Scaffold a project with Mistral Vibe

Use Mistral Vibe ↗ to generate a full project structure from a natural-language description, review every change before Mistral Vibe applies it, and run the result.

• Natural-language scaffolding: describe what you want and Mistral Vibe creates the files
• Step-by-step confirmation: Mistral Vibe splits large tasks into steps and asks for approval
• Full preview: see every file change before it is written to disk

By the end you will have a working project scaffolded entirely from a text prompt.

Time to complete: ~10 minutes

• Mistral Vibe installed and configured. If you have not set it up yet, complete the Install Mistral Vibe and send your first prompt ↗ quickstart first.

Start in a fresh directory so Mistral Vibe generates the project from scratch.

mkdir my-project && cd my-project
vibe

mkdir my-project && cd my-project
vibe

Mistral Vibe starts with an empty context, ready to scaffold a new project.

Give Mistral Vibe a clear description of what you want to build. Be specific about the language, framework, and key features. For example:

Create a Python Flask API with two endpoints: a /health endpoint that returns {"status": "ok"} and a /predict endpoint that accepts a JSON body with a "text" field and returns {"label": "positive", "score": 0.95}. Include a requirements.txt and a README.

Mistral Vibe breaks the request into steps and begins generating files. Before creating or editing any file, Mistral Vibe shows a preview of the changes.

For each step, Mistral Vibe displays:

1. The files it plans to create or modify.
2. The content of each file.
3. A confirmation prompt.

Review the changes and type y to approve, or provide feedback to adjust the output. After each approved step, Mistral Vibe shows the result.

Continue approving steps until the project is complete.

Check that the project was created:

ls -la

ls -la

You should see the files Mistral Vibe generated (for example, app.py, requirements.txt, README.md).

Run the project to confirm it works:

pip install -r requirements.txt
python app.py

pip install -r requirements.txt
python app.py

Test the endpoints:

curl http://localhost:5000/health
curl -X POST http://localhost:5000/predict \
  -H "Content-Type: application/json" \
  -d '{"text": "Mistral is great"}'

curl http://localhost:5000/health
curl -X POST http://localhost:5000/predict \
  -H "Content-Type: application/json" \
  -d '{"text": "Mistral is great"}'

Both endpoints should return valid JSON responses.