Setup: Install Your AI Coding Assistant

Before you can generate code from your API design, you need the right tools. In this chapter, you'll install an AI-powered code editor that can transform your OpenAPI specification into a working API.

This takes about 15 minutes. By the end, you'll have a professional development environment ready to go.

Choosing Your AI Assistant

You have two excellent options, and honestly, you can't go wrong with either. The main difference is pricing.

Cursor is what most professional developers use. It has the most polished experience, particularly its "Composer" mode which can generate entire projects from scratch. You get a free trial period (usually 2 weeks), then it's $20/month. If you're serious about development, it's worth it.

Windsurf is completely free and offers similar capabilities through its "Cascade" mode. It's built by Codeium, a well-established company in the AI coding space. The experience is nearly as good as Cursor, and it's free.

Recommendation: start with Windsurf. If you find yourself coding a lot and want the absolute best experience, switch to Cursor later. You can always change your mind.

Installing Windsurf (Free Option)

Step 1: Download

Go to codeium.com/windsurf and click the download button for your operating system. The installer is about 100MB.

Step 2: Install

macOS: Open the downloaded .dmg file and drag Windsurf to your Applications folder

Windows: Run the installer and follow the prompts (it's straightforward)

Linux: Extract the archive and run the install script

Step 3: First Launch

Open Windsurf. You'll see a welcome screen asking you to create a free account. Use your email or sign in with GitHub/Google. This takes about 30 seconds.

Step 4: Quick Settings

The default settings work fine, but if you want to customize:

Theme: Click the gear icon → Theme → pick your preference

Font size: Settings → Editor → Font Size (we recommend 14)

Auto-save: Settings → Files → Auto Save → set to "afterDelay"

That's it. Windsurf is ready.

Installing Cursor (Paid Option)

Step 1: Download

Visit cursor.sh and download the installer for your system. It's about 150MB.

Step 2: Install

macOS: Open the .dmg and drag to Applications

Windows: Run the .exe installer

Linux: Use the provided AppImage or .deb package

Step 3: Start Your Trial

Launch Cursor and create an account. You'll get a free trial period (check their website for current offer, usually 2 weeks). No credit card required for the trial.

Step 4: Configure

Cursor works great out of the box, but here are some useful tweaks:

Enable Composer: Settings → Features → Composer (should be on by default)

Set your preferred model: Settings → Models → choose GPT-4 or Claude (Claude Sonnet 3.5 is excellent)

Privacy: Settings → Privacy → decide if you want to share anonymous usage data

You're ready to go.

Verifying Your Installation

Let's make sure everything works. This is the same for both Cursor and Windsurf.

Create a test project:

Open your AI editor

Click "Open Folder" or File → Open Folder

Create a new folder somewhere (like Desktop/api-test)

Select that folder

Test the AI assistant:

Press Cmd+L (Mac) or Ctrl+L (Windows/Linux) to open the chat panel

Type: "Create a simple hello world Python script"

Press Enter

You should see the AI generate a Python script. If it does, everything is working perfectly. If not, check that:

You're connected to the internet

You're logged into your account

The AI panel is actually open (check the sidebar)

For Cursor users - test Composer:

Press Cmd+I (Mac) or Ctrl+I (Windows/Linux)

This opens Composer mode

Type: "Create a basic FastAPI project structure"

Watch it generate multiple files

For Windsurf users - test Cascade:

Click the Cascade icon in the sidebar (looks like a waterfall)

Type: "Create a basic FastAPI project structure"

It should generate multiple files

If you can generate code, you're all set.

Installing Python

You'll need Python to actually run the API code that gets generated. Here's the quickest way to get it installed.

Check if you already have it:

Open your terminal (Terminal on Mac/Linux, PowerShell on Windows) and type:

If you see something like "Python 3.10.x" or higher, you're good. Skip to the next section.

If you don't have Python 3.10+:

macOS:
The easiest way is with Homebrew. If you don't have Homebrew, install it first:

Then install Python:

Windows:

Go to python.org/downloads

Download Python 3.11 or 3.12

Run the installer

Important: Check "Add Python to PATH" during installation

Linux (Ubuntu/Debian):

Verify installation:

Both commands should work and show version numbers.

Understanding Your New Tools

Now that everything is installed, here's what you actually have:

Your AI coding assistant (Cursor or Windsurf) is a code editor with AI built in. Think of it as VS Code, but the AI can see your entire project, understand context, and generate or modify code across multiple files at once. It's not just autocomplete.

When you feed it your OpenAPI specification and ask it to build an API, it understands:

The structure of a web API project

How to set up routing based on your endpoints

What libraries to use for authentication, validation, etc.

How to connect to databases

Common patterns and best practices

The quality is surprisingly good. It won't be perfect, but it'll give you working code that you can understand, test, and modify.

Python is the programming language we'll use. If you've never written Python before, don't worry. The AI writes the code, and Python is one of the more readable languages. You'll pick it up as you go.

First Experience Tips

Start small. When you first use the AI, don't try to generate your entire API at once. Ask it to explain something simple first. Get comfortable with how it works.

Ask questions. If the AI generates code you don't understand, ask it to explain. "What does this function do?" or "Why do we need this library?" It's surprisingly good at teaching.

Don't trust it blindly. The AI makes mistakes. Always test the code it generates. That's why we have Apidog - to verify everything actually works.

Iterate. If you don't like something it generated, ask it to change it. "Make this simpler" or "Add error handling here" works well.

Save your work. Both editors have auto-save, but get in the habit of using version control (we'll cover this later).

What's Next

You now have:

✓ AI coding assistant installed and working

✓ Python installed and verified

✓ Basic understanding of how these tools work

Next up, you'll export your API design from Apidog and generate your first complete project. This is where it gets exciting.

Continue with → Quick Start: Generate Your API in 30 Minutes

Setup: Install Your AI Coding Assistant

Choosing Your AI Assistant#

Installing Windsurf (Free Option)#

Installing Cursor (Paid Option)#

Verifying Your Installation#

Installing Python#

Understanding Your New Tools#

First Experience Tips#

What's Next#