Codex for Developers: Essentials — Your First Week with Codex

The developer starting point for Codex, OpenAI's coding agent. Learners pick where to run it (Codex in the ChatGPT desktop app, the CLI, the IDE extension or the cloud), have it explain an unfamiliar codebase, write prompts with a goal, context, constraints and a 'done when', plan before multi-step work, choose safe permissions, and review every change in the diff before keeping it. They set up a starter AGENTS.md and finish with a fix-and-explain lab.

What this course covers

The course runs across 8 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

Where Codex runs, and picking one to start — Codex runs in the ChatGPT desktop app (choose Codex from the menu), in the terminal with the Codex CLI, in your editor with the IDE extension, in the cloud and on GitHub pull requests. All three local surfaces share one configuration, so learners pick one for the week and can switch later.
Your first session: let Codex explain the codebase — Open a repository on a new branch and ask Codex to map the project, explain an unfamiliar module and list where code and written rules disagree, without editing anything. Then check two of its claims yourself.
Prompts that work: goal, context, constraints, done when — Write prompts with the four parts Codex needs: the goal, the files that matter (mention them with @), the constraints, and how you will know it is done. Match the reasoning effort to the task instead of always using the highest.
Plan first for multi-step work — Use Plan mode (/plan or Shift+Tab) so Codex gathers context and asks questions before it codes. Edit the plan until each step can be checked on its own, then let it build.
Permissions: what Codex may touch and when it asks — The sandbox decides what Codex can read and write; the approval policy decides when it stops to ask. Learners start from the defaults, choose read-only for questions and reviews, allow workspace edits only on a branch, and decide when to say no.
The review loop: diffs, tests and /review — Treat every change like a pull request from a new teammate: read the diff, comment on lines in the app's diff panel or ask for /review, and have Codex run the tests and linters before you keep anything.
A starter AGENTS.md — Create AGENTS.md with /init or by asking Codex, then cut it down to what matters: how to build and test, conventions, do-not rules and how to verify work. Add a rule only after Codex repeats a mistake.
Final: fix and explain — Fix a buggy function against its written policy with Codex, prove the fix with tests, and explain the root cause and one thing Codex got wrong in your own words.

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick.

Who it is for

Software developers new to Codex. The material is pitched at beginner level, and takes roughly 90 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Tool: Codex track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive, including guided lab, branching scenario, code lab exercises. There is no video to sit through and no slide deck to click past.

Understanding is checked with a lab assessment of 5 items, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

Codex for Everyone: Essentials — Data & Reporting Playbook — A focused playbook for turning a messy spreadsheet export into a simple, repeatable report with Codex, without writing code. Learners clean a copy of the file safely, have Codex build a one-page report, check the numbers against the source by hand, and set it up to re-run next week. About 45 minutes including the final.
Codex for Everyone: Essentials — Internal Tools Playbook — A focused playbook for building a small internal tool with Codex in the ChatGPT desktop app, without writing code. Learners pick a sensible first tool, plan it and let Codex build it on fake data, check every result by hand, and finish with a plain run guide plus a clear sense of when a tool needs an engineer. About 45 minutes including the final.
Codex for Developers: Essentials — Code Review Playbook — A focused playbook for code review with Codex. Learners run /review against a base branch, give Codex a team checklist so it reviews the way the team does, triage its findings into fix, push back and ignore, and see how Codex reviews pull requests on GitHub when a company turns it on. They leave knowing Codex speeds up review but a human still owns the merge. About 45 minutes including the final.
Codex for Everyone: Essentials — Prototypes Playbook — A focused playbook for turning an idea into a clickable prototype with Codex, without writing code. Learners go from a short brief to a working mockup on fake data, refine how it looks by describing changes, gather feedback, and write a clean handoff note so an engineer can tell what is real and what is not. About 45 minutes including the final.
Codex for Developers: Essentials — Refactoring & Migration Playbook — A focused playbook for refactoring and migrating code with Codex without breaking behaviour. Learners pin current behaviour with characterisation tests first, use Plan mode to split a migration into small steps they can each verify, and review every diff before moving on. They leave with a safe, repeatable pattern for changes larger than one function. About 45 minutes including the final.
Codex for Developers Pathway — Use Codex as a daily engineering tool, from your first week to automating engineering for a whole team. Also includes 4 optional playbooks to take any time after Essentials; they don't count toward the certificate.

Frequently asked questions

How long does this course take?

It runs roughly 90 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code TUL-CDX-DEV-101.