Productivity - Setup Guide

How to set up GitHub Copilot

Otto's honest, no-fluff walkthrough. Every step here is what we'd actually do if we were sitting at your keyboard. Real gotchas first, real steps second, and a link to the personalized version at the bottom.

Read these before you start

• IP indemnification exists on Business and Enterprise (GitHub agrees to defend you if a Copilot completion leads to IP infringement claims), but requires the code-referencing filter to be enabled [source: docs.github.com/en/copilot/managing-copilot/managing-github-copilot-in-your-organization].
• Free tier introduced November 2024 has monthly usage caps that reset; power users hit them fast.
• Copilot Enterprise's knowledge bases and codebase-aware features require GitHub Enterprise Cloud, not the free public GitHub or Team tier.
• Model choice (Claude, GPT-4o, o1, Gemini, etc.) is a 2024/2025 addition; different models have different strengths, and GitHub's model routing is opaque.
• Copilot logs prompts and suggestions for product improvement by default on Individual tier; Business and Enterprise can disable this.

The 7-step setup

1. 1

   Create your GitHub Copilot account

   Sign up at the link below. Card required for the paid tier - most plans include a trial period; check the pricing section on this page first so you know what you're committing to.

   Open GitHub Copilot signup
2. 2

   Complete the initial onboarding

   Skip the marketing questionnaires when you can. Fill only the fields that actually configure the product - name, timezone, your first workspace or project. If GitHub Copilot pushes you into a setup wizard, take it - it usually accelerates the first productive session.

3. 3

   Connect your existing tools

   Wire GitHub Copilot into the rest of your stack. The integrations that most people set up first: VS Code, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand, etc.), Neovim, Visual Studio, Xcode, GitHub.com (chat, PR summaries, Issues), GitHub CLI, GitHub Mobile, Windows Terminal, Azure Data Studio.. Do these before importing data - clean integration first, data second.

4. 4

   Import your existing data (only what you'll actually use)

   Do NOT bulk-import everything. Import the last 30 days of the ONE workflow you're moving over first. Prove it works. Then import more. Big-bang migrations are how GitHub Copilot deployments die in month 3.

5. 5

   Set up your first real workflow

   Pick the single most-frequent task you'll do in GitHub Copilot - the daily-driver workflow. Configure it end-to-end. Use it live for a week. Do not touch any other feature yet. Adoption failure comes from teams trying to use everything on day one instead of the one thing that actually pays.

6. 6

   Add your team (if applicable) and set access

   Once your solo workflow works, invite one teammate at a time. Watch them use it. The friction points you missed are the ones they hit. Fix those before scaling to more users. Never invite 20 people at once - you'll get 20 confused people and 0 useful feedback.

7. 7

   Compound with the right pairings

   Default AI coding assistant recommendation for any developer client, especially those already using GitHub. Recommend Cursor when the developer wants a more aggressive AI-first IDE experience. Recommend Claude Code when the developer wants terminal-native agentic coding (Victor's daily driver). Recommend Cody by Sourcegraph when the client has a large private codebase that needs deep indexing. Copilot is the safe, well-integrated, GitHub-native default.