foreman

# Foreman

Foreman watches the software factory floor with [TypeSafe AI's Jev](https://docs.typesafe.ai/introduction),
placing a fast decision model above slower coding agents.

Give it a ticket, specification, bug report, or any free-form software job. A
[Codex](https://learn.chatgpt.com/docs/developer-commands?surface=cli) or
[OpenCode](https://opencode.ai) worker does the software engineering while Foreman independently
assesses whether the implementation is complete, requirements are satisfied, tests are sufficient,
verification is needed, or human input is required.

```text
                         SOFTWARE FACTORY
         Codex/OpenCode    Codex/OpenCode          Tests
            worker             worker                │
               │                  │                  │
               └──────────────────┼──────────────────┘
                                  │ factory evidence
                                  ▼
                              FOREMAN
                                Jev
                                  │
                                  ▼
                    implementation_complete  .91
                    tests_sufficient         .34
                    requirements_satisfied   .79
                    worker_stuck             .02
                    needs_verification       .82
                    work_off_track           .06
                    agents_md_drift          .01
                    meaningful_progress      .94
                    ready_to_finish          .21
                                  │
                                  ▼
                    continue / steer / stop / retry
                         verify / finish
```

**Generative models work. Foreman watches the work.**

Foreman is an architectural experiment, not a cl