Focus 01
Where Codex fits
Multi-file refactors, migrations, internal tools and tight feature work where the diff and tests are the deliverable.

Codex is a repo-aware coding agent. Used well it ships real diffs; used poorly it creates churn.
What this is
Hands-on training on OpenAI Codex for repo-aware agent work: bounded scope, review gates, eval suites and Microsoft 365 guardrails.
Focus 01
Multi-file refactors, migrations, internal tools and tight feature work where the diff and tests are the deliverable.
Focus 02
Read-only first, then a working branch with explicit gates. Each run gets a small task and clear context.
Focus 03
Change-category checklists, tests before merge, and PR templates that make the diff the artefact under review.
Engagement
Repository, current AI use, and CI shape are mapped. We agree the first three Codex-suited tasks and the review gates for them.
Workflow, prompt patterns, tool short list, scope boundaries and review checklist.
Real Codex runs on agreed tasks. Diffs are reviewed, tests run, and branches merge or roll back by the gate.
Light coaching, eval suite carried forward by the team, written rules of engagement, and a follow-up check-in to confirm the workflow is sticking.
FAQ
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.
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.
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.
Next step
Suited to teams with a working CI pipeline and a real repository, not greenfield experimentation. If you need help on the M365 side too, the IT practice runs in parallel.