The poster uses Claude with Apple Health, nutrition and lifting app data, plus medication and bloodwork files, and has it maintain an HTML dashboard.
The poster uses Claude with Apple Health, nutrition and lifting app data, plus medication and bloodwork files, and has it maintain an HTML dashboard.
One commenter described a setup very close to this: Garmin data is pulled hourly into an InfluxDB on their server, and Claude Code runs there on a scheduled daily morning task. Claude reads load, stress, sleep and related metrics, calculates a training-readiness score itself, builds and adjusts the training plan, and publishes the result to a small webpage they host for phone access; they also gave it an initial full export plus years of Garmin, Strava, and .fit history for context.
They said it keeps daily training specific enough to avoid burnout or overtraining and can notice rough periods like vacation, long work weeks, and time-zone travel. The post gives no quantified results, only that long-term history improved context for future goals.
The main catch they mention is setup: hourly polling plus a scheduled Claude Code task on your own server, with a big historical import at the start.
I'm going to upload my [Apple Health export, nutrition log, lifting app data] plus [bloodwork or medication notes]. Analyze trends in my training, recovery and diet toward my goal of [goal], then build me an HTML dashboard I can update each week with new data. Finish with three specific changes to try this week, and flag anything that sounds like a question for my doctor rather than guessing.
Score every demo request against your ICP, update HubSpot and ping the right rep in Slack within a minute of the form submit.
Every new Zendesk ticket gets a category, priority and sentiment tag plus a draft reply in an internal note before an agent opens it.
Copilot and Claude review each PR for bugs, missing tests and risky changes before a human looks, so reviewers can focus on design.