# Examples

These are real applications built only on June's public packages. Read them for patterns you can copy, not toy snippets.

## Applications

### Code Review Agent

A precision-first pull request reviewer that reports only the problems a change introduces, so no findings is a successful review. The fullest example of June's runtime: dependencies, parallel specialists and recovery in one workflow, with a benchmark that measures it.

Uses `june`, `june/train`.

A working CLI with deterministic tests, a precision-first benchmark and real-model runs.

- [Read the guide](https://june.dev/examples/code-review-agent.md)
- [Source: `apps/code-review-agent`](https://github.com/johno/june/tree/main/apps/code-review-agent)

### Copy Agent

A persistent writing agent in a person's own voice. It turns their edits into evidence, evaluates candidates on held-out cases, and changes only when they promote a candidate.

Uses `june`, `june/chat`, `june/copy`, `june/train`.

A working CLI with deterministic tests and a real-model run.

- [Read the guide](https://june.dev/examples/copy-agent.md)
- [Source: `apps/copy-agent`](https://github.com/johno/june/tree/main/apps/copy-agent)

## Which to read

- **Building a workflow?** Read the [Code Review Agent](https://june.dev/examples/code-review-agent.md): one run that plans, fans out to parallel specialists, verifies what they find and recovers from a failed branch.
- **Building a chat with feedback and evals?** Read the [Copy Agent](https://june.dev/examples/copy-agent.md): a conversation whose edits become evidence, and a new candidate that changes nothing until a person promotes it.
- **Just starting?** Write your first workflow with the [Quickstart](https://june.dev/docs/quickstart.md), then come back.

## How a guide is organized

Every guide has the same sections, in the same order, so you can read one application against another:

1. **Problem**: what the person using it needs, and what it does about that.
2. **Architecture**: the parts of the application and how data moves between them.
3. **June modules used**: which June imports it uses, and why.
4. **Execution flow**: the workflow or loop that does the main work, with excerpts from the source.
5. **Using it**: the commands a person runs, in the order they run them.
6. **Testing**: how it's tested without a model, and how it was checked with one.
7. **What stayed in the app**: the decisions that belong to the application, not to June.
8. **Source and related docs**: the code, and the docs pages for each module it uses.

A guide may add a section of its own between these. Code in a guide is an excerpt of a real file, linked to its lines, and the site's build fails if an excerpt stops matching the file.