How OpenAI uses Codex

{
  "title": "How OpenAI uses Codex",
  "description": "This document details how OpenAI's technical teams utilize Codex daily to accelerate various engineering tasks. It compiles use cases and best practices, demonstrating how Codex enhances speed, work quality, and complexity management across different teams like Security, Product Engineering, and Infrastructure.",
  "keyPoints": [
    "Codex accelerates code understanding, refactoring, and performance tuning.",
    "It boosts test coverage and increases development velocity for engineers.",
    "Codex aids in staying focused and supports exploration/ideation for solutions.",
    "Best practice: Start with Ask Mode for plans, then use Code Mode for well-scoped tasks.",
    "Best practice: Structure prompts like GitHub Issues, providing detailed context for better results.",
    "Best practice: Utilize AGENTS.md for persistent context and 'Best of N' for diverse solutions."
  ],
  "references": [],
  "tools": [],
  "mermaidMarkdown": "mindmap\n  root((How OpenAI uses Codex))\n    Introduction\n    Use Cases\n      Code understanding\n      Code Modification & Optimization\n      Improving test coverage\n      Increasing development velocity\n      Staying in flow\n      Exploration & ideation\n    Best Practices\n      Start with Ask Mode\n      Improve dev environment\n      Structure prompts like GitHub Issues\n      Use task queue as backlog\n      AGENTS.md for context\n      Leverage Best of N\n    Looking Ahead",
  "url": "https://cdn.openai.com/pdf/6a2631dc-783e-479b-b1a4-af0cfbd38630/how-openai-uses-codex.pdf"
}