Trend, not noise
Here's 6 months of daily weights. Calculate the 7-, 14-, and 30-day rolling averages. Tell me the true direction across the period and how much of the day-to-day variation is just noise.
AI for weight and body composition
The scale lies daily. AI helps you read what your body is actually doing across months.
What we’re actually working with
Body weight bounces by 1–2 kg per day from food, water, glycogen, and hormones. The real signal lives in the 30-day rolling trend, not the morning number.
Why doing this without a method fails
Weight apps trigger panic on bad days and false confidence on good ones. They don't account for cycle phase, training, or sodium.
The 3-Layer treatment
How the method handles weight
Layer 01
Research
Get a clear, sourced view on what daily weight really measures, and on the actual evidence behind common diet protocols.
Layer 02
Ledger
Daily weight + monthly body composition + meal log + training. Let AI build a true 30/90/180-day rolling view annotated with context.
Layer 03
Protocol
Run a 12-week single-protocol test (e.g. protein at every meal, no late-night eating) with weekly review and a clear stopping rule.
Three prompts you can use today
Paste any of these into the AI chat tool you already use. No setup.
Cycle-aware weight
I'm pasting 4 months of daily weight and cycle dates. Subtract out the typical phase-related fluctuation and tell me my true underlying trend.
Protein protocol
Design a 12-week protocol where the only change is hitting 1.6 g/kg of protein daily. Define how I'll measure success — weight trend, training quality, hunger — and what 'worked' would look like.
Common questions
Why not just use a smart scale's app?+
Smart-scale apps optimise for daily engagement. They're built to react to noise. AI built around your goal does the opposite.
Is body composition data reliable?+
Bioelectrical impedance scales drift hour to hour but the long-term trend is useful. DEXA every 6–12 months gives you a real anchor.
Will AI write my diet?+
It can — but we don't recommend handing diet to AI alone. Use it to design experiments and hold a mirror to your data.
More on weight
Everything we’ve published that touches this topic — refreshed automatically as new entries ship.
From the blog
Personal longevity analytics, without the dashboard
What longevity analytics really tracks, the four signals that compound, and why the right interface is a long-context AI — not another dashboard.
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.
GLP-1 without the brand app
GLP-1 medications shift weight, glucose, energy, and side effects together. Use AI to keep one honest ledger across all four — without the brand app.
The dual-lab interpretation pyramid
Stop choosing between conventional and functional medicine ranges. Read your labs through three lenses in order: clinical, functional, personal. The pyramid that prevents both panic and complacency.
Three free chat tools, three different jobs
Perplexity for research, Gemini for ledger, ChatGPT for protocol. Why we picked these three, what each is uniquely good at, and what to swap if any of them changes.
When the model updates, your method shouldn't
Models will update, get deprecated, change tone, and get acquired. Your method shouldn't have to. Architectural rules for a HealthOS that outlives any single tool.
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.
Activity Trend Recognition for Personalized Energy Management
An individual leverages automated data synthesis and pattern identification to inform daily routine adjustments for sustained energy.
Computer Vision Unlocks Deeper Nutrient Insights
A practitioner refines dietary recommendations by leveraging image analysis to quantify food intake with greater precision.
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.
Bridging the Gap Between Movement and Pain Thresholds
A physiotherapist integrated visual analysis to refine client recovery protocols.
The reader who deleted the fifth nutrition app and kept the noticing
A busy parent stopped re-downloading food trackers, swapped them for a one-page ledger and a Sunday read with a free chat tool — and finally saw the pattern the apps had been hiding for two years.
Glossary
Longevity Analytics
Applying the AI Health Stack to long-horizon biomarkers — labs, body composition, HRV, training load — over months and years.
AI Health Stack
A personal, tool-agnostic system that uses three free general-purpose AI chat tools as one coordinated health intelligence layer.
Evidence Hierarchy
A simple ranking (RCT > meta-analysis > observational > expert opinion > anecdote) used inside every AI prompt in the stack.
Personal AI
AI used by an individual for their own thinking — not as a product they pay for, but as a method they own.
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 Energy
Subjective energy is data. Combine it with sleep, HRV, training, and meals — and AI will show you what's actually making the difference.
Start with 10 free days.
The free 10-day email challenge teaches the same method on whatever data you already collect. No credit card.