AI in Your IDE: A Developer's Guide to GitHub Copilot

As developers, we can no longer dismiss AI as a part of our workflow. It's here for the long haul. While the rapid evolution of generative AI can be daunting, and some may feel it detracts from the learning process, the role of a developer is undeniably changing. The key is not to see AI as a replacement but as a powerful tool for adaptation. Embracing the tools available to us is crucial for staying productive and even enhancing our creativity.

This article explores how AI tools, specifically GitHub Copilot, can aid developers, making us more efficient and innovative.

The Modern AI Tooling Landscape for Developers

There are numerous tools available, each offering unique capabilities:

• Vibe Coding: Tools like Bolt and Lovable offer a more generative, free-flowing coding experience.
• Focused Integration: Solutions such as Copilot and Claude Code integrate directly into a traditional development workflow.
• AI-Driven Editors: Editors like Cursor and Windsurf are built from the ground up with AI features deeply embedded, often resembling VS Code but with enhanced capabilities.

This guide will laser in on the combination of GitHub Copilot and Visual Studio Code, a setup that fits nicely into most existing workflows. We will also briefly touch upon MCP (Model-Connector-Plugin) servers, which enable AI models to communicate with external APIs like GitHub or Supabase.

Getting Started with Copilot and VS Code

To follow along, you'll need to set up your environment.

1. Install Visual Studio Code: If you don't have it already, you can download it from code.visualstudio.com.
2. Install the Copilot Extension: In VS Code, navigate to the Extensions tab and search for "Copilot". Install the main extension, which will also install a companion extension, Copilot Chat. You will have two new extensions in total.
3. Restart and Log In: After restarting VS Code, you should see the Copilot icon in the activity bar and the status bar. You will need a GitHub account to use Copilot, so be sure to log in when prompted.

Understanding Copilot Plans

Copilot offers several tiers to fit different needs.

• Free Plan: Provides access to standard models within Copilot Chat with certain limits on the number of chats and code completions.
• Pro Plan: For a monthly fee, this plan gives you access to more premium models and removes the limits on chats and code completions with the standard models.
• Pro Plus Plan: A higher-tier plan that grants access to the latest models from providers like Anthropic and a larger number of requests using these premium models.

A Note on Premium Requests

The concept of a "premium request" can be confusing. It's calculated using a multiplier system based on the model you use.

Here’s a simplified breakdown of how request multipliers work for different models:

• Free Plan Models: A model on the free plan might have a multiplier of 1x. Each session is considered a single premium request.
• Paid Plan Standard Models (e.g., GPT-4.1): The modifier is often 0x, meaning sessions with this model are unlimited and don't count against a premium request quota.
• Paid Plan Premium Models (e.g., Opus 4): A powerful model might have a 10x modifier. This means five chat sessions with this model would count as 50 premium requests.

This pricing structure and the models themselves are subject to change, so it's always wise to check the official documentation for the latest details.

Choosing the Right Model for the Job

Different models excel at different tasks. It's prudent to select the appropriate one for your needs.

• 04 Mini: Excellent for simple or repetitive tasks.
• Opus 4: The latest from Anthropic, very effective for complex coding problems.
• GPT 4.1: A great general-purpose model.

The best approach is to experiment. Try various models for different tasks to see what best fits your personal workflow.

Advanced Customization: Integrating Open Router

You can also bring your own models to Copilot using services like Open Router. Open Router acts as a model aggregator, allowing you to purchase credits and use them across a vast library of models from Google, Anthropic, OpenAI, and more, all under a single payment plan. When you use your own models via Open Router, Copilot's premium usage limits do not apply.

Here’s how to set it up in just a few steps:

1. Sign up at Open Router and add credits to your account.
2. Create an API Key: Navigate to Settings > API Keys. Click Create Key, give it a name, and set an optional credit limit.
3. Copy the Key: Once created, copy the key to your clipboard. You'll use this inside Copilot.

Navigating the Copilot Chat Interface

With your setup complete, you can start interacting with Copilot.

• Toggle the Chat Window: Click the Copilot icon in the activity bar to open the chat panel. This is where you can ask questions and instruct Copilot to modify your code.
• Select Your Model: At the bottom of the chat window, you'll find a dropdown menu to select the AI model. This list will include the models from your Copilot plan.

To add your Open Router models:

1. Click the model selection dropdown and choose Manage models.
2. From the list of providers, hover over Open Router and click the cog icon that appears. If you don't see the cog, click the option itself.
3. Paste your Open Router API key when prompted. Copilot will now have access to all models provided by Open Router.
4. Go back to the provider list, click on Open Router, and check the boxes for any models you wish to add to your chat dropdown. I've found that Gemini 2.5 Pro is a reliable choice for my workflow.

Now that the basic setup is complete, you are ready to integrate AI into your development process. In a future section, we will explore a vibe coding session with a tool called Bolt before returning to a more focused, traditional workflow within VS Code to see how Copilot can truly accelerate development.