Can you write down how AI agents work in your project so a new agent, or a new teammate, follows the same rules?
- Capstone
- 05/05
- To read
- ~8 min
A team let each engineer run coding agents with their own setup. An agent-written change disabled an auth test to get CI green, and it was approved. What do you think was missing?
In the module you make your guess first, then read what happened and why.
One workflow, in the repository
Five sections, each with a check
Review is a gate, not a glance
Test the workflow, not just the code
Your AI workflow spec
A spec for your own app, as a text file you download. The module also gives you the prompt for Claude Code, Codex or Antigravity, a checklist to check what it built, and recommended skills.
- CI/CD as the gate
- Audit trail