The guide · setup guide
Your second brain, in depth.
Most people use AI like a search engine with amnesia — ask, answer, close the tab, start from scratch tomorrow. Nothing compounds. This system flips that: the AI builds and maintains a structured wiki from everything you feed it, and every question you ask gets saved back in. Three folders, one schema file, no apps, no code. The dumbest it will ever be is today.
The full setup
🔒 Drop your email to reveal the full setup
Get the full setup, free.
Drop your email and the schema plus all four prompts unlock instantly, plus every other guide and resource in the library. One email a week, unsubscribe anytime.
The architecture: 3 folders
Create one project folder anywhere on your computer. Inside it, create three subfolders:
That's the entire architecture. No apps. No plugins. No database. No code.
- raw/ is your intake shelf. The AI reads from here but never modifies it. This is your source of truth.
- wiki/ is where the AI compiles everything into organised, interlinked pages. You read it. The AI writes it.
- outputs/ is where answers to your questions live. File the good ones back into wiki/ to compound them.
The schema file (CLAUDE.md)
Create a file called CLAUDE.md in the root of your project folder. This is the training manual for your AI librarian. Without it, the AI guesses at what matters. With it, every output is structured exactly how you want. Copy and paste this exactly — just fill in your topic:
What to dump into raw/
Anything you want to stop losing or forgetting. Don't organise it. Don't rename files. Just dump it — that's the AI's job.
- Articles and bookmarks you saved but never re-read
- Meeting notes and call transcripts (Fathom, Fireflies, etc.)
- Screenshots of ideas you want to keep
- Old notes exported from Notion, Apple Notes, Google Docs
- Research papers and PDFs
- YouTube video transcripts
- Your own written ideas and drafts
- Competitor breakdowns and market research
- Personal journal entries and reflections
The fastest way to fill raw/: install the Obsidian Web Clipper Chrome extension. One click on any webpage saves it as a clean markdown file directly into your raw/ folder. Change the default save location in the extension settings from "clippings" to "raw".
The four prompts
Copy these and use them with any AI that can read your files (Claude Code, ChatGPT, Gemini, Cursor).
1. Build your wiki (first time). Run this after you've dumped files into raw/ for the first time.
2. Add new sources (ongoing). Run this every time you add something new to raw/.
3. Ask it anything (ongoing). Use this to query your knowledge base.
4. Monthly health check. Run this once a month to keep your wiki clean and accurate.
What you can build this for
- Content creators — track which topics, hooks, and formats actually perform. Query your own analytics instead of guessing what to post next.
- Business owners — every meeting, decision, and client detail in one place. Ask "what did we agree on across the last 5 calls with this client?" and get an actual answer.
- Researchers — 50 papers synthesised into one wiki. Ask questions across all of them at once instead of re-reading every time.
- Students — build the wiki a textbook never gave you. Add each chapter as you go, build out pages for concepts and how they connect.
- Anyone learning something hard — your knowledge compounds instead of disappearing after the conversation ends.
The compounding loop
Every answer you get from your wiki — save it back in. Drop it into outputs/ or have the AI update the relevant wiki article. The next question builds on the last. The 50th source doesn't just add a page — it updates every related entity, strengthens cross-references, and surfaces patterns you couldn't see in the first 10.
One X user turned 383 scattered files and 100+ meeting transcripts into a compact wiki and dropped their token usage by 95% when querying with Claude. Your wiki isn't a destination you fill up — it's a machine that gets smarter every time you touch it.
Tools that speed this up (optional)
Obsidianfree, from obsidian.md — view your wiki visually with a graph of all the connections between pages. Not required, but makes browsing enjoyable.Obsidian Web Clipperfree Chrome extension — one-click saves any webpage as markdown straight into your raw/ folder.Claude CodeAnthropic's command-line tool with full filesystem access — reads, writes, and updates your wiki files directly, no copy-pasting. The most powerful way to run this.
Half the internet is pitching Obsidian plugins and complex setups for this. You don't need them. A folder of .md files, a good schema file, and an AI that maintains everything — that's the whole system. You could run it from Notepad. Stop shopping for the perfect tool. Start building.
Original guide by Artem Novitckii, based on Andrej Karpathy's LLM knowledge-base system. More from Artem on Instagram, in the Skool community, and across his resource library.