OneRange

ChatGPT for Developers: Advanced — Agentic Engineering with Codex

Agentic engineering with Codex for experienced developers: plan long tasks, run parallel threads in worktrees and with subagents, back instructions with hooks and guardrails, share skills and plugins across a team, review pull requests with Codex on GitHub, run Codex headless with codex exec and the official GitHub Action, lock down sandbox and admin policy, and control cost and speed by measuring real runs.

What this course covers

The course runs across 9 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.

  • Planning long tasks before coding — Use /plan so Codex proposes the approach before touching files, and send it back until it's right. For long, measurable work, give acceptance criteria the agent can check and use goal-directed runs where your setup includes them.
  • Parallel work: threads, worktrees and subagents — Run several threads at once, each in its own git worktree, hand slower jobs to cloud tasks, and let Codex split a big task across subagents. Land each result through ordinary git review and clean up worktrees you've finished with.
  • Guardrails that hold: approvals, sandbox and hooks — Back AGENTS.md rules with approval and sandbox settings and with hooks that run at agent events and can block a risky action with a reason. Test every block, because an untested guardrail is only a hope.
  • Skills and plugins for your team — Package team know-how as skills (a folder with a SKILL.md that Codex loads when relevant) and share skills and MCP servers as plugins from a team source. Review what a repo or plugin brings in before you trust it.
  • Codex on GitHub: pull request reviews — Ask for a review by mentioning @codex review on a pull request, or turn on automatic reviews for a repository. Treat the review as one more reviewer: a human still approves and merges.
  • Headless Codex in scripts and CI — Run codex exec non-interactively: read-only by default, workspace-write only for fix jobs, --json for an event stream and --output-schema for a checked final answer. Use the official openai/codex-action in GitHub Actions with the key from the CI secret store, and have the job open a branch or comment for human review instead of pushing.
  • Security and admin policy — Defend against prompt injection from untrusted repos, issues, pull request text and tool output with sandboxing, network limits and review gates. Learn what admins can lock for everyone, from workspace controls in ChatGPT to managed requirements in Codex settings that users can't override.
  • Cost and speed: reasoning effort, context and measurement — Pick the model and reasoning effort per job with /model, keep context lean with focused AGENTS.md files and /compact, and cut wasted turns. Measure usage per task from real runs rather than guessing.
  • Capstone: an automated team workflow — Automate one team workflow end to end with Codex: a plan, guardrails you've tested, a shared skill, a least-privilege CI job and a usage note based on measured runs.

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 advanced level, and takes roughly 150 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, code lab, branching scenario 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: 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: Mastery — Leading Work with ChatGPT — Lead reliable work with ChatGPT in any role using the 4Ds: delegation, description, discernment and diligence. Redesign a workflow, package expertise, supervise Work when it acts, run team tasks within your company's governance, and measure impact and spend without a technical background; code and integrations belong in ChatGPT for Developers.
  • ChatGPT for Developers: Mastery — Building with the OpenAI API — Build reliable OpenAI API integrations with the Responses API, structured outputs, tool calling and the Agents SDK. Compare hosted File Search with custom RAG and ship a tested agent with code-enforced guardrails, evals, cost and rate-limit controls
  • 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
  • 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.

Related

Frequently asked questions

How long does this course take?

It runs roughly 150 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-251.