What the AI found
“Your current data suggests a significant decline in average VO2 max by 0.8 ml/kg/min per year since you turned 40, a trend stronger than predicted by age alone, impacting your long-term cardiovascular health markers.”
Before
Disparate health apps, no clear trends
After
Unified data, actionable longevity insights
The same system, three states — real screens, not a screenshot
| Date | Metric A — Metric B |
| 2023-01-01 | 45 — 120/80 |
| 2023-01-02 | 46 — 121/79 |
| ... |
Prompt
I've compiled my health data from Apple Health, Garmin, and lab results into a Google Sheet. Assume the role of a longevity data analyst. Identify the most significant trends impacting my long-term health based on this data, particularly regarding cardiovascular and metabolic markers. Highlight any surprising patterns or deviations from expected age-related changes. Focus on actionable insights with specific numerical findings. Here's a sample of my data structure and values: [Date, Sleep Score, Resting Heart Rate, HRV, Steps, VO2 Max, Fasting Glucose, HbA1c, Cholesterol Total, HDL, LDL, Triglycerides, Weight].
Can you analyse this aggregated data for longevity trends?
AI
Based on your data, your average VO2 max has seen a steady decline of 0.8 ml/kg/min per year since age 40, a rate higher than typical age-related changes. This suggests a specific area for cardiovascular focus. Your fasting glucose also shows a slight, but consistent, upward trend of 0.05 mmol/L annually over the last two years, shifting you closer to the pre-diabetic range.-0.8 ml/kg/min/year
VO2 Max Trend
+0.05 mmol/L/year
Fasting Glucose Trend
52 bpm
Avg Resting HR (30d)
One Insight, Better Longevity Tracking
From scattered self-tracking to a clear, actionable longevity forecast.
A 45-year-old software engineer, Northern Europe
Tools used
The real tools used here — swap any for your own equivalent. Each links to how we’d set it up.
Starting state
Before anything was set up
For years, Mark had diligently logged his health data across various apps: Apple Health for steps and sleep, Garmin for workouts, and a separate spreadsheet for blood markers. Each provided a snapshot, but connecting the dots into a coherent longevity picture felt like an insurmountable task. He knew he was collecting valuable information, but it remained siloed, offering no clear path forward beyond raw numbers. The data existed, but insights didn't.
| Date | Metric A — Metric B |
| 2023-01-01 | 45 — 120/80 |
| 2023-01-02 | 46 — 121/79 |
| ... | |
| 2024-03-15 | 42 — 128/84 |
Working state
Membership, doing its job
Mark copied his aggregated health data from various sources (Apple Health export, Garmin Connect export, and a CSV of bloodwork from a lab portal) into a single Google Sheet. He then pasted a carefully crafted prompt into ChatGPT, asking it to act as an analytical assistant. The prompt instructed the AI to identify critical trends and potential areas for intervention related to longevity, specifically focusing on cardiovascular and metabolic markers.
Prompt
I've compiled my health data from Apple Health, Garmin, and lab results into a Google Sheet. Assume the role of a longevity data analyst. Identify the most significant trends impacting my long-term health based on this data, particularly regarding cardiovascular and metabolic markers. Highlight any surprising patterns or deviations from expected age-related changes. Focus on actionable insights with specific numerical findings. Here's a sample of my data structure and values: [Date, Sleep Score, Resting Heart Rate, HRV, Steps, VO2 Max, Fasting Glucose, HbA1c, Cholesterol Total, HDL, LDL, Triglycerides, Weight].
Can you analyse this aggregated data for longevity trends?
AI
Based on your data, your average VO2 max has seen a steady decline of 0.8 ml/kg/min per year since age 40, a rate higher than typical age-related changes. This suggests a specific area for cardiovascular focus. Your fasting glucose also shows a slight, but consistent, upward trend of 0.05 mmol/L annually over the last two years, shifting you closer to the pre-diabetic range.Use case implemented
The finished system, running on its own
Now, Mark has a recurring weekly task to export his latest data and paste it into his Google Sheet. His "Membership" template in ChatGPT is ready. He runs the prompt, and within minutes, receives a summary of key trends and a refined forecast. This allows him to adjust his training or diet based on quantitative insights, rather than just intuition, making his longevity efforts more precise and data-driven.
-0.8 ml/kg/min/year
VO2 Max Trend
+0.05 mmol/L/year
Fasting Glucose Trend
52 bpm
Avg Resting HR (30d)
What an outside observer would notice
Reduced by 80%
Time spent gathering insights
Increased from ~10 to >100
Data points reviewed per week
Increased from 0 to 2-3
Actionable adjustments made monthly
The stack — build it yourself
Familiar, flexible for varied data types, easy to export and import.
Excellent for natural language querying of complex data patterns and generating summary insights.
Default for iPhone users; collects a wide range of ambient health metrics.
Comprehensive and accurate fitness tracking for training metrics like VO2 Max.
These are the tools used in this story. Any can be swapped for an equivalent you already trust.
Go deeper
Do this yourself
See Membership
This story runs on Membership. The tools and prompts above are the real build — swap any tool for your own equivalent and follow the same steps.