Set up Gemini for wearable data in 10 minutes

The model with the biggest context window — paired with the device you already wear.

9 minutes start to finish

Wearable apps show you a number a day. Gemini can read a year of nights and find the patterns the dashboard never surfaced. The trick is getting the data out and asking the right question.

Before you start

  • Free Google account with Gemini access
  • A CSV export from your wearable (Oura, Apple Health, Garmin, Whoop all support this)
  • 10 minutes

The steps

  1. 01

    Export your wearable data as CSV

    Oura → Account → Export. Apple Health → Profile → Export All. Garmin → Connect web → Export. You want the raw daily file, not a screenshot.

  2. 02

    Open a new Gemini chat

    Use the largest model available (currently Gemini 2.5 Pro or 3.x Pro). Upload the CSV directly — no need to convert.

  3. 03

    Ask trend questions, not snapshot questions

    Bad: "What was my HRV yesterday?" Good: "Across the last 6 months, which days of the week show the lowest HRV, and what's correlated with it in this file?" The point is to find patterns no app shows you.

  4. 04

    Bookmark the chat as your weekly review

    Sunday evening, re-upload the latest export, ask "What changed this week vs. the rolling 4-week average?" That's your weekly review — no new app required.

Honest note

Wearable data is noisy. Treat any single finding as a hypothesis, not a result. Two weeks of pattern beats one anomalous night.

Want the whole stack, not just one tool?

The free 10-Day Challenge wires these together. Or join the free 45-min live workshop and watch me build it end-to-end.

Want the whole method, not just one tool?

The free 10-day email challenge installs Research → Ledger → Protocol on whatever data you already collect.

More for people setting up their stack

Based on what you've been reading — always learning.

See all →