1. Overview
Where does building with AI start today? Well for most of us, it often starts with a simple question, "Can I quickly prototype a solution to the problem I have been thinking about?". That's exactly where Google AI Studio comes in. It's a place where you can rapidly prototype anything. In this codelab, we will put together a simple web application using vibe coding, and deploy it onto Cloud Run.
What you'll build
Ready to vibe code a web application and make it available for others to play with??? We'll create a web application and deploy it to Cloud Run, all using just AI Studio. As part of this lab, you will:
- Build a simple web application using vibe coding
- Test the application is working as expected
- Deploy the application on Cloud Run
Requirements
2. Before you begin
- In the Google Cloud Console, on the project selector page, select or create a Google Cloud project.
- Make sure that billing is enabled for your Cloud project. Learn how to check if billing is enabled on a project .
- In case you have the link to redeem credits, you can follow the instructions here to redeem it.
3. Prototype
Go to Google AI Studio. Start typing in your prompt that describes the application you want to build. Here's my prompt:
Create a formal looking frontend application that has two buttons: "Snowflakes" and "Balloons". If the user clicks on the "Snowflakes" button, snowflakes of medium size should start falling on the screen from top to bottom for 5 seconds. If the user clicks on the "Balloons" button, balloons of medium size should start floating from the bottom of the screen and float to the top for 5 seconds.
Choose the model of your choice. Here we are using Gemini 3 Pro Preview. Click on the Build button.
Based on this simple description, AI Studio will build a web application that exactly matches the description that you have provided. It will take 2-3 minutes for the application to be generated.
In case you find any issues with the application, feel free to give additional prompts that correct the application's behavior. For example, increase the size of the snowflake to twice their present size.
See the snapshot of the generated application below:

4. Deploy to Cloud Run
Now that the application is ready, let us deploy it to Cloud Run.
- Click on the rocket-like button on the top right corner of the AI Studio page. The button shows "Deploy app" on hovering over it.
- This opens up the pop-up **Deploy app on Google Cloud".

- Click the Select a Cloud Project dropdown.
- Select the project from the dropdown. In case, you are not able to find your project in the dropdown, click on Import project, and select the project from the Import project pane.
- Once you select the project, the project is verified to have the billing enabled. This verification will pass as we have attached the billing account to the project in the initial steps.
- Click the Deploy app button, and wait for the application to be deployed on the Cloud Run.

Note that the Cloud Run service name will be auto-generated.
- The deployment should complete in a couple of minutes, and you get the App URL. Clicking on the URL, you get to see the deployed web application.
5. Clean up
To avoid incurring charges to your Google Cloud account for the resources used in this post, follow these steps:
- In the Google Cloud console, go to the Manage resources page.
- In the project list, select the project that you want to delete, and then click Delete.
- In the dialog, type the project ID, and then click Shut down to delete the project.
6. Congratulations
Congratulations! You have successfully completed vibe-coding an application on AI Studio, and deployed it to Cloud Run!!
AI Studio is an ideal, go-to platform for developing and testing applications, allowing users to immediately visualize their designs in action.
The seamless integration of AI Studio with Cloud Run enables users to effortlessly deploy their applications directly onto Google Cloud. Utilizing Cloud Run grants all the inherent benefits of a serverless environment, abstracting away the complexities and overhead of infrastructure management.