# AI use cases for Armada (rafmacalaba/armada)

Repo: [rafmacalaba/armada](https://github.com/rafmacalaba/armada) | Use cases: 3 | Page: https://dedupedai.com/use-cases/rafmacalaba-armada/

armada is an npm CLI that scaffolds a team of eight AI specialist agents into a repository and runs contract-driven, evidence-gated feature work in parallel lanes that end in pull requests.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Scaffold an AI engineering team into an existing repo: https://dedupedai.com/use-cases/rafmacalaba-armada/scaffold-ai-team-into-repo/
- Run two features in parallel without clobbering each other: https://dedupedai.com/use-cases/rafmacalaba-armada/run-parallel-feature-voyages/
- Start a new app with an AI team from day one: https://dedupedai.com/use-cases/rafmacalaba-armada/start-new-project-with-ai-team/

## How to scaffold an AI engineering team into an existing repo with Armada

Repo: [rafmacalaba/armada](https://github.com/rafmacalaba/armada) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Run init to detect your stack and set up eight specialist roles with evidence gates.

**Who it is for:** A tech lead whose solo agent keeps making unasked architecture decisions.

**The problem:** Single agents guess, skip verification and forget context.

**The outcome:** A repo with a contract, build, test, review and PR loop scaffolded in place.

### Steps

1. Install with `npm install -g @rafamacalaba/armada`
2. Run `cd your-repo && armada init`
3. Review the scaffolded roles and contracts
4. Start a feature lane

### Prompt to paste into your agent

```text
In <repo>, run `armada init`, list the specialist roles it created, and explain which gate each transition requires. Confirm no source files outside the scaffold changed.
```

### Caveat

It scaffolds files into the repository, so run it on a branch first.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/rafmacalaba-armada/scaffold-ai-team-into-repo/

## How to run two features in parallel without clobbering each other with Armada

Repo: [rafmacalaba/armada](https://github.com/rafmacalaba/armada) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Boot separate lanes per feature and watch them all from a fleet dashboard.

**Who it is for:** A developer who wants an auth feature and a dashboard built at the same time.

**The problem:** Parallel agent tasks collide on the same working tree.

**The outcome:** Isolated feature lanes that each end in a pull request.

### Steps

1. Initialize Armada in the repo
2. Run `armada voyage auth-system`
3. Run `armada voyage dashboard` in parallel
4. Monitor both with `armada fleet`

### Prompt to paste into your agent

```text
Start armada voyages for <feature A> and <feature B>, monitor with `armada fleet`, and report each lane's status. Confirm each produced its own PR without touching the other's files.
```

### Caveat

Phases only run in parallel when they have no dependency on each other.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/rafmacalaba-armada/run-parallel-feature-voyages/

## How to start a new app with an AI team from day one with Armada

Repo: [rafmacalaba/armada](https://github.com/rafmacalaba/armada) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Use Armada new to answer a questionnaire and get a scaffolded project ready to ship.

**Who it is for:** A solo founder starting a fresh app who wants guardrails from the start.

**The problem:** Retrofitting process onto a messy codebase is harder than starting with it.

**The outcome:** A new project with the specialist team and loop already in place.

### Steps

1. Try it with no install via `npx @rafamacalaba/armada@latest new my-app`
2. Answer the questionnaire
3. Run `cd my-app` and start your first voyage
4. Review the first PR

### Prompt to paste into your agent

```text
Run `npx @rafamacalaba/armada@latest new <app name>`, answer the questionnaire for <stack>, and start one voyage. Report the files created and the first PR's checks.
```

### Caveat

Model costs depend on the providers you route to; check prices with the models command first.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/rafmacalaba-armada/start-new-project-with-ai-team/