Leanpub Header

Skip to main content

Know Everything, Read Almost Nothing Course

Building a Graph-Routed Second Brain So Your AI Reads 5 Pages, Not 4,000

The instructor has published 100% of this course.Last updated on 2026-10-26

Most AI memory setups make the model read everything. This course teaches you to build a graph-routed second brain with Obsidian, Graphify and ICM, so your AI reads about 5 pages instead of 4,000.

Minimum price

$149

$149

You pay

Author earns

$

Also available for 1 course credit with a Learner Membership

PDF
EPUB
WEB
About

About

About the Course

You start by building a real Obsidian second brain, from scratch or by reshaping the vault you already have: folders that hold up, hub notes, session notes, Zettelkasten notes and the habits that keep a vault alive across years of work, family life and side projects. Then, step by step, you turn that vault into something an AI can navigate: a knowledge graph of how your notes connect, and a simple routing layer that tells the AI where to look first.

Your notes grow faster than any model can read them. A personal vault passes a million words quickly, and past that point, stuffing context into the model makes it less accurate, slower and more expensive.

Know Everything, Read Almost Nothing teaches you to build a system that knows everything but only reads what a question needs. Obsidian is memory, Graphify is connection, and ICM is direction. One rule holds it all together: one home per fact.

What you will learn

  • Organize a plain-markdown Obsidian vault PARA-style, with hub notes, session notes and atomic Zettelkasten notes
  • Treat frontmatter as a contract and lint it with a script
  • Turn your notes into a knowledge graph with Graphify, with every edge tagged EXTRACTED, INFERRED or AMBIGUOUS
  • Find communities, god nodes and surprising connections with Leiden clustering
  • Wire graph recall into every prompt, with Graphify queries and with a small AI-free call.py of your own
  • Use ICM (Interpretable Context Methodology) so the folder structure itself becomes the instructions
  • Cut what your AI reads from thousands of pages to about five, with answers you can trace back to notes

Who it is for

  • Developers and technical writers who use LLMs daily and keep losing context between sessions
  • People with large Obsidian or markdown vaults who want an AI to use them reliably
  • Engineers building agent workflows who need cheap, explainable retrieval without a vector database

Prerequisites

  • Comfort with a terminal, basic Python and markdown
  • Obsidian installed, or willingness to install it (free)
  • No machine learning background needed

Instructor

About the Instructor

Joel Bryan Juliano

Hi, I'm Joel.

I am Dutch-Filipino Software Engineer with 20+ years of experience.

And with over 20 years in the game, I’ve seen it all and loved every minute of it.

My journey has taken me through a variety of industries, from sports streaming to cybersecurity, both in the private sector and for the Dutch government, and everything in between.

Along the way, I’ve picked up a diverse set of skills and experiences, in which I document into books.

Material

Course Material

  • Introduction

  • Why bother

  • The running vault

  • How to read this book

  • Part I: The Vault

  • A Plain Folder of Markdown

  • The five folders

  • Why plain text beats a database here

  • Git for your vault

  • A minimal Obsidian setup

  • Hands-on: create your vault

  • Chapter 1 Quiz

    3 attempts allowed

  • Projects, Hub Notes and Session Notes

  • The hub note

  • The session note

  • Why Mistakes and Decisions get headings

  • Not only for code

  • Closing a session

  • Hands-on: your first project

  • Chapter 2 Quiz

    3 attempts allowed

  • Resources as a Zettelkasten

  • One idea per note

  • Why small notes stay findable

  • Linking over filing

  • From Inbox to Resources

  • Granularity in practice

  • Hands-on: break up a long document

  • Chapter 3 Quiz

    3 attempts allowed

  • Frontmatter as a Contract

  • The five properties

  • Who reads it

  • Quote values that contain colons

  • Summary: the field that does the most work

  • Linting

  • Hands-on: lint your vault

  • Chapter 4 Quiz

    3 attempts allowed

  • Part II: The Graph

  • Your Vault Is Too Big to Read

  • Three costs of reading everything

  • Retrieval, not reading

  • What this book is not

  • Hands-on: price your own vault

  • Chapter 5 Quiz

    3 attempts allowed

  • Installing Graphify and Turning Notes into Nodes

  • Installing

  • Extracting a vault

  • What a node is

  • How the book’s graph was built

  • How conventions become nodes

  • Hands-on: your first graph

  • Chapter 6 Quiz

    3 attempts allowed

  • Edges You Can Trust

  • The relation vocabulary

  • Confidence tags

  • Measure your own ratio

  • A bad edge, caught

  • Filtering by trust

  • Hands-on: audit your edges

  • Chapter 7 Quiz

    3 attempts allowed

  • Communities and Surprising Connections

  • How Graphify clusters

  • Reading the communities of second-brain

  • God nodes

  • Surprising connections

  • Hands-on: name your communities

  • Chapter 8 Quiz

    3 attempts allowed

  • The Three Outputs

  • graph.json

  • graph.html

  • GRAPH_REPORT.md

  • Keep generated files out of the vault

  • Exports we don’t use

  • Hands-on: compare degree with the report

  • Chapter 9 Quiz

    3 attempts allowed

  • Part III: Retrieval and Routing

  • One Home per Fact

  • Why copies rot

  • The three homes

  • Pointers, not copies

  • Story is allowed to repeat; status is not

  • Drift

  • Hands-on: find the second homes

  • Chapter 10 Quiz

    3 attempts allowed

  • ICM: The Folder Is the Instructions

  • Interpretable Context Methodology

  • The routing table of second-brain

  • What a routing file can hold

  • Letting the assistant read it

  • Testing a routing table

  • Hands-on: write your routing table

  • Chapter 11 Quiz

    3 attempts allowed

  • Cards That Point, Not Tell

  • Anatomy of a card

  • Status: one home, many readers

  • Keep it short on purpose

  • Updating a card

  • Tracing a status question

  • Hands-on: three cards

  • Chapter 12 Quiz

    3 attempts allowed

  • Graph Recall Without AI: graphify query and call.py

  • Graphify’s building blocks

  • call.py

  • Graph query versus call.py

  • Payoffs: status, decisions and front matter

  • Routing first

  • Decisions as nodes

  • What front matter buys

  • Wiring it in

  • What it costs

  • Limits

  • Hands-on: build and compare

  • Chapter 13 Quiz

    3 attempts allowed

  • Part IV: Living With the System

  • Incremental Updates

  • What changes, and how often

  • Graphify’s cache and manifest

  • Watching and hooks

  • When a full rebuild is fine

  • Stale edges after deletions

  • Measuring a full run against an incremental one

  • Hands-on: keep the graph fresh

  • Chapter 14 Quiz

    3 attempts allowed

  • Maintenance and Anti-Patterns

  • The six anti-patterns

  • vault_doctor.py

  • What it found in second-brain

  • The weekly review

  • Archiving and pruning

  • Health metrics

  • Hands-on: build your doctor

  • Chapter 15 Quiz

    3 attempts allowed

  • Putting It Together

  • The whole picture

  • One project, start to finish

  • Measuring the savings

  • Teams

  • Portability across tools and models

  • In the wild: kdeps

  • Hands-on: the complete loop

  • Closing

  • Chapter 16 Quiz

    3 attempts allowed

  • Final Exam

  • Final Exam

    2 attempts allowed

  • Appendix A: Front Matter Schema

  • Appendix B: Hub Note Template

  • Appendix C: Session Note Template

  • Appendix D: Project Card Template

  • Appendix E: ROUTING.md Template

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub