uses tools to fetch, analyze, and summarize relevant data such as sleep and workout data, leveraging code-generation capabilities as needed.
A third component is a domain expert, such as a fitness expert, that analyzes user data to generate personalized fitness plans and adapt them as progress and context change.
Source: research.google.
Companies can share verified announcements through Newz9’s international press release submission page.
