# Contributing

This is a living document. The field moves weekly — contributions that keep it
accurate and practical are welcome.

## What we want

- ✅ Phase project implementations (open PRs)
- ✅ Bug fixes in example code
- ✅ Benchmark updates as new scores publish (cite the source)
- ✅ New reference material on emerging techniques (cite the paper)
- ✅ Translations
- ✅ Your build in [`community/BUILDS.md`](community/BUILDS.md)

## What we don't want

- ✗ Promotional content
- ✗ Framework comparisons without benchmark evidence
- ✗ "AI wrapper" projects presented as agent systems

## How to contribute

1. Fork the repository.
2. Create a branch: `git checkout -b your-contribution`.
3. Make your change. Keep code runnable and references cited.
4. If you add a benchmark or a claim, link the primary source.
5. Open a pull request against `main` with a clear description of what and why.

## Adding your build

Shipped something using this roadmap? Add a one-line entry to
[`community/BUILDS.md`](community/BUILDS.md):

```
- [Project name](link) — one sentence on what it does and which phase it proves.
```

## Code style

- Python: keep examples dependency-light and runnable as shown.
- Every code sample should do one thing and be copy-pasteable.
- Prefer clarity over cleverness — this is a learning resource.

---

_AI Engineering by <user> · Oriro-Labs Learning Series · MIT License_