What this is
Tool focus: OpenAI Codex
Hands-on training on OpenAI Codex for repo-aware agent work: bounded scope, review gates, eval suites and Microsoft 365 guardrails.
OpenAI CodexOpenAI Codex trainingWhere Codex fits
Codex agent training without the churn
Codex is a repo-aware coding agent. Used well it ships real diffs; used poorly it creates churn.
Codex review gate · access graduates from read-only to merge.
Where Codex fits
Multi-file refactors, migrations, internal tools and tight feature work where the diff and tests are the deliverable.
Bounded scope by default
Read-only first, then a working branch with explicit gates. Each run gets a small task and clear context.
Review gates that hold
Change-category checklists, tests before merge, and PR templates that make the diff the artefact under review.
How an engagement runs
Day 0
Read-only review
Repository, current AI use, and CI shape are mapped. We agree the first three Codex-suited tasks and the review gates for them.
Day 1
Workflow design
Workflow, prompt patterns, tool short list, scope boundaries and review checklist.
Day 2
On the real repo
Real Codex runs on agreed tasks. Diffs are reviewed, tests run, and branches merge or roll back by the gate.
Common questions
Is Codex safe to point at a private repository?
Yes, with named scope and access boundaries. The training treats access as a graduated thing: read-only first, then a working branch, then merge with a review gate. The repository is never handed over wholesale.
How is this different from a Copilot rollout?
Copilot lives inside an editor and helps with line-level work. Codex is a repo-level agent that does multi-file changes, often without a human at every keystroke. The discipline around review and scope matters more.
What does the team take away?
A written workflow, a tool short list, a review checklist tied to change categories, and a small codebase-specific eval suite. The eval suite is the highest-value durable artefact.