Maxime Parmentier maxparm

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

OpenClaw after 50 days: all prompts

Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)

These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.

Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.

My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.

FWIW: I (@rondy) am not the creator of the content shared here, which is an excerpt from Edmond Lau's book. I simply copied and pasted it from another location and saved it as a personal note, before it gained popularity on news.ycombinator.com. Unfortunately, I cannot recall the exact origin of the original source, nor was I able to find the author's name, so I am can't provide the appropriate credits.

Effective Engineer - Notes

By Edmond Lau
Highly Recommended 👍
http://www.theeffectiveengineer.com/

What's an Effective Engineer?

Hello, visitors! If you want an updated version of this styleguide in repo form with tons of real-life examples… check out Trellisheets! https://github.com/trello/trellisheets

Trello CSS Guide

“I perfectly understand our CSS. I never have any issues with cascading rules. I never have to use !important or inline styles. Even though somebody else wrote this bit of CSS, I know exactly how it works and how to extend it. Fixes are easy! I have a hard time breaking our CSS. I know exactly where to put new CSS. We use all of our CSS and it’s pretty small overall. When I delete a template, I know the exact corresponding CSS file and I can delete it all at once. Nothing gets left behind.”

You often hear updog saying stuff like this. Who’s updog? Not much, who is up with you?

The introduction to Reactive Programming you've been missing

(by @andrestaltz)

This tutorial as a series of videos

If you prefer to watch video tutorials with live-coding, then check out this series I recorded with the same contents as in this article: Egghead.io - Introduction to Reactive Programming.

NOTE I now use the conventions detailed in the SUIT framework

Template Components

Used to provide structural templates.

Pattern

t-template-name

	<!doctype html>
	<html>
	<head>
	<script src="//ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
	<script type="text/javascript">
	var spData = null;
	function doData(json) {
	spData = json.feed.entry;
	}