---
type: "Article"
title: "Building an LLM-native wiki: the system I use to run workflow, time and projects"
description: "How I turned scattered notes into a single, queryable source of truth, and added a personal knowledge management layer on top to run a small operation."
resource: "https://www.laurelinlabs.com/blog/building-an-llm-native-wiki"
tags: ["llm-native-wiki", "aeo-guardrails-and-agentic-search"]
generated: { by: "laurelin-site-build/2026-08-25", at: "2026-08-25T12:00:00+00:00" }
status: "stable"
stale_after: "2027-02-25T00:00:00+00:00"
---
# Building an LLM-native wiki: the system I use to run workflow, time and projects

Published 2026-06-15, updated 2026-08-25. Author: [Piers Butler](/entities/piers-butler.md).

An LLM-native wiki is a knowledge base written so that a language model can read and reason over it directly: a single structured vault with three layers, raw captures that are never edited, a distilled wiki the model maintains, and a small hot context the model loads on every task. I added a personal knowledge management layer on top to run workflow, time and projects for a small operation, so the same source of truth that answers questions also tracks what is being done. This article is the walkthrough of how it is set up and what it changed.


Hub: [Guardrails, Agentic & Future-proofing](/topics/guardrails-future.md)