Annual personal report
Here's my Apple Health export for the year. Build me a one-page report: trends in resting HR, HRV, sleep duration, and daily steps. Highlight the 3 months that look most different from the rest and hypothesise why.
AI for Apple Health
Apple Health is the largest dataset most people never look at. AI is how you finally read it.
What we’re actually working with
Apple Health quietly aggregates steps, HR, HRV, sleep, workouts, hearing, and dozens of third-party signals. Most people never export it.
Why doing this without a method fails
Apple's interface shows you graphs without context. There's no built-in way to ask 'what changed this year?' or 'what predicts my best months?'
The 3-Layer treatment
How the method handles apple health
Layer 01
Research
Decide which signals in your Apple Health export actually matter to you. Have AI explain what each one measures and the limits of accuracy.
Layer 02
Ledger
Export your full Apple Health archive (Settings → Health → Export). Hand the most relevant CSVs to a long-context AI and build a 1-page personal yearly report.
Layer 03
Protocol
Pick one Apple Health signal you can move (resting HR, daily steps, sleep duration). Run a focused 30-day protocol and let AI score it for you.
Three prompts you can use today
Paste any of these into the AI chat tool you already use. No setup.
Resting HR drift
My resting HR has drifted up over 6 months. Show me the week-by-week trend, calculate the slope, and list the most likely lifestyle drivers I should rule out.
Step count vs. mood journal
I've pasted my daily step count and a short daily mood note (1–5). Find any relationship between movement and mood across 90 days, controlling for day of week.
Common questions
How do I export Apple Health?+
Open Health → tap your profile → Export All Health Data. You get a zip with XML and CSV. The course walks through which files to use first.
Is the data accurate enough to bother?+
For trend-level questions, yes. For absolute clinical numbers (e.g. exact HR during sprints), treat as a sketch, not a measurement.
What about Health app integrations?+
Anything that writes to Apple Health (Oura, Whoop, glucose monitors, scales) becomes part of your single exportable record. That's the power.
More on apple health
Everything we’ve published that touches this topic — refreshed automatically as new entries ship.
From the blog
What ChatGPT is good and bad at for mental health support — an honest framework.
An honest framework for using ChatGPT for mental health support: what it is genuinely good at, where it is dangerous, and a four-line script to keep a thread safe. Not therapy. Not nothing.
The research was never proportionally about women. The apps inherited the gap.
Women's health was historically under-researched, and the apps inherited the gap. Here is the four-line daily note, the four-cycle read-back, and the one paragraph that finally moves a GP visit past “cycles vary.”
The 60-year-old mum who got healthy without any of the apps.
For mums fifty and over, the bottleneck is not data — it is the cost of producing it. Four honest lines a week, read by a practitioner, beat any app stack you cannot sustain.
AI for health, without another app
Why the right way to use AI for health is to skip the dedicated app and learn the method instead. The architecture, the limits, and the free way to start.
Your own AI stack is how you stop paying for generic advice.
Your own AI stack lets you challenge practitioners to go beyond protein and sleep. Here’s what’s under the hood — and the questions to bring next visit.
AI literacy is the health upgrade. The shiny "AI health" app isn't.
Learning to use the free AI tools you already have beats buying another "AI health" app. Why AI literacy — not another subscription — is the real health upgrade.
Case studies
Automated Health Data Flow for a Busy Executive
A streamlined system for health data collection and analysis improved decision-making for a demanding schedule.
Computer Vision Unlocks Deeper Nutrient Insights
A practitioner refines dietary recommendations by leveraging image analysis to quantify food intake with greater precision.
Bridging the Gap Between Movement and Pain Thresholds
A physiotherapist integrated visual analysis to refine client recovery protocols.
The 60-year-old mum who got healthy without any of the apps.
A South Asian mother in her sixties had tried four wellness apps, two wearables, and three diets. The breakthrough came when her practitioner stopped asking her to track and asked her to write four lines a week.
The clinician who narrowed her questions
A cognitive-health practitioner used AI-assisted research to compress a sprawling intake into a tighter, more useful conversation.
Enhanced Nutritional Insight for Individual Wellness
An individual leverages automated data flows to refine dietary choices and improve well-being.
Glossary
AI Health Stack
A personal, tool-agnostic system that uses three free general-purpose AI chat tools as one coordinated health intelligence layer.
Research Layer (Layer 01)
The sourced-search layer of the AI Health Stack. Ranks evidence with linked citations.
Evidence Hierarchy
A simple ranking (RCT > meta-analysis > observational > expert opinion > anecdote) used inside every AI prompt in the stack.
Free 10-Day Challenge
The free entry point to the AI Health Stack. One short prompt per day for 10 days.
Health Sovereignty
The principle that your biological narrative belongs to you — not to an app, a clinic, or a model vendor.
AI Prompt Anatomy
The Wellness & AI structure for a health prompt: role, evidence rules, constraints, output shape, escalation clause.
Related topics
AI for Oura Ring
Export your Oura data and use AI to find the patterns the app doesn't show you. Free method, works with any ring generation.
AI for Whoop
Whoop charges a monthly fee for an opaque score. AI lets you read your own strain and recovery data and decide what's actually working.
AI for Garmin
Garmin Connect collects years of training, HR, sleep, and stress data. Use AI to find patterns the app's badges don't surface.
AI for Fitbit
Fitbit's most useful insights live behind Premium. AI lets you read your own export and skip the upsell — even after Google's changes.
Start with 10 free days.
The free 10-day email challenge teaches the same method on whatever data you already collect. No credit card.