Three Places for One PKM Vocabulary
I wrote down the 223 concept terms my vault and my tools argue about. Then I had to work out which of my three websites each part of it actually belongs on.
🍴AI Diabetes Coach—Teaching Your AI Coach to Cook
My AI diabetes coach knew my glucose spiked to 204 mg/dL. It just didn't know about the banana bread. Part 6: building a recipe database that connects what I eat to what my glucose does.
🔧 AI Diabetes Coach — Build Your Own
You've read about what's possible. Now it's time to start building. This guide walks through three levels of implementation — from a simple Claude Project to a fully automated system — so you can begin wherever you are today.
🕸️ AI Diabetes Coach—Knowledge Graph
AI could be a genuinely knowledgeable diabetes coach — if only it could remember. Part 4 explores how a knowledge graph gives AI the persistent memory and structured context it needs to become a real health partner, not a brilliant stranger you re-introduce yourself to every time.
💭 AI Diabetes Coach—AI Prompt Engineering
How I went from asking 'Why is my glucose high?' to getting personalized daily coaching that improved my time in range from 82% to 98%. Six iterations of prompt engineering that transformed generic AI into an essential health tool.
📅 The Day Cluster: Multiple Daily Notes That Reduce Friction Instead of Adding It
Most PKM systems use a single daily note. I tried that for years. Everything piled into one file: plans, logs, reflections, glucose data, AI analysis, tasks, links. Finding anything meant scrolling through hundreds of lines...
🏗️ AI Diabetes Coach — System Architecture
In Part 1, you saw 82% → 98% time in range. But how does it work? This reveals the complete system: 5 components that transform raw sensor data into daily AI coaching. Dexcom API to Neo4j to Claude AI. Real examples, $20/month total. Part 2 of 5.
🚀 How I Built an AI Coach that Improved my Diabetes Control from 82% to 98%
Six weeks ago, I was averaging 82% time in glucose range. This week? 98% TIR with five perfect 100% days. Here's how I built an AI-powered PKM system that turns diabetes data into daily coaching.
Experiment - Day Cluster 3
Python services trigger QuickAdd macros to execute Obsidian command workflows.
Experiment: I will use a Day cluster in Obsidian for 5 workdays
Python services integrate PKM knowledge system architecture using Neo4j, Obsidian, and Claude AI.
