Codex

AI pair programming that edits code from instructions.

Codex is taught here in 12 lessons, running from What Codex is and how to set it up through to Security, cost and team practices. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. What Codex is and how to set it upAn agent that reads your repository and edits files, rather than a completion popup - plus a starting configuration you can trust.
2. Using Codex in a real workflowScope a task so it can be verified, iterate on a branch, and keep the human in the loop at the points that matter.
3. Reviewing output and its limitsThe failure modes that matter, why a passing test suite is not proof, and what an agent should never be trusted to verify about itself.
4. Approval modes and sandboxingRead-only, workspace-write and full-access sandboxes, approval policies from untrusted to never, and how to pair the two without handing over your machine.
5. Writing AGENTS.md project instructionsGenerating a starting file with /init, how global, repository and nested files combine, and which instructions actually change behaviour.
6. Configuration with config.toml and profilesModel and reasoning effort, approval and sandbox defaults, named profiles per workflow, project trust levels, and temporary overrides with -c.
7. Prompting Codex effectivelyDecomposition, precise scope, pointing at the file to copy, asking for a plan before code, and iterating with follow-ups rather than restating.
8. Non-interactive runs and CI automationcodex exec, structured output, sandbox and approval settings for automation, credentials in the environment, and gating a pipeline.
9. Reviewing, applying and reverting changesReading a diff properly, using codex review on uncommitted work, applying output deliberately, keeping commits small, and reverting cleanly when a run goes wrong.
10. Extending Codex with MCP serversRegistering MCP tool servers, scoping their permissions, discovering what they expose, and avoiding the context flooding that comes with too many tools.
11. Debugging and troubleshooting runsVerbose and debug logging, session logs, common install and authentication failures, sandbox denials, and diagnosing a loop that stops making progress.
12. Security, cost and team practicesSecrets in the workspace, network egress, dependency and prompt-injection risk, token spend, review gates, and standards for shared repositories.

More in AI & Intelligent Development

AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow PyTorch Natural Language Processing LangChain Ollama OpenCV Claude Code OpenCode Vibe Coding Selenium Playwright

FAQ