Skip to content

Experiment - Day Cluster 4

Enhanced templates improve my Day notes and workflow practices.

I'm doing a tiny experiment using my Day cluster notes in Obsidian: Plan, Log, Journal, Review, Actions, and Links. These are the results of my Day 4 trial for Thursday, Jan 15, 2026 with a brief summary, what went well (Plus), what didn't (Minus), and what can I do (Next).

Summary

Today, I focused on enhancing my Day Cluster templates based on the usage experience throughout this experiment to improve my workflows.

➕ Plus

  • Having a consistent Day workspace layout has helped minimize excess window clutter and focus on my Plan, Log, Journal work.
  • Although it's fairly easy to identify and write any scheduled events into my Plan for the day, automated calendar integration would remove extra manual workflow steps.
  • I returned to using (and improving) my navigational wayfinders because they added a lot of value to my cluster notes; I missed not having them after I briefly thought that might simplify the layout.

➖ Minus

  • I'm still not assigning actions to my session time blocks, especially later in the day, but simplified workflow will help.
  • I've had to go back and recreate some recent changes because I forgot to actually update my templates.
  • I'm still working on minimizing inline actions, but instead using a link strategy to actions for concepts, topics, efforts, outputs, etc.).
  • My Plan workflow has been improving every day, and recently I've been working on improving my Log activities and associated automations.
  • Most Reviews have been done the following morning, and I need to shift more to the end of the day including a Preview Plan.

➡️ Next

  • Continue working on consolidating enhanced templates and ensure consistency across the cluster notes.
  • Refine workflows and identify further automation opportunities.
  • Document Day 5 trial and summarize results from experiment.

Comments

Latest

🕸️ AI Diabetes Coach—Knowledge Graph
PKM

🕸️ 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.

Members Public
PKM

💭 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.

Members Public
🏗️ AI Diabetes Coach — System Architecture
PKM

🏗️ 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.

Members Public