What the AI found
“In clients aged 45-60, a 30% increase in reported "brain fog" directly correlates with diets containing more than 150g of processed carbohydrates daily, a pattern she had previously attributed to stress.”
Before
Disorganised client notes, anecdotal patterns
After
Quantified cognitive impacts, personalised plans
The same system, three states — real screens, not a screenshot
- Client: A.K., F, 52
- Week 17 Notes:
- Diet: Breakfast - croissant, coffee. Lunch - pasta, soda. Dinner - ready meal, wine.
- Supplements: Omega-3, B complex.
Prompt
Analyse the attached anonymised client notes for recurring patterns between reported dietary intake (specifically processed carbohydrates) and cognitive complaints (e.g., 'brain fog', 'difficulty concentrating'). Quantify any observed correlations. Focus on clients aged 45-60.
Analyse the attached anonymised client notes for recurring patterns between reported dietary intake (specifically processed carbohydrates) and cognitive complaints (e.g., 'brain fog', 'difficulty concentrating'). Quantify any observed correlations. Focus on clients aged 45-60.
AI
Across your client set (aged 45-60), I observe a statistically significant correlation: a 30% increase in reported 'brain fog' incidents was noted on days following dietary intake exceeding 150g of processed carbohydrates. This trend is present in 78% of the reviewed cases.78%
Clients with carb-linked fog
18%
Avg. 'brain fog' reduction (4 weeks)
r = -0.65
Processed Carb Intake vs. Cognitive Score
From Scattered Notes to Focused Insights
A nutritionist transforms disparate client observations into actionable cognitive patterns with AI.
A nutritionist running a small EU practice, focusing on cognitive health.
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, this nutritionist diligently recorded client dietary intake, mood, and cognitive complaints in a digital notebook. While she suspected certain patterns, the sheer volume of unstructured text made objective analysis impossible. She had hunches, but no quantifiable data to support them, making it difficult to demonstrate progress or refine recommendations effectively. The value of her detailed notes remained largely locked away.
- Client: A.K., F, 52
- Week 17 Notes:
- Diet: Breakfast - croissant, coffee. Lunch - pasta, soda. Dinner - ready meal, wine.
- Supplements: Omega-3, B complex.
- Reported mood: Anxious. Cognitive: Significant 'brain fog' Tuesday-Thursday.
- Sleep: 6h average. Exercise: Light walk x2.
Working state
Membership, doing its job
Frustrated with anecdotal evidence, she began experimenting with a Membership integration, connecting her client notes directly to a large language model. The process involved a simple copy-paste of a week's worth of a client's anonymised data and a direct query to the AI. This allowed her to test her hypotheses against real-world data, observing how the AI processed and identified hidden correlations she couldn't easily spot.
Prompt
Analyse the attached anonymised client notes for recurring patterns between reported dietary intake (specifically processed carbohydrates) and cognitive complaints (e.g., 'brain fog', 'difficulty concentrating'). Quantify any observed correlations. Focus on clients aged 45-60.
Analyse the attached anonymised client notes for recurring patterns between reported dietary intake (specifically processed carbohydrates) and cognitive complaints (e.g., 'brain fog', 'difficulty concentrating'). Quantify any observed correlations. Focus on clients aged 45-60.
AI
Across your client set (aged 45-60), I observe a statistically significant correlation: a 30% increase in reported 'brain fog' incidents was noted on days following dietary intake exceeding 150g of processed carbohydrates. This trend is present in 78% of the reviewed cases.Use case implemented
The finished system, running on its own
Now, she allocates 15 minutes each Friday afternoon to input anonymised weekly client data into her integrated system. The AI swiftly analyses the text, providing succinct summaries and highlighting statistically significant correlations between dietary elements and reported cognitive states. This systematic approach has not only validated her insights but also revealed new, unexpected links, allowing for more precise, evidence-based recommendations and clearer progress tracking for her clients.
78%
Clients with carb-linked fog
18%
Avg. 'brain fog' reduction (4 weeks)
r = -0.65
Processed Carb Intake vs. Cognitive Score
What an outside observer would notice
Reduced by 70%
Time spent on note review
Increased by 50%
Client plan adjustment speed
From 0 to 3-5
Quantifiable insights per week
The stack — build it yourself
Flexible, tagging capabilities for quick data entry.
Excellent at identifying nuanced patterns in unstructured text.
Familiar, shareable, and efficient for tracking quantifiable changes.
These are the tools used in this story. Any can be swapped for an equivalent you already trust.
Go deeper
Do this yourself
Explore the practitioner 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.