Understand what Codex actually is
This is the conceptual anchor: Codex is not just a chatbot. It sees your files, edits them, runs commands, and can do the same local work you would otherwise do by hand.
A practical map through the Codex Desktop course: what to watch closely, what to skim, and what to do with your own research folders afterward.
The course is broad because Codex is broad. As an economist, your goal is narrower: learn enough of the interface, permissions, skills, Git, and review loop to make your research folders safer and faster.
When the course turns into a web app build, do not worry about memorizing the stack. Watch for the workflow: plan the work, let Codex operate, inspect the diff, and keep only what improves the project.
Open the full course on YouTube →This is the conceptual anchor: Codex is not just a chatbot. It sees your files, edits them, runs commands, and can do the same local work you would otherwise do by hand.
This is the part that makes the tool usable day to day. Pay special attention to context windows, compaction, voice input, permissions, guardrails, and terminal basics.
You do not need to become a software engineer to use project instructions. The important move is to tell Codex what it keeps getting wrong in your research folders.
For economists, skills are the highest-leverage concept in this stretch. Watch enough of plugins and MCPs to know what they are, then slow down when the course turns to skills.
This is what makes agentic coding safe. You do not need to memorize Git commands, but you do need the habit of checkpoints, branches, private repos, and reviewing diffs.
Translate this section into research management: use issues for research backlogs, automations for recurring checks, and cloud delegation only when your data and permissions make sense.
The Creator Carousel build is less directly about economics. Skim it for method: how to plan, let Codex work, review output, and recover when the project gets complex.
Pick an old folder with Stata, Python, R, LaTeX, outputs, and stray notes. Ask Codex to copy it to a backup directory, propose a .gitignore, initialize Git, create a first private GitHub repo, then reorganize on a new branch.
Create a reusable skill that teaches Codex how you run Stata projects: where scripts live, how outputs are checked, what files never belong in Git, and how to compare new results to prior tables.
Connect email through a Claude Connector or Codex plugin, then make a small triage skill for seminar invitations, referee reports, coauthor requests, and RA follow-ups.
After Codex edits your project, ask it to summarize the diff in plain English. Keep the changes that survive scrutiny and roll back the rest. This is the habit that turns fast work into safe work.
The slide deck above is the full public deck I used for the course. The timestamped plan on this page is the economist-specific layer: where to slow down, where to skim, and what exercises to do after watching.