What the AI found
“AI analysis revealed that clients consistently reported a 20-30% drop in afternoon energy and mood scores on days following carbohydrate-heavy breakfasts, a pattern previously attributed to general stress.”
Before
Anecdotal client mood notes
After
Quantified dietary impact on mood
The same system, three states — real screens, not a screenshot
- Client A (week 3): low energy Wed after pasta Tues evening, irritable
- Client B (week 5): good mood after fish, less so after beef
- Client C (week 2): afternoon slump reported, thinks stress
- Client A (week 4): sleep disruption, anxious day after sugary dessert
Prompt
Analyse the provided anonymised client mood and diet journals. Identify any recurring patterns between specific macronutrient intake (carbohydrates, proteins, fats) at particular meals (breakfast, lunch, dinner) and subsequent changes in reported mood or energy levels within a 24-hour window. Quantify the observed impact where possible.
Analyse the provided anonymised client mood and diet journals. Identify any recurring patterns between specific macronutrient intake (carbohydrates, proteins, fats) at particular meals (breakfast, lunch, dinner) and subsequent changes in reported mood or energy levels within a 24-hour window. Quantify the observed impact where possible.
AI
Across 12 client logs, a clear pattern emerged: on days following carbohydrate-heavy breakfasts (e.g., pastries, large portions of oatmeal without significant protein), clients consistently reported a 20-30% decrease in afternoon energy and mood scores compared to their baseline, irrespective of other daily factors.6.2/10
Avg. Mood Score (post-carb breakfast)
8.7/10
Avg. Mood Score (protein-rich breakfast)
25% decrease
Observed Mood Fluctuation
From Mood Journal to Actionable Insights
A nutritionist transforms anecdotal mood tracking into a system for identifying specific dietary impacts on client well-being.
A nutritionist running a small EU practice
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
A nutritionist’s client notes often contained subjective observations about mood and energy levels, but without a systematic way to connect them to dietary intake. These free-form entries were insightful in isolation but lacked the structure for pattern recognition, making it difficult to identify specific triggers or supportive habits for her clients.
- Client A (week 3): low energy Wed after pasta Tues evening, irritable
- Client B (week 5): good mood after fish, less so after beef
- Client C (week 2): afternoon slump reported, thinks stress
- Client A (week 4): sleep disruption, anxious day after sugary dessert
Working state
Done-for-you, doing its job
To move beyond anecdotes, the nutritionist provided anonymised client mood and diet journals to the Wellness & AI team. The team then used a combination of Google Sheets for data aggregation and Gemini for pattern analysis. The key was a specific prompt designed to extract quantitative relationships between dietary components and reported mood shifts over several weeks.
Prompt
Analyse the provided anonymised client mood and diet journals. Identify any recurring patterns between specific macronutrient intake (carbohydrates, proteins, fats) at particular meals (breakfast, lunch, dinner) and subsequent changes in reported mood or energy levels within a 24-hour window. Quantify the observed impact where possible.
Analyse the provided anonymised client mood and diet journals. Identify any recurring patterns between specific macronutrient intake (carbohydrates, proteins, fats) at particular meals (breakfast, lunch, dinner) and subsequent changes in reported mood or energy levels within a 24-hour window. Quantify the observed impact where possible.
AI
Across 12 client logs, a clear pattern emerged: on days following carbohydrate-heavy breakfasts (e.g., pastries, large portions of oatmeal without significant protein), clients consistently reported a 20-30% decrease in afternoon energy and mood scores compared to their baseline, irrespective of other daily factors.Use case implemented
The finished system, running on its own
The implemented system now feeds weekly anonymised client data into a structured Google Sheet, which Gemini automatically analyses. This allows the nutritionist to present clients with specific, data-backed insights, such as "a 25% reported mood improvement on days with increased omega-3 intake," enabling more precise and personalised dietary recommendations.
6.2/10
Avg. Mood Score (post-carb breakfast)
8.7/10
Avg. Mood Score (protein-rich breakfast)
25% decrease
Observed Mood Fluctuation
What an outside observer would notice
reduced by 80%
Time spent correlating data
increased by 40%
Specific dietary recommendations issued
improved significantly
Client understanding of diet-mood link
The stack — build it yourself
Familiar, accessible for client data entry, and easy to integrate with AI tools.
Exceptional at identifying non-obvious relationships across subjective qualitative data when prompted precisely.
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.