This course is a 37-lesson, approximately 14-hour program that covers OpenAI’s AI coding agent, Codex, from start to finish.
AI coding tools are now commonplace. However, most users remain at the level of accepting autocomplete suggestions or asking questions in a chat window. Agentic tools like Codex can do much more than that. They can read an entire project, modify multiple files simultaneously, run tests, and find and fix errors on their own. The problem is that they require an equivalent level of control. If you do not know what to allow and what to block, or how to teach the tool your project’s rules, you will end up cleaning up the code it creates afterward.
This course focuses on how to establish that control. In the beginner section, you will learn installation and your first conversations, file editing and session management, and slash commands, while building a foundation in prompt writing. Through hands-on practice, you will internalize three principles: making clear requests, breaking down tasks, and verifying the results.
The intermediate section is where the main content begins. You will configure behavior with config.toml, teach project rules with AGENTS.md, and manage memories with Memories. You will design safety boundaries yourself by combining the sandbox with four types of approval policies. The course then covers thread separation and parallel work, planning mode, connecting MCP servers, and creating custom skills based on SKILL.md.
Finally, after covering web searches and Git automation, VS Code and Cursor integration, and hands-on FastAPI practice, you will examine Codex’s internal protocol, the SQ/EQ queue model. Understanding how the tool works changes how you respond when problems arise.
The entire course follows the process of building a single service called TaskFlow. Rather than learning each feature in isolation, you will experience, in sequence, when and why each one is needed in a real project.