Create a Shopping Agent with Google AI Studio

Lab 1 hour universal_currency_alt No cost show_chart Introductory
info This lab may incorporate AI tools to support your learning.
This content is not yet optimized for mobile devices.
For the best experience, please visit us on a desktop computer using a link sent by email.

GSP1383

Google Cloud self-paced labs

Overview

In this lab, you rapidly prototype a shopping agent in Google AI Studio. You create a Party Planner Shopping Agent for CymbalMart—a retail company—that helps customers plan events and generate shopping lists. Through this hands-on experience, you learn how to translate a Critical User Journey (CUJ) into a functional agent, enhance its features with Vibe Coding and natural language prompts, and validate it across diverse scenarios.

A Critical User Journey (CUJ) is a detailed map of the key steps and interactions customers perform to achieve a specific goal, capturing decision points and outcomes essential to their experience.

For deeper context, consider taking the associated course: Agentic Strategy: Discover, Design, and Prototype.

What you'll learn

In this lab, you learn how to perform the following tasks:

  • Create a shopping agent from a Critical User Journey (CUJ).
  • Enhance and iterate on agent functionality using Vibe Coding and natural language prompts.
  • Test and validate agent behavior across different scenarios.

Setup and requirements

Before you click the Start Lab button

Read these instructions. Labs are timed and you cannot pause them. The timer, which starts when you click Start Lab, shows how long Google Cloud resources are made available to you.

This hands-on lab lets you do the lab activities in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials you use to sign in and access Google Cloud for the duration of the lab.

To complete this lab, you need:

  • Access to a standard internet browser (Chrome browser recommended).
Note: Use an Incognito (recommended) or private browser window to run this lab. This prevents conflicts between your personal account and the student account, which may cause extra charges incurred to your personal account.
  • Time to complete the lab—remember, once you start, you cannot pause a lab.
Note: Use only the student account for this lab. If you use a different Google Cloud account, you may incur charges to that account.

Open Google AI Studio

  1. Click Start Lab. The lab panel will display the temporary credentials for this lab.

    • Note: If this is a paid lab, you will be prompted to select a payment method.
  2. Open Google AI Studio in an Incognito window. The Google sign-in page will appear.

    • Tip: For easier access, arrange the lab and AI Studio tabs in separate, side-by-side windows.
  3. Copy the Username below and paste it into the Email field, then click Next.

    {{{user_0.username | "Username"}}}
  4. Copy the Password below and paste it into the Enter your password field, then click Next.

    {{{user_0.password | "Password"}}}
  5. Accept any on-screen terms and conditions to proceed.

You are now logged into Google AI Studio using your temporary student account.

Task 1. Create a shopping agent from a Critical User Journey (CUJ)

In this task, you create a Party Planner Shopping Agent based on a defined CUJ that helps CymbalMart customers plan parties and generate shopping lists.

  1. Click the Get Started button and then accept the terms and conditions.

  2. In the left navigation menu, click Build.

    To enable Drive access, for Add files (+), click Drive, select your student account (for example, [student-username]), and then grant the necessary permissions.

  3. In the main text prompt bar under "Build your ideas with Gemini", paste the following prompt to create your Party Planner Shopping Agent:

Create a Party Planner Shopping Agent.
  1. Click Build and wait for Google AI Studio to generate the agent.

  2. Review the agent and test it with sample data. Does the agent meet your expectations?

  3. In the Gemini conversation panel, paste the following CUJ prompt, and then click Send prompt to define the Critical User Journey:

Create a party planner shopping agent for CymbalMart based on the following critical user journey (CUJ): User: Busy hosts needing event planning. Goal: Convert intent into a curated, budget-conscious shopping list. Tasks: Define event: Define party type, theme, budget, guest count, and special requests. Review list: Align items with the total budget. Refine & Checkout: Adjust for constraints and finalize plan. Note: A Critical User Journey (CUJ) is a structured description of the key steps a customer takes to accomplish a specific goal. It includes three major components: user (who), goal (what), and tasks (how).
  1. In the Gemini conversation panel, review the generated agent specification to ensure it aligns with the CUJ.

  2. In the Preview pane, test the agent with sample party details:

Note: Since the agent uses AI-generated content, output may vary.
  • Party type: "Birthday"
  • Number of guests: "20"
  • Date: "Next Saturday"
  • Theme: "Tropical"
  1. Verify that the agent generates a relevant shopping list that aligns with the CUJ.

  2. Rename your application. Click the pencil icon beside the app name, change it to CymbalMart Shopping Agent, and click Save.

Click Check my progress to verify the objective. Verify the created shopping agent.

Task 2. Enhance agent functionality with Vibe Coding

In this task, you use Vibe Coding to enhance your Party Planner Shopping Agent with custom features and improved user experience.

  1. Explore the generated code. Click on files like App.tsx in the Code tab to view the main application code and explore how UI elements are constructed.

  2. Enhance the agent's features. In the Gemini conversation panel, paste the following command to add a chatbot to the agent UI:

Add a chatbot called CymbalMart Assistant to interact with customers. Note: If the agent already includes a chatbot, try adding a different feature instead.
  1. Click Send prompt. Observe the changes in the application styling and layout.

  2. Continue enhancing functionality. In the Gemini panel, type the following command:

Enable customers to update the shopping list and automatically recalculate the budget totals. Note: If you are satisfied with this feature, try adding a different one or further refining this capability.
  1. Click Send prompt and observe the new features being added to the UI.

  2. Test the new features in the Preview pane.

Task 3. Test and finalize the agent

Test your Party Planner Shopping Agent across different scenarios and add final enhancements to ensure robust functionality.

  1. In the Preview pane, test the agent with the following scenarios:

    Scenario 1 - Children's Birthday Party:

    • Party type: "Children's Birthday Party"
    • Number of guests: "15"
    • Theme: "Superhero"
    • Verify the shopping list contains age-appropriate items and quantities.

    Scenario 2 - Corporate Team Event:

    • Party type: "Corporate Team Building Event"
    • Number of guests: "50"
    • Theme: "Professional"
    • Verify the list includes corporate-appropriate items and realistic budget estimates.

    Scenario 3 - Outdoor Wedding:

    • Party type: "Wedding Reception"
    • Number of guests: "100"
    • Theme: "Garden/Outdoor"
    • Verify the agent includes outdoor-specific items like weather protection and outdoor seating.
  2. In the Gemini panel, provide feedback to refine the agent as needed.

  3. Add a final enhancement. In the Gemini panel, paste the following prompt to add a voice control feature:

Add a voice control feature that enables customers to complete the entire process hands-free.
  1. Click Send prompt, then allow microphone access in the pop-up window.

  2. Verify your Party Planner Shopping Agent functions correctly with all enhancements.

  3. Navigate to the home page by clicking Back to start, then click the Google AI Studio logo in the top-left corner.

  4. In the left navigation menu, click Build.

  5. Click Your apps > Created by you to view your Party Planner Shopping Agent with all enhancements.

Optional: Deploy your agent To share your agent with others: 1. Click Publish to deploy on Google Cloud (requires a Google Cloud project). 2. Click Code, then download the source code to deploy on other platforms (GitHub, third-party hosting, etc.).

Congratulations!

You've successfully created and enhanced a Party Planner Shopping Agent from a Critical User Journey. You learned how to:

  • Create a shopping agent from a Critical User Journey (CUJ).
  • Enhance and iterate on agent functionality using Vibe Coding and natural language prompts.
  • Test and validate agent behavior across different scenarios.

You're now equipped to build and iterate on your own AI agents in Google AI Studio!

Google Cloud training and certification

...helps you make the most of Google Cloud technologies. Our classes include technical skills and best practices to help you get up to speed quickly and continue your learning journey. We offer fundamental to advanced level training, with on-demand, live, and virtual options to suit your busy schedule. Certifications help you validate and prove your skill and expertise in Google Cloud technologies.

Manual Last Updated April 1, 2026

Lab Last Tested April 1, 2026

Copyright 2026 Google LLC. All rights reserved. Google and the Google logo are trademarks of Google LLC. All other company and product names may be trademarks of the respective companies with which they are associated.

Before you begin

  1. Labs create a Google Cloud project and resources for a fixed time
  2. Labs have a time limit and no pause feature. If you end the lab, you'll have to restart from the beginning.
  3. On the top left of your screen, click Start lab to begin

Use private browsing

  1. Copy the provided Username and Password for the lab
  2. Click Open console in private mode

Sign in to the Console

  1. Sign in using your lab credentials. Using other credentials might cause errors or incur charges.
  2. Accept the terms, and skip the recovery resource page
  3. Don't click End lab unless you've finished the lab or want to restart it, as it will clear your work and remove the project

This content is not currently available

We will notify you via email when it becomes available

Great!

We will contact you via email if it becomes available

One lab at a time

Confirm to end all existing labs and start this one

Use private browsing to run the lab

Using an Incognito or private browser window is the best way to run this lab. This prevents any conflicts between your personal account and the Student account, which may cause extra charges incurred to your personal account.