Turn Apple Health exports into weekly coaching notes
They used a custom agent to review Apple Health history and return practical guidance on food, exercise, and recovery.
- What they did
- They maintained a chat with background details about their routine, then added one fresh batch of personal health records each week. The bundle covered meals, steps, workouts, sleep, blood pressure, smart-scale readings, and supplements. They checked the file themselves first so clear errors would be caught before Gemini saw it. After that, they asked for concrete help such as how to warm up, how to structure sessions, how to wind down, what to do about specific joints, and what to eat from the foods they already keep around.
- How it went
- Gemini detected that their iodine intake was extremely low, and after they changed to iodized salt they felt better within a week. It also rearranged their five weekly sessions into a PPL, Tabata, and distance-run setup that improved recovery. The whole system still depended on manual uploads, and older context could slip away in a long chat.
- Tips
- A quick manual check before each upload helps prevent bad data from steering the advice. Long-running chats are useful, but they need occasional refreshes if you want the agent to remember earlier weeks.
Try it yourself with Claude Code
I want to make a health coach from my Apple Health export. Build a workflow or script that reads files in [export file or folder path], pulls out meals, activity, weight, blood pressure, sleep, workouts, and supplements, and turns them into a weekly summary with trends plus advice for [goal]. Before any irreversible action, stop and ask me to approve it after showing me the parsed data and any suspicious entries. Don’t send anything to an external service unless I explicitly say yes.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Triage school messages and prepare my replies
A parent has an agent sort school mail, summarize it, and draft responses they can review before sending.
Use a local agent for personal errands
A commenter uses a trusted local agent to handle travel, media conversion, ebook searching, design tweaks, and schedule tracking.
Let an AI renter handle apartment follow-ups
A renter let Kaleno message properties, ask for missing details, and keep the conversation going while they stayed in control.
Let a sleep pose trigger a fan
They built a Raspberry Pi setup that watches sleeping posture and flips a fan on or off with a remote button pusher.
Use a browser copilot to complete PDF forms
A browser-based agent can pull details from connected records or typed input and place them into PDF fields for review before signing.
Draft tailored job materials before you apply
A commenter had an agent prepare role-specific CVs and cover letters so they could review and edit before submitting applications.