Workflow · healthcare · workflow
Google builds a personalized AI health coach powered by Gemini models for Fitbit Premium users
Health and fitness journeys have historically been fragmented, generic, and inaccessible — providers suggest actions like seeing a specialist or losing weight without connecting users to the right resources, leaving users to connect the dots themselves.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User health question
A user asks a health or fitness question to the personal health coach.
Tools used
Gemini modelsFitbitSHARP evaluation framework
Outcome
Google launched a public preview of the AI-powered personal health coach for eligible US-based Fitbit Premium users, validated through the SHARP evaluation framework involving over 1 million human annotations and more than 100k hours of human evaluation.
Results
Time savedmore than 100k hours
Volumeover 1 million
Running sincelate October 2025 (public preview rollout)
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
agentic workflowcode generationconversational aimulti agent workflowpersonalizationsummarizationmedical recordhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedhealthcaresoftwareaccuracy improvementtechnical build writeupagentic task execution