ChatGPT for Developers: Core — Codex in ChatGPT & MCP

Codex for working developers, where it now lives: inside the ChatGPT desktop app as Codex mode, plus the Codex CLI and IDE extension. Learners set up a project, give Codex the right context with AGENTS.md, choose how much it may do without asking, run planned coding tasks on a repository, review diffs and pull requests with discipline, connect tools with MCP, and work in large codebases. Ends with a ticket taken from plan to reviewed change.

What this course covers

The course runs across 10 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.

Getting set up: Codex in the ChatGPT app, the CLI and your IDE — Since July 2026 the Codex app is Codex mode inside the ChatGPT desktop app, next to Chat and Work; the CLI and IDE extension use the same agent and settings. Learners sign in with their work account, open a practice repository as a project, and run a first read-only task such as explaining the repo.
Projects, threads and worktrees: where Codex works — Each folder is a project and each thread can work in its own git worktree, so tasks don't trample each other or your checkout. Learners see the difference between local work on their machine and cloud tasks they can check later, and tidy up worktrees they no longer need.
Giving Codex context: AGENTS.md — Write a short AGENTS.md with build and test commands, conventions and never-do rules, and add a nested AGENTS.md where a package works differently. The file closest to the work applies, a personal file can live in ~/.codex, and untrusted projects don't get to supply instructions.
Approvals and the sandbox: how much Codex may do — Codex works inside a sandbox that limits where it can write and whether it can reach the network, and asks before stepping outside. Learners choose read-only, workspace-only or ask-before-commands setups by what they do, and back every never-do rule with an approval or sandbox limit rather than instructions alone.
Agentic coding tasks with a plan — Ask for a plan with /plan, correct it, then let Codex implement a small feature with tests step by step. Keep each task small and give it a way to check its own work, such as a failing test it must make pass.
Review discipline: diffs, inline edits and pull requests — Read every diff in the review pane, edit it inline or send a follow-up, split out unrelated or risky changes, and use the pull request review panel or /review before merging. Branches and commits are the real undo.
Connecting tools with MCP — Add an MCP server with `codex mcp add` or in ~/.codex/config.toml; the ChatGPT app picks up servers configured for the CLI in trusted projects. Keep tokens in environment variables or an OAuth sign-in, check the tools a server exposes, and prefer read-only access.
Working in large codebases — Ask Codex for a map of the repo before changing it, point it at the right folder, keep AGENTS.md files focused, use /compact when a long thread fills up, and raise or lower reasoning effort with /model to fit the task.
Codex, Chat or Work: picking the right mode — Codex is for repository work, Chat for quick questions and explanations, and Work for business deliverables across apps. Learners sort realistic requests into the right mode and spot jobs that need a teammate's review whichever mode they use.
Capstone: an end-to-end change with review — Take one ticket from plan to reviewed change in Codex on a branch: AGENTS.md in place, a safe approval and sandbox setup, an MCP tool for context, tests passing, and a reviewed diff with nothing risky bundled in.

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 and technical builders. The material is pitched at intermediate level, and takes roughly 180 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: ChatGPT 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 tool 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

All ChatGPT training courses →
ChatGPT: Core — Custom GPTs, Data Analysis & Reasoning — A hands-on working level for experienced ChatGPT users in any role. Build Custom GPTs and Projects, analyze uploaded data, compare reasoning approaches, bring your apps into Work through plugins and @mentions, and run Work tasks with a plan and approvals. No technical background needed; for code and integrations take ChatGPT for Developers.
What's New in ChatGPT for Developers — A short refresher on the latest ChatGPT, Codex and OpenAI API updates for developers
What's New in ChatGPT for Everyone — A short refresher on the latest ChatGPT for Everyone updates
ChatGPT: Advanced — Power Workflows & Automation — The step between everyday fluency and leading work with ChatGPT, without writing code. Learners design multi-step workflows, automate recurring work with Work, plugins, Scheduled tasks, Custom GPTs and Sites, keep long-running tasks on track, and set personal systems that compound over weeks. They finish as the person on the team others come to for ChatGPT technique.
ChatGPT: Essentials — Data & Analysis Playbook — A focused playbook for doing data and analysis work in ChatGPT. Learners run real tasks end to end - data cleanup, analysis, charts, and interpretation - and leave with repeatable workflows they can use the same day. About 45 minutes including the final.
ChatGPT for Developers Pathway — ChatGPT for developers, from coding in chat (Essentials), through Codex in the ChatGPT app and MCP (Core) and agentic engineering with Codex (Advanced), to production-minded OpenAI Responses API agents (Mastery). Also includes 4 optional playbooks (Testing, Code Review, Refactoring & Migration, Docs & Onboarding) 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 180 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-GPT-DEV-201.