Notes from building a personal LLM-PKM (knowledge management) system in the open — turning a decade of OTT/DRM experience into a structured, AI-assisted wiki, one episode at a time.
Part 1 of 10 · Building LLM-PKM in Public
Starting a public series on building a personal LLM-Wiki out of a decade of OTT and DRM experience. Why AI can summarize but not reflect, and what the system looks like a few weeks in.
Part 2 of 10 · Building LLM-PKM in Public
I used to think feeding articles to AI and letting it fill my wiki counted as building knowledge. Here's how bad sources turned that into a well-organized trash can, and the three-part quality check I built to stop it.
Part 3 of 10 · Building LLM-PKM in Public
Looking for where DRM expertise actually meets the AI agent economy, my first answer was wrong. Here's the retraction, and the one real connection point regulation is already making mandatory.
Part 4 of 10 · Building LLM-PKM in Public
Opening a wiki session, I saw 50,000 tokens already consumed — before touching a single file. A 93 KB development framework had been loading into every session regardless of the task. What I learned about keeping AI context lean.
Part 5 of 10 · Building LLM-PKM in Public
Personal notes, reusable templates, and public writing lived in the same space — and an AI agent had no reliable way to know which rules applied where. Why I split the vault into four explicit layers, and what the separation made visible.
Part 6 of 10 · Building LLM-PKM in Public
Every summary Claude returned seemed obvious — until I realized my own impressions were being shaped by Claude's framing before I'd formed any of my own. What Sofia Quintero's essay helped me see, and how I built a friction step into my ingest workflow.
Part 7 of 10 · Building LLM-PKM in Public
Source trust judgments kept drifting between sessions, so I built a registry to make them persistent. The two-axis framework behind that design, the author-level extension that strengthened it — and the uncomfortable thing I found in the seed data I'd used to populate it.
Part 8 of 10 · Building LLM-PKM in Public
Twelve entries seeded the source registry. Two had real evidence behind them. Ten were AI guesses stored in a file that looked like confirmed facts. How I reconstructed evidence from the ingest history — and what it means when confirmed and unconfirmed data look identical in a system you built to prevent guessing.
Part 9 of 10 · Building LLM-PKM in Public
One source at a time, I reviewed carefully. Seven at once, and by the fifth I was scanning titles and rubber-stamping. How I recognized the browse-and-accept failure mode — and why splitting ingest into three separate stages fixed it.
Part 10 of 10 · Building LLM-PKM in Public
Of 128 wiki pages, I had personally read almost none. When AI builds every connection, the knowledge graph belongs to the AI — it just lives under your name. How I built a weekly review workflow and a Slack safety net to keep my own thinking in the loop.