Roles: Architect, Author, Reviewer
An agent-assisted workflow has three roles, and the agent only fills one of them:
| Role | Who | Main artifact |
|---|---|---|
| Architect | You | Types, signatures, module boundaries, the spec |
| Author | The agent | Function bodies, boilerplate, first-draft tests |
| Reviewer | You | The verdict, and the next prompt |
Two things fall out of that:
- Design happens before generation, in types. You specify the architecture in structs, enums, function signatures, and trait signatures, and the compiler enforces it while the agent fills in bodies. A review can catch problems in the bodies, but it canât add a design that was never made.
- A review finding is complete when it becomes a prompt. âThis is wrongâ isnât actionable on its own. âThis violates principle P, regenerate with instruction Qâ can actually be acted on. The course teaches each pattern in that form: smell, then principle, then prompt.
Rust is a good fit for this workflow because the architectâs intent gets machine-checked. Put an ownership decision, a state machine, or an error contract into types, and it stops being a convention the agent can drift from. Generated code that ignores it doesnât compile.