Home / Presentation / Setup Guide
Pre-Workshop

Setup Guide

Complete these steps before May 6th so you can follow along during the live session.

~10 min to complete
Step 1

Install Visual Studio Code

5 min

VS Code is the free, open-source code editor we will use as our primary workspace. It provides the integrated terminal where you will interact with AI agents.

💡
If you already have VS Code installed, skip to Step 2. Just make sure it is up to date.
  1. Download: Go to code.visualstudio.com and download the installer for your operating system (Windows, macOS, or Linux).
  2. Install: Run the installer. Accept the default settings.
  3. Launch: Open VS Code. You should see the Welcome tab.
  4. Open Terminal: Press Ctrl + ` (backtick) to open the integrated terminal. This is where all the magic happens.
✅
Checkpoint: You should see a blinking cursor in a terminal panel at the bottom of VS Code.
Step 2

Install Node.js

5 min

Node.js is the JavaScript runtime that powers the Gemini CLI. You need it installed before you can use npm (the Node Package Manager).

  1. Download: Go to nodejs.org and download the LTS (Long Term Support) version.
  2. Install: Run the installer. Accept all default settings.
  3. Verify: Open your VS Code terminal and run:
Terminal
node --version npm --version
✅
Checkpoint: Both commands should print a version number (e.g., v20.x.x and 10.x.x). If you see an error, restart VS Code and try again.
Step 3

Install Gemini CLI

3 min

The Gemini CLI is Google's command-line AI agent. It turns your terminal into an intelligent workspace that can read files, write code, search the web, and execute multi-step plans.

Terminal
npm install -g @google/gemini-cli

Once installed, verify it works:

Terminal
gemini --version
⚠️
macOS/Linux users: If you see a permissions error, prefix the install command with sudo.
✅
Checkpoint: You should see a version number printed. The Gemini CLI is ready.
Step 4

Authenticate with Google

3 min

The Gemini CLI needs to connect to your Google account to access the Gemini API. This is a one-time setup.

Terminal
gemini
  1. Run the command above. The CLI will prompt you to authenticate.
  2. Sign in: A browser window will open. Sign in with your Google account.
  3. Authorize: Grant the requested permissions.
  4. Return to terminal: The CLI should confirm that authentication is successful.
💡
Alternative: If you have a Gemini API key, you can set it as an environment variable instead: export GEMINI_API_KEY=your_key_here
✅
Checkpoint: You should see the Gemini CLI interactive prompt. Type exit to return to your normal terminal. You are ready for the workshop!

Setup Complete!

You are ready for the live-build. Head over to the lab session to start creating your AI agents.

Start Lab Exercise →