What the AI found
“Your client's observed ferritin dip consistently occurred 12-18 days after specific high-intensity interval training (HIIT) sessions, suggesting a delayed inflammatory response rather than dietary intake.”
Before
Disparate client data, diffuse interventions
After
Targeted, AI-informed client protocols
The same system, three states — real screens, not a screenshot
- Client: J.M. (52), goals: energy, inflammation
- Notes: ferritin fluctuations, unclear pattern
- Observed low ferritin last month, supplemented. Re-test this week.
- Dietary review: adequate iron sources. Exercise: HIIT 3x/week.
Prompt
Analyze the provided anonymized client data (including daily exercise logs, wearable heart rate variability, sleep scores, and weekly blood markers for ferritin and CRP over 8 weeks). Identify any statistically significant lagged correlations (up to 3 weeks delay) between specific exercise types/intensities and subsequent changes in ferritin or CRP levels. Provide specific dates and proposed mechanisms. Emphasize patterns not immediately obvious.
Analyze the provided anonymized client data (including daily exercise logs, wearable heart rate variability, sleep scores, and weekly blood markers for ferritin and CRP over 8 weeks). Identify any statistically significant lagged correlations (up to 3 weeks delay) between specific exercise types/intensities and subsequent changes in ferritin or CRP levels. Provide specific dates and proposed mechanisms. Emphasize patterns not immediately obvious.
AI
Analysis reveals a consistent, significant drop in ferritin (average 18% below baseline) 12-18 days following high-intensity interval training (HIIT) sessions performed on Tuesdays and Fridays. This pattern is less evident after other exercise types. Notably, CRP levels showed a subtle, transient elevation (average 0.7 mg/L increase) 3-5 days post-HIIT, suggesting a delayed, systemic inflammatory response impacting iron metabolism, rather than primary dietary insufficiency. Specific occurrences: 28 May, 4 June, 11 June.98 ng/mL (+22%)
Ferritin (post-protocol)
1.1 mg/L (-35%)
CRP (average)
8/10 (+2 points)
Client Reported Energy
From Scattered Notes to Focused Longevity Protocol
How a practitioner streamlined client interventions with a structured, AI-assisted method.
A 45-year-old functional medicine practitioner, Northern Europe
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
Dr. Anya Sharma faced the common challenge of synthesizing varied client data points – dietary logs, sleep metrics, exercise routines, and blood panels – into actionable, cohesive longevity protocols. Her initial approach involved manual review and cross-referencing, often leading to insights that were either too broad or too time-consuming to uncover. The sheer volume of information made it difficult to pinpoint subtle yet significant patterns influencing client outcomes. Without a structured framework, developing truly personalised and evidence-based interventions felt more like an art than a science.
- Client: J.M. (52), goals: energy, inflammation
- Notes: ferritin fluctuations, unclear pattern
- Observed low ferritin last month, supplemented. Re-test this week.
- Dietary review: adequate iron sources. Exercise: HIIT 3x/week.
- Considering gut health panel next to investigate malabsorption.
Working state
Core Course, doing its job
Anya used the Core Course's 'Ledger' method to standardize data capture across her clients. Once compiled, she fed a client's anonymized, multi-modal data into a large language model. Her prompt specified the data types and asked the AI to look for any lagged correlations between exercise intensity and inflammatory markers, providing a summary and specific timestamps. The AI then analysed weeks of granular data, identifying a recurring pattern that would have been exceptionally difficult to spot manually, providing a clear, actionable insight into the client's inflammatory response dynamics. The Core Course framework ensured the data was structured correctly for this analysis.
Prompt
Analyze the provided anonymized client data (including daily exercise logs, wearable heart rate variability, sleep scores, and weekly blood markers for ferritin and CRP over 8 weeks). Identify any statistically significant lagged correlations (up to 3 weeks delay) between specific exercise types/intensities and subsequent changes in ferritin or CRP levels. Provide specific dates and proposed mechanisms. Emphasize patterns not immediately obvious.
Analyze the provided anonymized client data (including daily exercise logs, wearable heart rate variability, sleep scores, and weekly blood markers for ferritin and CRP over 8 weeks). Identify any statistically significant lagged correlations (up to 3 weeks delay) between specific exercise types/intensities and subsequent changes in ferritin or CRP levels. Provide specific dates and proposed mechanisms. Emphasize patterns not immediately obvious.
AI
Analysis reveals a consistent, significant drop in ferritin (average 18% below baseline) 12-18 days following high-intensity interval training (HIIT) sessions performed on Tuesdays and Fridays. This pattern is less evident after other exercise types. Notably, CRP levels showed a subtle, transient elevation (average 0.7 mg/L increase) 3-5 days post-HIIT, suggesting a delayed, systemic inflammatory response impacting iron metabolism, rather than primary dietary insufficiency. Specific occurrences: 28 May, 4 June, 11 June.Use case implemented
The finished system, running on its own
With the Core Course "Protocol" layer, Anya translated the AI-generated insight into a precise client intervention. Based on the identified delayed inflammatory response post-HIIT, she adjusted the client's recovery schedule and nutrient timing. This new protocol is now systematically applied and tracked, with subsequent data feeding back into the Ledger for ongoing refinement. The implemented system allows for continuous, data-driven optimisation of client longevity plans, moving beyond generic advice to highly individualised, responsive care. The workflow is repeatable and scalable for other clients, ensuring consistent, high-quality interventions.
98 ng/mL (+22%)
Ferritin (post-protocol)
1.1 mg/L (-35%)
CRP (average)
8/10 (+2 points)
Client Reported Energy
What an outside observer would notice
Reduced by 70%
Time to pinpoint root cause
Increased by 45%
Client protocol precision
1.5 hours saved
Weekly client review prep
The stack — build it yourself
Flexible database for consolidating varied client information, from subjective notes to quantified metrics.
Its ability to process complex, multi-modal data and identify non-obvious lagged correlations proved invaluable.
Robust and shareable for creating dynamic, visual dashboards to track client progress against new protocols.
These are the tools used in this story. Any can be swapped for an equivalent you already trust.
Go deeper
Do this yourself
See Core Course
This story runs on Core Course. The tools and prompts above are the real build — swap any tool for your own equivalent and follow the same steps.