The Problem
Years of decision logs, daily journals, and pattern observations. Thousands of entries. The signal is in there, but the volume makes it invisible.
I needed a system that could search semantically, surface patterns I'd never notice, and help me prepare for diagnostic conversations. What I didn't need: a system that draws conclusions or automates judgment.
The Architecture
Everything runs on local infrastructure. No data leaves my network.
What It Does
- Semantic Search Natural language queries across years of logs. Meaning matching, not keyword matching.
- Pattern Surfacing "These three concepts appeared together in four entries this month." Observation without interpretation.
- FM/FFN Analysis Tag and retrieve decisions by pattern type. Familiar Mechanics vs. Familiar-Feeling Novelty.
- Preparation Mode Pull relevant context before diagnostic conversations. Past situations, how they resolved, what I wrote at the time.
What It Doesn't Do
It doesn't summarize my thinking for me. It doesn't recommend actions. It doesn't decide what's important.
Every output is a surface. I decide what it means.
Demo
Why This Matters
The default assumption is that AI should optimize, recommend, and automate decisions. I think that's backwards for a lot of contexts.
Some domains require human judgment to remain human. Diagnosis is one of them. The value isn't in the answer. It's in the process of arriving at one.
Building tools that respect that distinction is the work.