Stack audit
Here's my current supplement stack with doses. For each one: best available evidence, realistic effect size, who responds, and whether you'd keep it. Vendor-neutral, no recommendations to buy other things.
AI for supplement decisions
The supplement industry sells you the next thing. AI helps you actually test what you already take.
What we’re actually working with
Supplements are the most marketed and least tested category in personal health. Most people add, never subtract.
Why doing this without a method fails
Influencers and brands sell stacks. Real evidence often disappoints. Most users have never tested whether their stack does anything for them.
The 3-Layer treatment
How the method handles supplements
Layer 01
Research
Have sourced AI read the actual literature on each supplement in your stack — effect size, dose, who responds, who doesn't.
Layer 02
Ledger
Log your current stack with start date, dose, timing, and the symptoms you hoped to change.
Layer 03
Protocol
Run a clean 8-week stop/start test on one supplement at a time. Define success before starting.
Three prompts you can use today
Paste any of these into the AI chat tool you already use. No setup.
Stop-test design
Help me design an 8-week test where I stop [magnesium / fish oil / creatine] cleanly. Define what I'll measure and what change would count as 'works for me'.
Sourced brief
Give me a 1-page sourced brief on the current evidence for [creatine / NAC / berberine] in healthy adults. Cite each claim.
Tools that help
How AI tools make supplements easier to live with — and understand.
You don’t need another app. These are the tools most people already have or can use for free, and the specific job each one does when you point it at supplements.
Research the literature
A sourced-search AI (e.g. Perplexity, ChatGPT search, Gemini)
Replaces an afternoon of tab-juggling on supplements with a cited summary in minutes. Ask it to mark every claim as primary study, review, or opinion — that one habit removes most of the noise.
Read your own data
A long-memory chat AI (e.g. Claude, ChatGPT, Gemini)
Paste weeks of notes, exports, or symptom logs about supplements in a single window. The AI spots patterns your seven separate apps hide from you, and remembers them next week.
Capture without friction
Apple Health + Notes (or Google Fit + Keep)
Already on your phone. Pulls supplements-relevant signals into one export and lets you jot context in seconds — no new subscription, no new dashboard to maintain.
Stream the raw signal
Your wearable (Oura, Whoop, Garmin, Apple Watch)
Stop reading the marketing score. Export the raw stream behind your supplements number and feed it to a chat AI — that's where the actual insight lives.
Build your own reference
NotebookLM (or any source-grounded notebook)
Drop in your lab PDFs, saved articles, and personal notes on supplements. Ask questions; the answers cite back into your own sources. Becomes a second brain you actually trust.
Turn data into a plan
A weekly review prompt
One scheduled prompt every Sunday: "Given this week's supplements data and notes, what changed, what's noise, what's the smallest experiment for next week?" Replaces three productivity apps and an anxiety spiral.
Common questions
Will AI tell me what to take?+
No — and that's the point. The method protects you from the next sales pitch.
Is this medical advice?+
No. AI helps you read evidence and your own response. Decisions stay with you and your clinician.
Why doesn't the course recommend brands?+
Because that's how supplement content gets corrupted. Vendor-neutral by design.
Deeper research
The evidence — and where it breaks down
Six short briefs on what the literature, the devices, and the AI tools actually do when you point them at supplements. Read them before you change anything.
What the current research actually says about supplements+
Supplements are the most marketed and least tested category in personal health. Most people add, never subtract. Most peer-reviewed work on supplements sits in three buckets: mechanistic studies (small samples, tightly controlled), observational cohorts (large samples, noisy variables), and consumer-device validation papers (mixed quality, often vendor-funded). When you read AI-generated summaries on AI for supplements, treat the first two as signal and the third as buyer-beware. The 3-Layer method makes you triage these before they enter your personal ledger.
What your wearable or app is really measuring (and what it isn't)+
Consumer devices that surface a "Supplements" score almost always combine a small set of raw signals — accelerometry, optical heart rate, skin temperature, sometimes ECG — into a proprietary index. The score is opinionated, the raw stream is not. The Ledger layer of the method exports the raw stream so AI can analyze the underlying variables instead of the marketing score. That is where most insight lives.
Where consumer-grade supplements data is reliable vs noisy+
Cross-validation studies (Stanford, ETH Zürich, and several EU centres in 2023–2025) consistently show that wearables are most reliable for trend direction and least reliable for absolute values — especially night-to-night supplements. Use the data the way it is actually accurate: deltas over weeks, not single-night verdicts. AI is well-suited to this kind of rolling-window analysis; humans staring at one number are not.
Common confounders that distort supplements signals+
Influencers and brands sell stacks. Real evidence often disappoints. Most users have never tested whether their stack does anything for them. The most under-discussed confounders are time-of-month variation, recent travel, alcohol with a 48–72 hour tail, ambient temperature, and any acute infection — all of which shift baseline values by more than most behaviour changes do. A good AI ledger tags these as covariates before drawing conclusions; a bad one quietly attributes the swing to whatever supplement you started that week.
What "good evidence" looks like — and what's hype+
Good evidence on supplements: pre-registered protocols, declared funding, raw data available, effect sizes reported with confidence intervals, replication in an independent cohort. Hype: single n-of-1 anecdotes generalised on social media, supplement-funded reviews, AI summaries that cite nothing. Have sourced AI read the actual literature on each supplement in your stack — effect size, dose, who responds, who doesn't. Asking AI to mark every claim with "primary study", "review", or "opinion" before you act on it is one of the most useful prompts you can run.
How AI changes the picture for supplements in 2026+
Three shifts matter. First, long-context models can now read 60–90 days of your raw export in a single pass and find correlations no app dashboard surfaces. Second, sourced-search models (with citations) collapse the literature-review step from days to minutes — provided you verify the citations. Third, agentic workflows can run the same daily check-in you would otherwise skip. Run a clean 8-week stop/start test on one supplement at a time. Define success before starting. The judgement layer — what to test, what to ignore, when to stop — is the part that stays with you.
Educational summaries — not medical advice. Cross-check claims against primary sources before changing anything material.
More on supplements
Everything we’ve published that touches this topic — refreshed automatically as new entries ship.
From the blog
AI inside your messenger — the most under-used setup in personal health.
How to wire an AI assistant into the messenger you already use — captures, questions, reminders and background research land in one thread instead of four apps. The full 10-minute setup and the standing-instructions block.
One source, four outputs — the quiet 2026 shift in your AI tool stack.
The 2026 AI tool stack shift: one source document now becomes a deck, an explainer video, a podcast, and an infographic — in one tool. The new stack, the keepers, and the cuts.
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.
We are our own case study
Wellness & AI built its own recommendation engine using the 3-Layer Stack it teaches. Browse signals, affinity scoring, dismiss-to-learn. Here is why eating your own cooking is the only credible proof.
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
Computer Vision for Diet and Supplement Review
A nutritionist improved client compliance and personalized recommendations using an image analysis tool to objectively review dietary intake and supplement use.
Rethinking Sleep Architecture for Deeper Rest
A practitioner shifted from generic sleep advice to nuanced, evidence-based recommendations by leveraging a multi-tool AI approach.
The individual who replaced three subscriptions with one scheduled prompt
A reader cancelled a habit tracker, a meal planner, and a weekly review app after a single Monday-morning scheduled prompt quietly did all three jobs.
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 platform that became its own case study
How we built a recommendation engine that learns what each visitor needs — and why we published the playbook.
Glossary
AI Health Stack
A personal, tool-agnostic system that uses three free general-purpose AI chat tools as one coordinated health intelligence layer.
3-Layer Method
The Wellness & AI methodology: Research → Ledger → Protocol. Three jobs, three tools, one stack.
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.
Reality Filter
The constraint test the Protocol layer applies — the reason 90% of generic protocols fail and yours does not.
Further reading
Outside voices on supplements
Editorial citations from publications we trust. Different lens, same rigour — useful before you change anything material.
Related topics
AI for Training Load
Use AI to read your weekly training data and your recovery markers together — and stop wrecking yourself by accident.
AI for Stress
Your HRV, sleep, and resting HR already record your stress. AI helps you read them — and design a response that actually fits your life.
AI for Longevity
Skip the guru subscriptions. Use AI to read the longevity literature, your own labs and data, and build a focused protocol that fits your life.
AI for Weight
Daily weight is mostly noise. AI helps you read the trend across months, separate water from fat, and stop reacting to the wrong signal.
Pairs with supplements
Ready to install this, not just read about it?
Three à la carte ways to go from prompts to a running stack — pick the one that matches where you are.
DIY · 10 minFrom €0
Setup guides
Configure ChatGPT, Claude, Gemini and NotebookLM for supplements in under ten minutes each.
Browse setupsLearn the methodFrom €97
The 3-Layer Course
Four-week course on Research → Ledger → Protocol. Same method we use with private clients.
See the coursesWe do it for youFrom €250
Setup, done with you
One working session — we install your stack live and hand you a running system.
See SetupStart with 10 free days.
The free 10-day email challenge teaches the same method on whatever data you already collect. No credit card.
Personalised
More for people exploring supplements
Based on what you've been reading — always learning.
Related
Keep building the stack.
Three doors deeper into the system — pick the one that matches where you are.
Start here€5
The AI Tools Atlas
100+ AI tools sorted by what they actually do for your health stack — research, ledger, protocol. Updated quarterly.
Get the AtlasFree · Live
Build it live in 45 min
Bi-weekly Zoom workshop with Sabin. Build your AI Health Stack end-to-end, ask one real question, leave with a working setup.
Reserve a seatLearn the method
The 3-Layer Course
Build your own AI Health Stack in 4 weeks. Same method we use with private clients — Research, Ledger, Protocol.
See the courses