{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicpfb4cvrsckjlidrwgy3s6m6alydvzhhka4iqnjjwkjrpxk2dggy",
    "uri": "at://did:plc:5sgu76a53rz3n6unbykmovqy/app.bsky.feed.post/3mm33gmk6mml2"
  },
  "description": "GitHub Copilot, launched in 2021 and built on OpenAI Codex (later GPT-4), was the first AI pair programmer to reach mainstream adoption. It integrates as an extension into VS Code, JetBrains, Neovim, and Visual Studio, making it the broadest-reaching AI coding tool by editor support.\n\n\nCore Capabilities\n\n * Inline completions, suggests the next line or block as you type, shown as ghost text\n * Copilot Chat, context-aware conversation about your code (explain, refactor, generate tests)\n * Slash c",
  "path": "/engineering-glossary/github-copilot/",
  "publishedAt": "2026-05-17T19:20:50.000Z",
  "site": "https://sahilkapoor.com",
  "tags": [
    "Cursor",
    "Windsurf",
    "Ollama",
    "Vllm",
    "Prompt Engineering",
    "Llm"
  ],
  "textContent": "GitHub Copilot, launched in 2021 and built on OpenAI Codex (later GPT-4), was the first AI pair programmer to reach mainstream adoption. It integrates as an extension into VS Code, JetBrains, Neovim, and Visual Studio, making it the broadest-reaching AI coding tool by editor support.\n\n## Core Capabilities\n\n  * **Inline completions** , suggests the next line or block as you type, shown as ghost text\n  * **Copilot Chat** , context-aware conversation about your code (explain, refactor, generate tests)\n  * **Slash commands** , `/explain`, `/fix`, `/tests`, `/doc` for common tasks\n  * **Workspace context** , Copilot Chat can reference your entire open workspace, not just the current file\n  * **Copilot Edits** , propose changes across multiple files from a single prompt\n  * **Copilot Agent (Coding Agent)** , agentic mode where Copilot autonomously implements GitHub Issues\n\n\n\n## How It Works\n\nCopilot sends your current file, surrounding context, and any chat messages to a hosted LLM (model choice varies by plan, GPT-4o, Claude, Gemini). The response is streamed back and displayed as suggestions. For Copilot Chat, it uses retrieval over your workspace files to find relevant context before calling the model.\n\n## Copilot vs Cursor\n\nCursor offers deeper agentic capabilities and a more opinionated editor experience built from scratch around AI. Copilot's advantage is ecosystem: it works wherever developers already are. For a team that can't switch editors but wants AI assistance, Copilot is the practical choice. For a team willing to adopt a new editor for maximum AI leverage, Cursor or Windsurf offer more.\n\n## Context Window and Privacy\n\nCopilot sends code context to GitHub's servers. For organizations with strict data requirements, Copilot for Business offers options to disable model training on your code. Alternatively, self-hosted options like Ollama or Vllm behind a code-completion proxy keep code on-premises.\n\n## Prompt Engineering for Copilot\n\nCopilot works best when you prime it with context: comments explaining intent, type annotations, and meaningful function/variable names. A well-named function with a docstring will get better completions than an ambiguous one, this is Prompt Engineering applied at the code-as-prompt level.\n\n## Related Terms\n\n  * Cursor, AI-first editor with stronger agent capabilities\n  * Windsurf, alternative AI IDE\n  * Prompt Engineering, the skill that makes Copilot suggestions more accurate\n  * Llm, the underlying technology powering suggestions\n\n",
  "title": "GitHub Copilot",
  "updatedAt": "2026-05-18T20:04:09.543Z"
}