Most people think they know what AI is.

They've used ChatGPT. They've typed a question, gotten an answer, maybe felt a little impressed, maybe a little underwhelmed. And they've filed it under "useful sometimes" and moved on with their life.

If that's you — good. You're in the right place. Because what you're about to learn has almost nothing to do with what you've experienced so far.

I'm going to share three distinctions with you. They're not complicated. But they will fundamentally change how you think about AI, about the tools we're going to use, and about what's actually possible when you stop chatting with AI and start building with it.

These three ideas are the reason this program exists. Get them, and everything that follows will make sense. Miss them, and you'll spend the next few weeks wondering why we're not just using ChatGPT like everyone else.

Here's What Most People Get Wrong About AI

Let me give you a number that should stop you in your tracks.

Now, ask yourself this: What is happening in the gap between the 88% and the 6%?

Because the 88% are not stupid. They've bought the tools. They've run the pilots. They've sent their people to prompt engineering workshops. And they're still stuck.

The answer is that the 88% are doing the wrong thing with AI. They're chatting with it when they should be building with it. They're optimizing the wrong layer. And they're using tools designed for conversation when they need tools designed for construction.

That's what the three distinctions below are about. Not which AI is "better." Not which tool has more features. But which mode you're operating in — because mode determines everything.

Mode one: the chat interface. ChatGPT, Claude.ai, Gemini — you open a browser, type a question, get a response. This is what 99% of people think AI is. It's useful. It's impressive. And it's the wrong mode for what we're doing.

Mode two: the coding CLI. Claude Code, OpenAI's Codex CLI, Google's Gemini CLI, and others — these tools run on your computer, inside your file system, with access to your actual projects and documents. They don't just answer questions. They read your files, edit your documents, create systems, and build things that persist after the session ends.

Every major AI company has built both. The chat interface is the one they market. The coding CLI is the one that changes how you work.

With a chat interface, you type a question, get a response, close the tab, and tomorrow you start from scratch. Every conversation is a fresh start. There's no memory of what you built yesterday. No ability to save the instructions that worked. No way to hand off what you learned to a system that keeps running without you.

A coding CLI is different. It lives on your machine. It reads your files. It edits your documents. It remembers your project context across sessions. When you build something today, it exists tomorrow. And the day after that. And the day after that.

Imagine you need to get across town every morning. A chat interface is like asking a stranger for directions each day. You get a fine answer. Maybe even a great answer. But tomorrow morning, you're asking again. A coding CLI is like building a road. The first day takes longer. But from then on, you just drive.

One approach is tool-mode: bring a task to the AI, get an answer, leave. The other is infrastructure-mode: build persistent systems that compound over time.

The entire AI industry has been selling you on something called "prompt engineering" — the art of crafting clever instructions to get better answers. And prompt engineering isn't useless. But research from some of the smartest people in AI has broken down where results actually come from:

• 15% comes from which AI model you're using
• 10% comes from the prompt — your clever instructions
• 75% comes from everything else: the context you provide, the architecture around the AI, the system design, the data, the configuration

Most AI training teaches you to optimize the 10%. The prompt. The clever question. And they ignore the 75% that actually determines whether you get real results or just impressive-sounding responses.

This program teaches the 75%.

Let me tell you how I learned this the hard way.

I was a master power user of Evernote. Loved it. Used it for everything. And then I started working seriously with AI and hit a wall almost immediately. I couldn't get my notes out of Evernote and into AI easily. I couldn't get AI's output back into Evernote easily. Every interaction required me to manually drag files in, copy results out, paste them somewhere. The tool I'd relied on for years was suddenly a bottleneck.

So I moved to Notion, hoping it would be better. And it was — a little. Notion had an integration that let AI pull files and work on them directly. But it didn't always work. Sometimes the connection failed. Sometimes files didn't sync correctly. And here's the part that really burned me: when it didn't work, I was dead in the water. There was no copy of my files on my computer. Everything lived in Notion's cloud. If the integration broke, I had nothing to work with.

I stumbled on Obsidian almost by accident. And if I'm being honest, I didn't even like it at first.

But the more I used Obsidian with AI, the more I fell in love with it.

And because those files are plain text on your computer, your coding CLI reads them directly. Your notes, your documents, your project files, your business context — the AI sees all of it, instantly, without any export, conversion, or API. Your vault IS the context.

I think one of the major reasons I'm so far ahead of most people with AI is simply that I stumbled on Obsidian early. It gave my AI long-term permanent memory before anyone else had figured that out.

A researcher named Eva Keiffenheim said we've gotten really good at capturing and organizing information. We've built beautiful digital warehouses. But we're treating these systems like warehouses when we should be treating them like forges.

Google Docs, Notion, Evernote — they're warehouses. You store information there. It sits.

Obsidian — connected to a coding CLI — is a forge. Your knowledge goes in, and the AI transforms it.

The shift is not from one note-taking app to another. It's from storing knowledge to using knowledge.

And it starts with a question most people never ask: Who is the assistant?

Think about how most people use AI right now. They open a chat interface. They need AI to work on a document, so they go find the document, drag it into the chat, wait for the response, copy the output, go put it where it belongs, come back, drag in the next file, repeat.

The AI sits in one place. The human runs all over.

The AI does the thinking. The human does the fetching, the carrying, the filing, the organizing. The human is the assistant to the AI.

Now think about how it works with a coding CLI. You sit at your computer. You tell the AI what you need. The AI goes and grabs the files. It reads them. It works on them. It creates new files, organizes them, puts them where they belong, and tells you when it's done. You bark the orders. The AI does the running.

That's not a small difference. That's a complete inversion of the relationship. In one mode, you serve the AI. In the other, the AI serves you.

Picture two people. Both are using AI. Both are smart. Both work hard.

Person A asks AI for answers. Each interaction is independent. Nothing carries forward. Every day starts from zero.

Person B builds a system that answers. Each session builds on the last. The system gets smarter every time they use it.

Person A's output is linear. Double the time, double the output. Stop working, output stops.

Person B's output compounds. The hundredth session is ten times faster than the first, because the system already knows everything.

Here's a real example. A guy named Alex McFarland spent about an hour building context profiles for his AI system. Then he rebranded his entire business in two days. Fifteen-plus pieces of professional content. Not because he wrote better prompts. Because he built a system that already knew him.

One hour of building replaced weeks of asking for answers.

The 88% are asking for answers. The 6% have built systems that answer.

This program teaches you to build the system.

What This Means for You

I built this system myself. I use it every day. The AI tools you're about to set up are the same ones running in my business right now. This is not theory I read in a book and decided to teach. It's infrastructure I built, tested, broke, rebuilt, and now rely on.

I'm not going to pretend the setup is effortless. There's a learning curve. You'll hit moments where you're frustrated. Here's what I've learned about those moments: you cannot learn unless you push through them. The frustration IS the learning.

A study of 667 people found that working effectively with AI is a separate skill from being good at your job. Years of experience, advanced degrees, deep expertise — none of it predicted who would get the best results from AI.

The difference was not intelligence. It was not domain expertise. It was the skill of building systems that let AI work with what you know.

That's the skill this program teaches.

What Happens Next

Part 2 is where you set up Claude Code on your computer. It's a step-by-step walkthrough — no guesswork, no assumptions about what you already know.

You don't need to be technical. You don't need to have used a terminal before. You don't need any programming experience. If you can follow instructions on a screen, you can do this.

Part 2 is the setup. But Part 1 — what you just read — is why the setup matters. The road, not the directions. The forge, not the warehouse. The system, not the answer.

You're about to install the tool we'll use throughout the rest of this program. This is the single most important setup step. Everything else builds on this.

In Part 1, I talked about the difference between chatting with AI and building with AI. ChatGPT is chatting. Claude Code is building. It lives on your computer. It reads your files. It creates things. It remembers your project from session to session.

Right now, none of that matters. Right now, all that matters is getting it installed and running. Just follow the steps.

What You're Looking At: The Terminal

A terminal is a text-based way to talk to your computer. Instead of clicking icons, you type commands. It looks intimidating. It isn't. You'll type exactly what I tell you to type.

How to open it:

Press Cmd + Space to open Spotlight Search. Type Terminal. Press Enter.

Mac Spotlight search showing Terminal

Click the Start button (or press the Windows key). Type PowerShell. Click "Windows PowerShell" when it appears.

Windows PowerShell search

That blinking cursor is where you'll type commands. When I show you a command in this guide, type it exactly as written and press Enter.

Step 1: Quick Check (Mac Only)

The installer handles everything automatically. This is just a quick check to make sure your system is ready. Windows users — skip to Step 2.

Mac users: In your Terminal, type this and press Enter:

node --version

Copy

If you see a version number (like v20.11.0) — you're good. If you see "command not found" — that's fine. The native installer doesn't require it.

Terminal showing node --version output

If it said "command not found" and you want to install Node.js to future-proof your setup, type this into your terminal. Node.js is a behind-the-scenes tool that some AI plugins and extensions need to run — you won't use it directly, but having it means fewer hiccups later:

brew install node || curl -fsSL https://nodejs.org/install.sh | bash

Copy

Not required — just nice to have. Either way, move on to Step 2.

Step 2: Install Claude Code

Mac:

curl -fsSL https://claude.ai/install.sh | bash

Copy

This downloads the Claude Code installer from Anthropic's website and runs it.

Successful Claude Code installation on Mac

Windows:

irm https://claude.ai/install.ps1 | iex

Copy

Same thing — downloads and runs the installer using PowerShell syntax.

Successful Claude Code installation on Windows

After installation, close your terminal and open a fresh one. Then verify:

claude --version

Claude Code version confirmed

Seeing "command not found: claude"? This is normal. It means you didn't open a fresh terminal after installing. Close your terminal completely (not just the tab — quit the app), open a brand new one, and try claude --version again. The install worked — your old terminal just doesn't know about it yet. If that still doesn't fix it, check the Troubleshooting section at the bottom of this page.

Step 3: Choose Your Plan

Claude Code requires either a Claude subscription or an Anthropic API account.

Option A: Claude Pro or Max Subscription (Recommended)

One monthly subscription covers both Claude on the web AND Claude Code in your terminal.

Option B: Anthropic API (Pay-Per-Use)

Charges based on usage. A typical session costs $0.50–$2.00. If you'll use it regularly (which you will), the Pro subscription is almost always the better deal.

Step 4: Connect Your Account

In your terminal, type:

claude

The first time you run Claude Code, it will walk you through authentication. It will open your browser — log in with your Claude account, approve the connection, and return to your terminal.

Claude Code welcome screen

Step 5: Your First Run — The "It's Working" Moment

Navigate to your Desktop so the file shows up somewhere you can easily find it.

cd ~/Desktop

cd $HOME\Desktop

Start Claude Code (if not already running):

claude

Now type this (replacing "YOUR NAME" with your actual name):

Create a file called test.md with the text "Hello, my name is YOUR NAME. This file was created by Claude Code."

Claude Code creating a file

The file appears on your Desktop

Congratulations. You just had your first building experience with AI. That file is real. It's sitting on your computer. Claude Code didn't just tell you about a file — it MADE one.

Step 6: What NOT to Worry About

• CLAUDE.md files — You'll learn about these in the program.
• Skills and agents — Program content. Not now.
• VS Code or IDE integration — Optional and advanced.
• MCP servers — You don't need to know what this is yet.
• Slash commands — You'll pick these up naturally.

Right now, all that matters is: can you type claude and get a response?

Troubleshooting

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc && source ~/.zshrc

mkdir -p ~/.local/bin
curl -fsSL https://claude.ai/install.sh | bash

Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

Obsidian is where everything you build with Claude will live.

Remember the mental model from Part 1 — plain files on YOUR computer, not someone else's cloud. Every document, every plan, every piece of research Claude creates for you will be a file sitting in a folder on your machine. Obsidian is the app that makes those files easy to read, navigate, and organize.

We're not doing anything complicated today. We're just getting Obsidian installed, creating your workspace, and proving that it connects to Claude Code.

What is a Vault?

A vault is just a folder on your computer. That's it. Obsidian looks at that folder and shows you the files inside as notes. If Obsidian disappeared tomorrow, your files would still be right there in that folder. They're yours.

Step 1: Download Obsidian

Open your web browser and go to: obsidian.md/download

Obsidian download page

Step 2: Install Obsidian

Obsidian welcome screen

Step 3: Create Your Program Vault

Click "Create new vault." You'll see fields for a vault name and location — fill those in using the instructions below, then click Create.

Create vault dialog

Vault name: Something simple — AI-Training, your program name, or whatever makes sense.

Before you choose a location: Do NOT put your vault in any folder that syncs to iCloud, OneDrive, or Dropbox. Cloud sync can corrupt files that Claude creates. That's why we recommend your home folder (Mac) or C:\ (Windows) — these don't sync by default.

Location — THIS PART MATTERS:

Already use Obsidian? Create a SEPARATE vault for this program. Don't mix program files with personal notes.

Step 4: What You're Looking At

Obsidian main interface

Left sidebar: Your file list. Every note shows up here.

Main area: Where you read and write notes. That's all you need to know right now.

Step 5: Create Your First Note

1. Click the New note icon (document with a plus sign), or press Cmd + N (Mac) / Ctrl + N (Windows)
2. Type a title: Hello
3. Type below it: This is my first note in my AI training vault.
4. It saves automatically.

Your first note

Step 6: Find Your Vault Folder

Let's prove that file is real — find it outside Obsidian.

Your vault is just a folder with text files

No database, no proprietary format, no cloud service. Just a folder with text files.

Step 7: The Claude Code Connection

This is where Parts 2 and 3 come together. Navigate to your vault in the terminal:

cd ~/AI-Training

cd ~\AI-Training

Start Claude Code:

claude

Ask Claude to create a note:

Create a note called "Claude Was Here.md" with the message "Your AI assistant is connected and ready to work."

Switch back to Obsidian. You should see "Claude Was Here" in your sidebar.

Claude creates files. You see them in Obsidian. This is how the system works.

Step 8: What is Markdown?

Markdown is a simple way to format text. Use # for headings, ** for bold, - for bullets. You don't need to learn it now. Claude writes in Markdown, and Obsidian displays it beautifully.

Step 9: What NOT to Worry About

• Plugins — We'll add those in Part 4.
• Themes — Cosmetic. Not important now.
• Graph view — Cool but not relevant yet.
• Tags, links, backlinks — Program content.
• Obsidian Sync — Not needed for this.
• Settings — Leave at defaults.

Right now you have two separate tools: Claude Code in your terminal and Obsidian as its own app. That works, but it means switching back and forth between windows constantly.

Before: two separate windows

In this guide, you're going to put Claude Code inside Obsidian. Notes on the left, Claude Code terminals on the right — all in one window.

After: everything in one window

How This Works (30-Second Version)

Obsidian has a plugin system. One plugin, Claude Code MCP, adds terminal panels directly inside the Obsidian window. You type claude in one of those panels, and Claude Code starts up with full access to your vault. That's the whole concept.

1

Enable Community Plugins in Obsidian

▶

Obsidian ships in "safe mode" that blocks third-party plugins. Turn it off:

1. Open Obsidian with your vault from Part 3
2. Click the gear icon (bottom-left) to open Settings

Gear icon in the bottom-left

3. Click Community plugins in the left sidebar

Settings sidebar

4. Click Turn on community plugins

Enable community plugins

You should now see a Browse button.

Browse button visible

2

Install the Claude Code MCP Plugin

▶

1. Click Browse in Community plugins settings
2. Type Claude Code MCP in the search bar

Searching for Claude Code MCP

3. Click on "Claude Code MCP" by iansinnott

Plugin found

4. Click the purple Install button

Click Install

5. Click Enable when it appears

Click Enable

You should see "Claude Code MCP" listed with a purple toggle.

Plugin enabled and ready

Can't find the plugin? See the Alternative Installation section below.

3

Open Your First Terminal Panel

▶

Quick way: Look for the small Claude/Anthropic logo in the bottom-left corner. Click it.

Claude logo toggles the terminal

Other way (Command Palette):

Mac Windows

Press Cmd + P, type terminal, click the open terminal option.

Press Ctrl + P, type terminal, click the open terminal option.

Command Palette

Terminal option in Command Palette

Terminal panel inside Obsidian

4

Start Claude Code in the Terminal Panel

▶

In the terminal panel, type:

claude

Copy

Claude Code inside Obsidian

Now test it:

Create a file called integration-test.md with the text "Claude Code is running inside Obsidian. The integration works."

Copy

Claude asks permission to create the file

File appears in sidebar instantly

File open with Claude's text

5

Add More Terminal Panels

▶

Open another terminal via Command Palette or the Claude logo icon.

Second terminal tab

Option A: Stacked vertically — Drag the tab toward the bottom edge of the existing panel.

Drag toward bottom edge

Two panels stacked vertically

Three panels stacked

Option B: Side by side — Drag toward the right edge instead.

Side by side layout

Tip: Resize panels by hovering over the border between them.

Resize handle between panels

6

Arrange Your Workspace

▶

Goal: notes on the left, terminal panels on the right. Obsidian remembers your layout automatically.

Workspace taking shape

Final workspace layout

7

The "It's All Connected" Moment

▶

Open a note on the left, then type in a terminal on the right:

Read the file integration-test.md and add a second paragraph that says what today's date is

Copy

Note open on the left

Claude processing the instruction

Note updates in real time

8

Set Up Your System Folders

▶

In a Claude Code terminal panel, type:

Create a folder called "00 System" in my vault root with a subfolder called "logs" inside it.

Copy

Creating the 00 System folder

Now clone your program materials:

git clone https://github.com/strategic-profits/connect-the-dots.git "01 Connect the Dots"

Copy

git clone https://github.com/strategic-profits/force-multiplier.git "01 Force Multiplier"

Copy

Select your program on the Welcome page to see the correct command.

Program materials downloading

00 System and 01 Program Name visible

If git clone doesn't work:

• "git: command not found" — Mac: type xcode-select --install and accept the prompt. Windows: download Git from git-scm.com, install it, then restart PowerShell.
• "Repository not found" or "404" — Double-check you selected your program on the Welcome page. If the error persists, email mail@strategicprofits.com.
• Any other error — Take a screenshot and email mail@strategicprofits.com. Don't spend more than 10 minutes on this.

9

Load the Tools for Parts 5-7

▶

Install the skills Claude will need for the next steps:

Install the client profile interview skill and the file discovery skill. Create the skill folders at ~/.claude/skills/client-profile-interview/ and ~/.claude/skills/file-discovery/ and write the SKILL.md files from the grounding package materials in this vault.

Copy

Claude installing the skills

Verify:

List the skills you have installed

Copy

Both skills confirmed installed

Troubleshooting

!

"No terminal option in Command Palette"

▶

Go to Settings > Community plugins. Make sure Claude Code MCP is toggled on.

Check the plugin toggle

!

"Can't drag panels to rearrange"

▶

Click and hold on the tab name, not the content area. Drag slowly and watch for the blue highlight.

Click the tab name to drag

cd ~/AI-Training
claude

cd ~\AI-Training
claude

Alternative Installation: From GitHub

If the plugin isn't in the community browser, install manually:

cd ~/AI-Training/.obsidian/plugins
mkdir -p obsidian-claude-code-mcp
cd obsidian-claude-code-mcp
curl -L -o main.js https://github.com/iansinnott/obsidian-claude-code-mcp/releases/latest/download/main.js
curl -L -o manifest.json https://github.com/iansinnott/obsidian-claude-code-mcp/releases/latest/download/manifest.json
curl -L -o styles.css https://github.com/iansinnott/obsidian-claude-code-mcp/releases/latest/download/styles.css

Copy

Download commands completing on Mac

cd ~\AI-Training\.obsidian\plugins
mkdir obsidian-claude-code-mcp
cd obsidian-claude-code-mcp
Invoke-WebRequest -Uri "https://github.com/iansinnott/obsidian-claude-code-mcp/releases/latest/download/main.js" -OutFile "main.js"
Invoke-WebRequest -Uri "https://github.com/iansinnott/obsidian-claude-code-mcp/releases/latest/download/manifest.json" -OutFile "manifest.json"
Invoke-WebRequest -Uri "https://github.com/iansinnott/obsidian-claude-code-mcp/releases/latest/download/styles.css" -OutFile "styles.css"

Copy

Download commands completing on Windows

Then in Obsidian: Settings > Community plugins > toggle Claude Code MCP on.

Plugin appears after manual installation

This is where Claude gets to know you. Not the surface-level stuff — the real picture of your business, how you work, what you're responsible for, and where AI can make the biggest difference.

Claude will have a conversation with you. Not a form. Not a questionnaire. An actual back-and-forth conversation where it asks smart follow-up questions based on your answers.

What Happens During the Interview

Claude will cover nine areas, roughly in this order:

1. Identity — Your name, business name, what you do
2. Responsibilities — What you're actually responsible for day-to-day (this one matters most)
3. Tools — What software and systems you currently use
4. Team — Who you work with, who reports to you
5. Documents — What types of documents you work with regularly
6. Pain Points — Where you waste time, what frustrates you
7. Communication — How you prefer to work with AI (tone, detail level, etc.)
8. Goals — What you want to get out of this program
9. Future Vision — Where you see your business going with AI

The more specific and honest you are, the better your system will be. Claude uses your answers to design your vault structure, write your CLAUDE.md configuration, and prepare your client dossier for the Strategic Profits team.

How to Run It

Open a Claude Code terminal panel inside Obsidian (from Part 4) and type:

Claude will start the conversation. Just answer naturally. Take your time. If you need to step away, Claude saves progress after each section — you can pick up where you left off.

What Gets Created

• 00 System/CLIENT-PROFILE.md — Your complete profile, organized by category
• 00 System/logs/_interview-progress.md — Auto-saved progress (in case you need to resume)
• Vault structure suggestion — Claude will propose folder organization based on your responsibilities

Tips

• Be specific about your responsibilities — not "marketing" but "I write all email sequences, manage our Facebook ads, and review landing page copy before it goes live"
• Don't worry about being polished. Claude works better with real, messy, honest answers than with carefully crafted ones.
• If Claude asks something you don't have a good answer for, say so. "I don't know yet" is a perfectly valid answer.

Now that Claude knows who you are and what you do, it's time to bring your existing documents into the system. Claude will help you find important files on your computer, convert them to Markdown, and organize them into the vault structure it proposed in Part 5.

What Happens During File Discovery

1. Vault Structure — Claude proposes numbered folders (02+) based on your profile, asks you to approve or adjust
2. Guided Search — Claude scans your common document locations (Desktop, Documents, Downloads) for relevant files
3. Conversion — Found files get converted to Markdown and placed in the right folders
4. Review — Claude shows you each converted file so you can check it looks right before moving on
5. Cloud Files — Claude gives you instructions for downloading files from Google Drive, OneDrive, etc.
6. Completion Report — Summary of everything that was brought in

How to Run It

Claude will walk you through each step. It scans your file system (with your permission), shows you what it found, and asks before moving or converting anything.

What Gets Created

• Custom folders (02, 03, 04...) — Based on your ranked responsibilities
• Converted documents — Your existing files, now in Markdown format inside your vault
• 00 System/VAULT-SUMMARY.md — Complete report of what was converted and where it went
• 00 System/CLAUDE.md — Your personal AI configuration file. This is the file Claude reads at the start of every session so it already knows who you are, what you do, and how you like to work. That's all you need to know for now — we'll go deep on this in the program.
• Pointer file at vault root — A small CLAUDE.md at the top level that points to the full one in 00 System. This way Claude can find your configuration no matter which folder you start in.

Tips

• You don't need to find every file today. Focus on the ones you use regularly.
• Claude can resume where it left off — progress is saved after each responsibility area.
• If you have files in cloud services, Claude will give you download instructions rather than accessing them directly.

Claude has now built a client dossier — a summary of your entire setup, your business context, your vault structure, and what was accomplished during the grounding process. This dossier gets sent to the Strategic Profits team so they know exactly who you are and where you stand before the program starts.

What the Dossier Contains

• Your business profile summary (from the interview)
• Your responsibilities and pain points
• Your vault structure and what documents were organized
• Your CLAUDE.md configuration
• Your goals for the program
• Technical setup status (what tools are installed, what's working)

How to Review It

If the dossier wasn't already generated at the end of Part 6, run this:

Claude will create the dossier and show you its contents. Read through it. If anything is wrong or missing, tell Claude and it will update the dossier.

When you're satisfied, tell Claude to send it:

How you'll know it worked: Claude will confirm the dossier was sent and show you a summary of what was delivered. If you want extra confirmation, email mail@strategicprofits.com and ask them to confirm receipt.

What Happens Next

The Strategic Profits team will review your dossier before the program starts. They'll know your business, your setup, your goals, and your current state. When you walk in (or log in) on Day 1, the team already knows who you are.