What the AI found

“AI identified that 80% of client mood dips correlated with days they reported consuming less than 1.5 litres of water, a factor previously overlooked in self-reported dietary logs.”

Before

Vague client mood reports, unclear triggers

After

Clear mood patterns, actionable hydration insights

The same system, three states — real screens, not a screenshot

1Starting

Client Progress Notes

Client A (4 weeks): Mood: 'okay', 'a bit tired', 'good day'.
Diet notes: 'standard', 'ate out once'.
Activity: 'walked dog', 'gym twice'.
Sleep: '7-8 hours', 'woke up once'.

2Working

Gemini

Prompt

Analyze the provided anonymised client daily logs (mood, diet, sleep, activity) for the past 4 weeks. Identify any consistent correlations or significant patterns between reported mood and other lifestyle factors. Specifically, quantify any strong relationships. Daily Logs: Day 1: Mood 6/10. Diet: usual. Sleep: 7h. Water: ~1L. Activity: walk. Day 2: Mood 7/10. Diet: usual. Sleep: 8h. Water: ~2L. Activity: gym. Day 3: Mood 5/10. Diet: ate out, pizza. Sleep: 6h. Water: ~1L. Activity: light walk. Day 4: Mood 8/10. Diet: usual. Sleep: 7.5h. Water: ~2.5L. Activity: gym. [... 24 more days of similar anonymised data ...] Day 28: Mood 5/10. Diet: usual. Sleep: 6.5h. Water: ~1L. Activity: no exercise.

Upon reviewing the logs, a notable pattern emerges: 80% of days where mood was reported as 5/10 or lower also coincided with a reported daily water intake of less than 1.5 litres. This correlation is stronger than those observed for diet variety or sleep duration within the given data.

3Implemented

Google Sheets

Client A Mood Log (Week 1)
Day 1 Mood Score	7
Day 1 Water Intake (L)	2.2

PractitionerResources in use

A Simple Mood Playbook for Client Clarity

How a practitioner leveraged an AI-curated resource to refine client mood tracking from vague self-reports to actionable, specific patterns.

A nutritionist running a small practice, Northern EU

Tools used

Gemini· data analysis & pattern recognition Google Sheets· structured data capture

The real tools used here — swap any for your own equivalent. Each links to how we’d set it up.

Oct 2, 20265 min readWellness & AI editorial

Starting state

Before anything was set up

Anna, a nutritionist, found her clients' mood tracking to be inconsistent. Weekly check-ins often yielded generic "fine" or "a bit low" reports, making it difficult to identify underlying patterns. Their scattered notes on diet, sleep, and activity provided little coherent data to act upon.

Client Progress Notes

Client A (4 weeks): Mood: 'okay', 'a bit tired', 'good day'.
Diet notes: 'standard', 'ate out once'.
Activity: 'walked dog', 'gym twice'.
Sleep: '7-8 hours', 'woke up once'.
Feeling overwhelmed by vague reports.

Working state

Resources, doing its job

To bring clarity, Anna turned to a Wellness & AI mood tracking playbook. She inputted her client's anonymised daily logs for the past month into a custom prompt within Gemini, requesting an analysis of potential correlations between reported mood and other lifestyle factors. The AI immediately began processing the disparate data points.

Gemini

Prompt

Use case implemented

The finished system, running on its own

With the AI's insight, Anna could quickly establish a targeted conversation with her client about hydration, moving beyond general dietary advice. She then built a simple Google Sheet to monitor fluid intake alongside mood scores, providing concrete, measurable progress for their next review. This refined process made client check-ins more focused and effective.

Google Sheets

Client A Mood Log (Week 1)
Day 1 Mood Score	7
Day 1 Water Intake (L)	2.2
Day 2 Mood Score	6
Day 2 Water Intake (L)	1.8
Day 3 Mood Score	8
Day 3 Water Intake (L)	2.5

What an outside observer would notice

From 'Vague' to 'Hydration-linked'

Client Mood Insight Specificity

From 'General' to 'Targeted'

Consultation Focus

Reduced by 60%

Time to Insight

The stack — build it yourself

Geminiprimary analysis engine

Chosen for its ability to quickly process unstructured text and identify non-obvious correlations across multiple variables.

Google Sheetsstructured data collection

Simple, accessible, and easily shareable for ongoing client tracking post-insight.

These are the tools used in this story. Any can be swapped for an equivalent you already trust.

Go deeper

ResourcesSee the product this story runs on.The 3-Layer MethodResearch, Ledger, Protocol — the method behind every story.Every tool, mappedThe full stack of AI tools these systems are built from.Build your own stackGet a free, personalised stack in about two minutes.

Do this yourself

See Resources

This story runs on Resources. The tools and prompts above are the real build — swap any tool for your own equivalent and follow the same steps.

Resources →More success stories

Before anything was set up

Resources, doing its job

The finished system, running on its own

See Resources

Suggested for you