Foundations Module 1 · The AI Landscape

The AI Landscape

What AI CLI tools are, why they matter, and where you're about to go

What you'll learn

~10 min
  • Understand what AI CLI tools are and how they differ from chatbots
  • Learn the describe → build → review loop that drives agentic coding
  • See the three tools you'll master in this course
  • Choose the learning path that fits your experience level

What are AI CLI tools?

You’ve probably used ChatGPT or a similar chatbot — you type a question, it types back an answer. That’s useful, but it’s limited. The AI can only see what you paste into the chat window.

AI CLI tools are different. They run inside your terminal (the text-based interface on your computer) and have access to your actual project files. They can:

  • Read your existing code and documents
  • Create new files and folders
  • Edit multiple files at once
  • Run commands, tests, and builds
  • Fix errors and try again automatically

Instead of copying and pasting code between a browser window and your editor, you describe what you want in plain English, and the AI agent builds it — right there in your project.

Terminal session showing an AI agent building a REST API from a single natural-language command
A typical AI CLI session: you describe what you want, the AI builds it, you review the result.

The core loop: Describe → Build → Review

Every interaction with an AI CLI tool follows the same pattern:

  1. You describe what you want. “Build a login page with email and password fields” or “Fix the test that’s failing in auth.test.ts” — plain English, no special syntax.

  2. The AI builds it. It reads your project, plans the changes, writes code, creates files, and can even run tests to verify its work.

  3. You review and refine. Check what it built. If something’s not right, tell it: “Make the button bigger” or “Add error handling for invalid emails.” The AI iterates until you’re satisfied.

That’s it. Your job isn’t to write code — it’s to think clearly, give good instructions, and verify the results. That’s what this course teaches you to do.

💡This is a skill, not magic

Anyone can type a question into ChatGPT. Directing an AI agent to build real software takes practice — knowing what to ask for, how to break down problems, and when to course-correct. That’s what separates the top 0.002% from everyone else.

The three tools you’ll learn

ToolMakerWhat makes it special
Claude CodeAnthropicDeep codebase understanding, long context, terminal-first
Gemini CLIGoogleOpen source (95K+ stars), generous usage tier, 1M token context
Codex CLIOpenAIAutonomous task execution, agent-first architecture

You don’t need to pick just one. Part of being an effective orchestrator is knowing which tool to reach for and when.

Where you stand right now

Most people haven’t even tried AI yet. The people who can direct AI agents to build things? That’s a tiny fraction of the world population:

  • ~84% of people have never used AI at all
  • ~16% have tried it at least once
  • ~0.7% use AI tools regularly
  • ~0.05% use AI coding tools like Copilot
  • ~0.002% use agentic CLI tools — about 200,000 people on Earth
You're closer than you think

If you’re reading this, you’re already curious enough to be in the top fraction. By the end of this course, you’ll be in that 0.002% — the people who don’t just use AI, but direct it to build things.

🔍Explore the full adoption data

Want to see the numbers visualized? Walk through each tier interactively:

2,500 DOTS = 8.1B HUMANS · EACH DOT ≈ 3.2M PEOPLE
1 / 6
8.1B
All humans alive
8.1 billion people on Earth
SPACE / ARROWS

Choose your path

This course is designed for three types of learners. All paths cover the same core material — the difference is pacing and depth.

Or just continue to the next lesson — the curriculum works great read straight through.

KNOWLEDGE CHECK

What makes AI CLI tools different from regular AI chatbots like ChatGPT?