What the AI found
“Your average weekly protein intake consistently dropped by 15% on weeks following international travel, correlating with a 7% decrease in reported energy levels.”
Before
Vague nutritional goals, inconsistent tracking
After
Data-driven weekly nutrition adjustments
The same system, three states — real screens, not a screenshot
| Week of 2/10 | Protein goal — 120g |
| Week of 9/10 | Protein goal — 120g |
| Week of 16/10 | Protein goal — 120g |
| Week of 23/10 | Protein goal — 120g |
Prompt
Analyse the attached spreadsheet containing 8 weeks of daily food logs (protein intake in grams) and corresponding self-reported energy levels (1-10 scale), alongside my travel dates (international flights). Identify any significant correlations between international travel, protein intake, and subsequent energy levels. Quantify any observed trends.
Analyse the attached spreadsheet containing 8 weeks of daily food logs (protein intake in grams) and corresponding self-reported energy levels (1-10 scale), alongside my travel dates (international flights). Identify any significant correlations between international travel, protein intake, and subsequent energy levels. Quantify any observed trends.
AI
Analysis of your 8-week data set reveals a notable pattern: your average weekly protein intake consistently dropped by 15% (from 120g to 102g/day) on weeks immediately following international travel, compared to non-travel weeks. This dip correlated with a 7% decrease in your reported average weekly energy levels (from 8.2 to 7.6 on your 1-10 scale) during those same post-travel weeks. No other significant correlations were observed for protein intake fluctuations.115
Avg. Weekly Protein (g)
8.1
Avg. Weekly Energy (1-10)
-8%
Post-Travel Protein Dip
Weekly Trends Over Time
A 58-year-old in Northern Europe shifted from vague nutritional intentions to clear, data-informed weekly adjustments by integrating wearables and AI analysis.
A 58-year-old in Northern Europe, focusing on healthy aging.
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
Before engaging in a more structured approach, Lars, a 58-year-old focusing on healthy aging, had a general idea of what he should be eating. He tracked some meals inconsistently using a popular food logging app, but mostly relied on intuition. The data remained fragmented across various apps, never consolidated or analysed to yield actionable insights. He rarely reviewed his dietary patterns against his activity or subjective well-being, leaving a significant gap between his intentions and his actual daily habits. This left him feeling uncertain about his nutritional progress, especially after business trips.
| Week of 2/10 | Protein goal — 120g |
| Week of 9/10 | Protein goal — 120g |
| Week of 16/10 | Protein goal — 120g |
| Week of 23/10 | Protein goal — 120g |
| Energy levels | subjective, unrecorded |
Working state
Done-for-you, doing its job
The Wellness & AI team integrated Lars’s existing wearable data with his food logs. We then used a large language model to analyse the combined data. Lars provided a specific prompt to identify correlations between his travel schedule, dietary intake, and subjective energy levels. The AI processed weeks of granular data to spot trends, offering a tangible connection between his travel habits and nutritional adherence, which he could then address proactively. This process transformed raw data into a clear, actionable insight that he could immediately apply to his routine.
Prompt
Analyse the attached spreadsheet containing 8 weeks of daily food logs (protein intake in grams) and corresponding self-reported energy levels (1-10 scale), alongside my travel dates (international flights). Identify any significant correlations between international travel, protein intake, and subsequent energy levels. Quantify any observed trends.
Analyse the attached spreadsheet containing 8 weeks of daily food logs (protein intake in grams) and corresponding self-reported energy levels (1-10 scale), alongside my travel dates (international flights). Identify any significant correlations between international travel, protein intake, and subsequent energy levels. Quantify any observed trends.
AI
Analysis of your 8-week data set reveals a notable pattern: your average weekly protein intake consistently dropped by 15% (from 120g to 102g/day) on weeks immediately following international travel, compared to non-travel weeks. This dip correlated with a 7% decrease in your reported average weekly energy levels (from 8.2 to 7.6 on your 1-10 scale) during those same post-travel weeks. No other significant correlations were observed for protein intake fluctuations.Use case implemented
The finished system, running on its own
Now, Lars receives a concise weekly summary via email, highlighting key nutritional metrics and any significant deviations based on his activity and travel. This automated report, generated through a consistent AI analysis, allows him to quickly identify patterns and make informed adjustments to his diet. His dietary decisions are no longer based on guesswork but on a personalised, data-driven understanding of his body’s responses. This system provides a clear, reliable feedback loop, ensuring his nutritional strategy remains aligned with his longevity goals. The consolidated view offers clarity without overwhelming him with raw data.
115
Avg. Weekly Protein (g)
8.1
Avg. Weekly Energy (1-10)
-8%
Post-Travel Protein Dip
What an outside observer would notice
6 minutes
Weekly review time
+40%
Nutritional intake clarity
+1 key point
Post-travel energy maintenance
The stack — build it yourself
Familiar, flexible, and easily integrated for manual data input and consolidation from various sources.
Reliable and comprehensive tracking of activity, heart rate, and sleep metrics from personal devices.
Capable of processing complex data sets to identify non-obvious correlations and quantify trends.
Ensures consistent, timely delivery of personalised insights without manual intervention.
These are the tools used in this story. Any can be swapped for an equivalent you already trust.
Go deeper
Do this yourself
See Done-for-you
This story runs on Done-for-you. The tools and prompts above are the real build — swap any tool for your own equivalent and follow the same steps.