What the AI found
“Your three lowest energy days each week consistently align with a specific client-facing task – client onboarding calls – where you spend an average of 45 minutes more than usual on 'listening' rather than 'speaking' during those sessions.”
Before
Vague fatigue, inconsistent client focus
After
Actionable energy insights, better client prep
The same system, three states — real screens, not a screenshot
| Monday morning energy | 7/10 |
| Tuesday afternoon energy | 5/10 |
| Wednesday client notes | |
| Thursday energy | 6/10 |
Prompt
Analyze my daily energy scores (1-10) against my calendar entries and brief client session notes for the last two weeks. Identify any recurring patterns where energy dipped significantly, especially correlating with specific types of tasks or client interactions. Focus on identifying non-obvious links.
Analyze my daily energy scores (1-10) against my calendar entries and brief client session notes for the last two weeks. Identify any recurring patterns where energy dipped significantly, especially correlating with specific types of tasks or client interactions. Focus on identifying non-obvious links.
AI
Your three lowest energy days each week consistently align with a specific client-facing task – client onboarding calls. During these sessions, your notes indicate you spend an average of 45 minutes more than usual on 'listening' rather than 'speaking', compared to follow-up calls. This prolonged, active listening appears to be a significant energy drain.5.2/10
Avg. Energy Post-Onboarding
78%
Listening Time (Onboarding)
+20%
Proactive Schedule Adjustments
From Hunch to Habit: AI Reveals Hidden Energy Drain
A nutritionist moves from vague energy complaints to data-driven insights with a tailored AI system.
A nutritionist running a small Northern 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
Our nutritionist found her energy levels often unpredictable, leading to inconsistent focus during client sessions. She suspected various factors but lacked a clear, objective understanding. Her data was scattered across calendars, basic logs, and anecdotal notes, making patterns impossible to discern without extensive manual review.
| Monday morning energy | 7/10 |
| Tuesday afternoon energy | 5/10 |
| Wednesday client notes | |
| Thursday energy | 6/10 |
| Friday client prep |
Working state
Setup, doing its job
Using a simple prompt in Gemini, she directed the AI to analyse a week's worth of calendar data, client notes, and self-reported energy scores. The AI quickly cross-referenced her subjective feelings with objective time-on-task data for specific activities, looking for surprising correlations.
Prompt
Analyze my daily energy scores (1-10) against my calendar entries and brief client session notes for the last two weeks. Identify any recurring patterns where energy dipped significantly, especially correlating with specific types of tasks or client interactions. Focus on identifying non-obvious links.
Analyze my daily energy scores (1-10) against my calendar entries and brief client session notes for the last two weeks. Identify any recurring patterns where energy dipped significantly, especially correlating with specific types of tasks or client interactions. Focus on identifying non-obvious links.
AI
Your three lowest energy days each week consistently align with a specific client-facing task – client onboarding calls. During these sessions, your notes indicate you spend an average of 45 minutes more than usual on 'listening' rather than 'speaking', compared to follow-up calls. This prolonged, active listening appears to be a significant energy drain.Use case implemented
The finished system, running on its own
With the AI now set up to provide a weekly summary, she receives clear, actionable insights into her energy patterns. This allows her to proactively adjust her schedule and client preparation, ensuring she brings her best self to every appointment without relying on guesswork.
5.2/10
Avg. Energy Post-Onboarding
78%
Listening Time (Onboarding)
+20%
Proactive Schedule Adjustments
What an outside observer would notice
from 6/10 to 7.5/10 avg.
Reduced post-onboarding fatigue
Observed +15%
Improved client session focus
Increased by 10%
Scheduling efficiency
The stack — build it yourself
Chosen for its ability to quickly process natural language queries across structured and unstructured data, ideal for spotting non-obvious patterns.
Ubiquitous, easy to log events and approximate time-on-task, providing a reliable source for activity data.
Simple, flexible for manual energy score entry, and easily exportable for AI analysis.
Free, integrates seamlessly with Google products, offering clear, customisable dashboards for ongoing monitoring.
These are the tools used in this story. Any can be swapped for an equivalent you already trust.
Go deeper
Do this yourself
Discover your hidden energy patterns
This story runs on Setup. The tools and prompts above are the real build — swap any tool for your own equivalent and follow the same steps.