GSP1320

Overview

Gemini Enterprise is Google Cloud's premier agentic platform that unlocks enterprise expertise for employees by bringing together Gemini's advanced reasoning, Google-quality search, and multimodal enterprise data, regardless of where it is hosted. It empowers employees to find the right information at the right time by connecting content scattered across an enterprise, generating grounded, personalized answers, and performing tasks through integrated workflow actions. Featuring AI agents that can plan, reason, and execute tasks, Gemini Enterprise assists with information retrieval and summarization, task automation, data analysis, and reporting.

Business use-case

For Cymbal Foods, a food manufacturing and distribution company, Gemini Enterprise offers a solution to their significant data fragmentation and information silo challenges. Currently, Cymbal Foods struggles with inaccurate demand forecasting, leading to food waste and financial losses. This makes it difficult for employees to find information, gain actionable insights, or collaborate effectively. By implementing Gemini Enterprise, Cymbal Foods can connect these disparate data sources. This allows employees, from production managers to data analysts, to search across all systems, retrieve and summarize sales data, customer feedback, and inventory levels, and gain a holistic view of operations.

To accelerate your workflow, the Cymbal Foods - Gemini Enterprise application (cymbal-foods-gemini-enterprise), its Cloud Storage data store (cloud-storage-ds), and the Gemini Enterprise Drive Assets folder in Google Drive are pre-provisioned at lab start. The application is configured with Google Identity (GSUITE), Cymbal Foods branding, and agentic feature toggles. You can connect your Google Workspace data sources (Google Drive and Google Calendar) and immediately explore Gemini Enterprise's agentic features. You also build custom agents with Agent Designer (Workflow Builder), create reusable skills, run Deep Research reports, and perform curated analysis in Gemini Notebook.

Objectives

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

• Verify pre-staged enterprise files in Google Drive, add an event in Google Calendar, and connect Google Drive and Google Calendar data stores to Gemini Enterprise.
• Query Gemini Enterprise agents across connected data stores, build a custom sales assistant agent using Agent Designer (Workflow Builder), and create a reusable skill.
• Generate comprehensive research reports using the Deep Research agent.
• Analyze curated documents and generate multimodal Studio overviews using Gemini Notebook.

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.

How to start your lab and sign in to the Google Cloud console

1. Click the Start Lab button. If you need to pay for the lab, a dialog opens for you to select your payment method. On the right is the Lab setup and access panel with the following:

   • The Open Google Cloud console button
   • The temporary credentials (username and password) that you must use for this lab
   • Other information, if needed, to step through this lab

   Note that the lab timer is located near the top of the page, showing the remaining time.

2. Click Open Google Cloud console (or right-click and select Open Link in Incognito Window if you are running the Chrome browser).

   The lab spins up resources, and then opens another tab that shows the Sign in page.

   Tip: Arrange the tabs in separate windows, side-by-side.

   Note: If you see the Choose an account dialog, click Use Another Account.

3. If necessary, copy the Username below and paste it into the Sign in dialog.

   {{{user_0.username | "Username"}}}

   You can also find the Username in the Lab setup and access panel.

4. Click Next.

5. Copy the Password below and paste it into the Welcome dialog.

   {{{user_0.password | "Password"}}}

   You can also find the Password in the Lab setup and access panel.

6. Click Next.

   Important: You must use the credentials the lab provides you. Do not use your Google Cloud account credentials. Note: Using your own Google Cloud account for this lab may incur extra charges.

7. Click through the subsequent pages:

   • Accept the terms and conditions.
   • Do not add recovery options or two-factor authentication (because this is a temporary account).
   • Do not sign up for free trials.

After a few moments, the Google Cloud console opens in this tab.

Note: To access Google Cloud products and services, click the Navigation menu or type the service or product name in the Search field.

Task 1. Prepare data for Gemini Enterprise and Calendar

In this task, you inspect the sample enterprise documents prepared in Cloud Storage, verify the pre-staged files in your Gemini Enterprise Drive Assets folder in Google Drive, and add a relevant meeting to your Google Calendar to create diverse content for Gemini Enterprise to interact with.

1. From the Google Cloud console Navigation menu (☰), select Cloud Storage > Buckets.

2. Click the name of the Cloud Storage bucket that has been pre-provisioned for you in this lab. The bucket name is your Project ID: .

Note: In Cloud Storage > Buckets, you also see a system-generated Discovery Engine import staging bucket alongside your bucket. Be sure to open the bucket named .

Inside your bucket, three folders are prepared by the startup script:

• gemini-enterprise-drive/: Contains CSV files and images intended for use with your Gemini Enterprise application and custom agents that work directly with these formats.
• notebooklm-drive/: Contains plain text (.txt) versions of key data files, optimized for use with Gemini Notebook.
• gemini-enterprise-cloud-storage/: Contains enterprise operations text files that are already connected and being imported into your pre-provisioned Cloud Storage data store.

Verify pre-staged files in Google Drive

1. In the Incognito window where you logged into the Google Cloud console, open a new browser tab and navigate to Google Drive. Ensure you are logged in with your student account.

2. In My Drive, open the Gemini Enterprise Drive Assets folder that was automatically created and populated for you at lab start.

3. Verify that the folder contains the following four files used by your Gemini Enterprise application:

   • MARKETING_data.csv
   • SALES_data.csv
   • customer_feedback.csv
   • pie_chart_customer_sentiment-png.png

Note: For the purposes of this lab, these files have been pre-staged in Google Drive by the startup script so you do not need to download and upload local files in Incognito mode, though you can also upload files directly from your computer or the gemini-enterprise-drive/ Cloud Storage folder in your own environment.

Add an event to Google Calendar

1. In the same Incognito window, open another new tab and navigate to Google Calendar. Accept or dismiss any pop-up messages.

2. Confirm that you are logged in with your student account by checking the profile icon in the Google Calendar header.

3. In Google Calendar, click Create > Event.

4. In the event creation window that appears:

   • For Title, type Cymbal Foods - Marketing Strategy Meeting.
   • Set a start time that is at least one hour from the current time.
   • (Optional) Add any other relevant details if you wish.

5. Click Save.

Click Check my progress to verify the objective. Add content to Google Drive and Google Calendar.

Task 2. Inspect the Gemini Enterprise application and connect Google Workspace data stores

In a typical enterprise deployment, administrators provision the Gemini Enterprise application, configure workforce identity, enable agentic features, and attach foundational cloud storage repositories before connecting workspace collaboration tools. In this lab environment, Terraform pre-provisions the Cymbal Foods - Gemini Enterprise application (cymbal-foods-gemini-enterprise) in the global location. The application is configured with Google Identity (GSUITE), Cymbal Foods branding, agentic feature toggles (including custom agents, workflows, skills, projects, and canvas), and a pre-connected Cloud Storage data store (cloud-storage-ds).

In this task, you verify the pre-provisioned Gemini Enterprise application and its Cloud Storage data store. You then connect your Google Drive and Google Calendar data stores so Gemini Enterprise can search and reason across all three enterprise repositories.

Verify the pre-provisioned Gemini Enterprise application

1. In the Google Cloud console search bar, type Gemini Enterprise, and then select Gemini Enterprise.

2. On the Gemini Enterprise > Apps page, verify that the Cymbal Foods - Gemini Enterprise (cymbal-foods-gemini-enterprise) application is already created and listed in the global location with Cloud Storage under Connected data stores.

3. Click Cymbal Foods - Gemini Enterprise, and then select Connected data stores from the navigation menu.

4. Verify that the Cloud Storage data store (cloud-storage-ds) is already pre-connected and importing unstructured documents from the gemini-enterprise-cloud-storage/ folder in your Cloud Storage bucket ().

Create a Google Drive data store

1. On the Connected data stores page for Cymbal Foods - Gemini Enterprise, click + New data store.

2. In the Select a data source search bar, type Google Drive, and then on the Google Drive card, click Add data source.

3. On the Specify the Google Drive authentication parameters page, click Continue.

4. Under Select Google Drive actions to enable, select Select all actions and then click Continue.

Note: While Gemini Enterprise makes it easier to find information across your data sources, it does not grant additional access. You only have access to documents shared with you through existing Drive permissions, and others only have access to documents that you share with them.

5. Configure the connector with the following settings, and leave the remaining settings as their defaults:

   Setting	Value	Description
   Multi-region (under Location of your data connector)	global (Global)	Pre-selected to match the global Gemini Enterprise application location.
   Data connector name	Google Drive	Display name for the Google Drive connector.

6. Click Create.

Create a Google Calendar data store

1. On the Connected data stores page, click + New data store.

2. In the Select a data source search bar, type Google Calendar, and then on the Google Calendar card, click Add data source.

3. On the authentication parameters page, click Continue.

4. Under Select Google Calendar actions to enable, select Select all actions and then click Continue.

5. Configure the connector with the following settings, and leave the remaining settings as their defaults:

   Setting	Value	Description
   Multi-region (under Location of your data connector)	global (Global)	Pre-selected to match the global Gemini Enterprise application location.
   Data connector name	Google Calendar	Display name for the Google Calendar connector.

6. Click Create.

7. Confirm that all three data stores (Cloud Storage, Google Drive, and Google Calendar) appear in the Connected data stores panel for Cymbal Foods - Gemini Enterprise.

Behind the scenes, Gemini Enterprise links the Google Drive, Google Calendar, and pre-provisioned Cloud Storage data stores to the cymbal-foods-gemini-enterprise search engine. It enforces per-user Access Control Lists (ACLs) through Google Identity (GSUITE).

Click Check my progress to verify the objective. Connect Google Drive and Google Calendar data stores.

Task 3. Interact with your Gemini Enterprise agents

Now that your Cymbal Foods Gemini Enterprise application is configured and connected to your data, you experience its capabilities firsthand. In this task, you interact directly with agents to search your uploaded documents, extract specific information, and summarize content. This hands-on exploration showcases how Gemini Enterprise transforms information retrieval and task management within an organization.

Note: It may take 5–10 minutes for your data stores to fully index. If you don't see the sources populated on the Gemini Enterprise application, wait a few minutes and try again.

1. From the Gemini Enterprise page, click the Overview tab.

2. Click the URL under Your Gemini Enterprise webapp is ready to open the application. If prompted with a Welcome to Gemini Enterprise! dialog, click Get started. Note that this looks different depending on the data stores used. Your home page should resemble the following:

   

   This home page is designed to give users easy access to the content and events they find most useful. It includes the following sections:

   • Agents: Use Google-provided agents or create your own to help with tasks like research, iterating on ideas, or workflow automation.
   • Gemini Notebook: An AI-powered research and writing assistant that works best with the sources you upload.
   • Deep Research: An agentic feature in Gemini that can automatically browse up to hundreds of websites on your behalf, think through its findings, and create insightful multi-page reports in minutes.
   Note: If your data stores are still indexing, the files may require a little time to become accessible.

3. In the chat box, click Connectors (the puzzle-piece icon in the chat box) to view your available data sources.

4. Next to Drive, click Authorize.

5. Next to Calendar, click Authorize.

6. In the chat box, enter the following prompt:

Give me an update on our latest marketing data.

Your answer should resemble the following:

Note: If no response is received, refresh and submit the query again.

7. In the chat box, enter the following follow-up prompt:

What products were in the March newsletter?

You can use the Gemini Enterprise AI assistant to handle multimodal prompts as well.

8. In the navigation menu, click New chat to start a new chat.

9. In the search bar, click Tools, and select Search company data.

10. Enter the following prompt:

Summarize the customer sentiment pie chart.

The response should resemble the following:

Note: You may need to run the query again if it doesn't find the pie chart image file you uploaded.

11. In the navigation menu, click New chat to start a new chat.

12. Enter the following prompt:

What meetings are on my agenda today? What do I need to have prepped for them?

Observe the response. Since you set up the data stores for your Google Calendar, it knows what events you have, and can assist you in curating the information you need for them!

Build a custom agent with Agent Designer (Workflow Builder)

In this section, you use the visual Agent Designer (also referred to as Workflow Builder in the Gemini Enterprise documentation) to create a custom agent tailored to your enterprise sales data. Agent Designer lets you build both conversational Chat agents and automated multi-step Workflows triggered on a schedule or by workspace events.

1. Click the Google Gemini Enterprise (or Cymbal Foods) logo to return to the homepage.

2. In the navigation menu, click + New agent and select Chat agent.

3. In the What do you want your agent to do? prompt box, enter the following prompt and press ENTER:

Create a Sales Assistant agent that analyzes quarterly transaction data and customer feedback.

4. Once Gemini generates the Sales Assistant agent (Your agent 'Sales Assistant' is ready), review the agent preview panel, which includes Flow, Schedule, and Preview tabs:

5. Select the Flow tab and click the Sales Assistant node to open the Details panel, where you can inspect or customize the agent's Name, Description, Instructions, Model, and connected data sources:

6. Click Create in the agent builder toolbar to publish the agent. When the Agent Created Successfully dialog appears, click Chat with Agent.

7. In the chat bar, enter the following prompt to test your published agent:

Summarize the key takeaways from our Q1 2026 sales records.

8. Inspect the generated analysis.

9. Click the Google Gemini Enterprise (or Cymbal Foods) logo to return to the homepage, and in the navigation menu, click Agents to verify that your published Sales Assistant agent is listed under Your agents.

Tip: In addition to opening an agent from the Agents gallery, you can invoke any published custom agent directly inside a standard chat conversation by typing @Sales Assistant (@-mention) in the chat box.

Create a reusable skill with Gemini

While a custom agent acts as a specialized persona with its own data source bindings, a Skill is a lightweight, reusable instruction package (SKILL.md) that you can invoke on demand in any chat conversation using a / slash command (or @ mention) to enforce brand voice, formatting standards, or repeatable procedures.

1. In the Gemini Enterprise navigation menu, click Skills.

2. On the Add your first skill page, click Create skill with Gemini.

3. In the Describe your skill chat box, enter the following prompt and press ENTER:

Create a Cymbal Brand Voice skill that formats marketing and product summaries into Cymbal Foods' friendly, sustainability-focused executive tone and ends with a three-bullet action plan.

4. Wait a few seconds for Gemini to draft the skill and populate the Name (cymbal-brand-voice), Description, Trigger (/cymbal-brand-voice), and step-by-step Instructions fields in the skill editor panel.

5. Click Save in the skill editor header and confirm that the Skill created successfully. notification appears.

6. In the navigation menu, click New chat, type /cymbal-brand-voice (or /) in the chat input bar to select cymbal-brand-voice from the Skills menu, and then enter the following prompt:

Draft an internal announcement summarizing our Spring Cookie Promotion results.

7. Inspect the response to see how Gemini displays the Skill used (cymbal-brand-voice) badge, loads your brand voice guidelines, searches your connected data stores for the Spring Cookie Promotion (Campaign SPRING25) metrics, and formats the announcement with a three-bullet action plan.

Click Check my progress to verify the objective. Interact with your Gemini Enterprise agents.

Task 4. Use the Deep Research agent

In this section, you use the Deep Research agent to unlock deep insights with AI-driven research, reports, and audio summaries.

1. Click the Google Gemini Enterprise (or Cymbal Foods) logo to return to the homepage.

2. In the navigation menu, select Deep Research.

3. Enter the following prompt:

Research the latest marketing tips and tricks that food companies are using, and generate a list of actionable steps our company can take to improve our current marketing strategy.

The agent generates a research plan for you.

4. Click Start research to begin the task.

Note: Since Cymbal Foods is a fictitious company, the internal data of the current marketing strategy is illustrative. The goal of this task is to demonstrate the capabilities of the Deep Research agent.

This takes a few minutes to complete. You can wait or continue with the remaining tasks in the lab and return later to check the status of the generated report. After 5–10 minutes, your research report completes and displays the following summary and audio overview:

Task 5. Analyze enterprise documents with Gemini Notebook

In the previous tasks, you explored Gemini Enterprise as a comprehensive platform for accessing enterprise information and using specialized AI agents. Now, you explore Gemini Notebook, a tool designed for focused research, deep analysis, and sense-making with specific collections of documents. Gemini Notebook acts as your personal research assistant, allowing you to import chosen sources, ask detailed questions, generate summaries, and synthesize information. All AI responses are grounded directly in the materials you provide.

For Cymbal Foods, an employee might use Gemini Notebook to conduct an in-depth review of specific sales reports alongside customer feedback trends before drafting a new product proposal or marketing strategy. In this task, you create a new notebook, import text versions of your Cymbal Foods data files as sources, and interact with Gemini Notebook to gain insights from this curated collection.

Create a new notebook and add sources

1. In the Gemini Enterprise navigation menu, click Gemini Notebook.

2. On the Welcome to Gemini Notebook screen, click + Create new notebook. This opens a new notebook along with the Add sources dialog:

Note: Gemini Notebook supports uploading files directly from your computer (such as PDFs, text files, Markdown, audio, or images), selecting Google Docs or Google Slides from Google Drive, or pasting copied text. For the purposes of this lab—and to ensure compatibility if your browser policy restricts uploading local files in an Incognito window—you import the source files using their Cloud Storage web URLs.

3. In the Add sources dialog, under Link, click Website.

4. In the Paste URLs field, paste the following three Cloud Storage URLs:

https://storage.googleapis.com/spls/gemini-enterprise/SALES_data.txt https://storage.googleapis.com/spls/gemini-enterprise/customer_feedback.txt https://storage.googleapis.com/spls/gemini-enterprise/MARKETING_data.txt

5. Click Insert.

   Wait a few seconds for Gemini Notebook to import all three sources and generate an automatic title (Sweet Treats: Campaigns, Sales, Feedback) and summary for the notebook:

Query uploaded sources in Gemini Notebook

With your Cymbal Foods data loaded into the notebook, you can now ask targeted questions and explore the content.

1. Observe the Gemini Notebook interface, which displays your added sources, the main chat panel, and a Studio section for your notes and multimodal artifacts.

2. In the chat input bar, type your questions. Gemini Notebook generates answers based only on the content of the documents you added to this specific notebook. Try the following prompts:

   • Query 1:

What audience did the Spring Cookie Promotion target?

• Query 2:

Summarize the key themes from the customer_feedback.txt regarding products that had sales figures reported in Q1 2026 in the SALES_data.txt.

• Query 3:

Are there any marketing campaigns in MARKETING_data.txt that correspond to products with significant customer feedback or notable sales trends from the other documents?

• Query 4 (General inquiry about a single document):

What are the top 3 most frequently mentioned positive aspects in the customer_feedback.txt?

Notice how Gemini Notebook formulates its answers, drawing information directly from your imported text files. Many grounded AI tools, including Gemini Notebook, provide citations or highlight the source text used to generate an answer. These citations help you verify the information and refer back to the original context in your documents. Gemini Notebook is designed for iterative exploration, allowing you to ask follow-up questions to dive deeper into specific points.

It is different from the broader Gemini Enterprise search (which queries across all connected data) or a specialized custom agent (which operates based on its specific programmed instructions). Gemini Notebook offers a flexible environment for any collection of sources you want to study closely.

A key feature of Gemini Notebook is often the ability to save AI responses, key passages from sources, or your own thoughts as "notes" within the notebook. This helps you build a structured understanding and gather material for reports or further work.

Generate an Audio Overview and explore Studio features

Beyond textual summaries and Q&A, Gemini Notebook offers innovative ways to synthesize information from your sources through the two-column Studio panel. The panel includes Audio Overview, Slide Deck, Video Overview, Mind Map, Reports, Flashcards, Quiz, and Infographic. These tools allow you to generate spoken summaries, visual data sheets, study aids, and presentation decks derived directly from the documents in your notebook.

1. In the Studio section, click Audio Overview, Infographic, and Slide Deck.

Note: These studio artifacts generate in the background and may require a few minutes to complete.

2. Click the generated Audio Overview, Infographic, and Slide Deck artifacts to review them. Consider how accurately these multimodal synthesis tools capture the main themes from your Cymbal Foods documents.

Click Check my progress to verify the objective. Focused analysis with Gemini Notebook.

Continue exploration (Optional)

You've now covered the core exercises for Gemini Notebook and Gemini Enterprise in this lab! If you have remaining time, this is an excellent opportunity to delve deeper and experiment further with both tools:

In Gemini Notebook:

• Experiment with different questions: Go beyond the example queries. Try asking for comparisons, potential implications (based only on the text), or asking Gemini Notebook to explain a concept using examples from your documents.
• Explore note-taking: Investigate the "Notes" feature more thoroughly. Try saving key AI responses, extracting important quotes from your sources into notes, and writing your own annotations to build a more structured understanding.
• Test other features: Look for other available features in the Gemini Notebook interface, such as suggested questions or different views, and see how they can aid your analysis.

In your Gemini Enterprise app:

• General AI assistant: Return to the main search/chat interface of your deployed Cymbal Foods - Gemini Enterprise app. Try different or more complex queries. For example, ask it to compare information that might come from different connected data stores (e.g., "Are there any marketing campaigns for products that have recent customer feedback entries in Drive, and do any of these align with upcoming calendar events?").
• Organize team context with Projects: Select Projects in the navigation menu to create a dedicated workspace grounded in specific Google Drive files, uploaded documents, and custom instructions tailored to a project team.
• Test interactive canvas: Prompt the assistant to draft a marketing proposal or strategy document, and then use the side-by-side Canvas editor to refine, edit, and format the generated content.
• Export responses to Google Docs and Google Sheets: Use the export controls on generated chat responses and tables to send reports directly to Google Docs or structured data to Google Sheets.
• Experiment with Agent Designer: Revisit the visual Agent Designer (+ New agent) to build additional custom agents. Try adjusting system instructions, attaching specific data connectors, or prompting the copilot to build multi-step workflow logic.
• Share sessions and agents: Explore enterprise collaboration capabilities by inspecting the share menu on your active chat conversations or custom-built agents to see how teams distribute AI workflows.
• Analyze Deep Research findings: Return to the Deep Research agent to examine the detailed report and its actionable insights.
• Explore pre-built agents: In the Agents section of your Gemini Enterprise app's homepage, see if any Google-provided example agents are listed and try interacting with them to understand their capabilities.

This self-directed exploration is a great way to solidify what you've learned and discover even more potential uses for these powerful AI tools in managing and understanding enterprise information.

Congratulations!

Congratulations! You've successfully explored Google Gemini Enterprise. Throughout this lab, you've verified your pre-provisioned application and Cloud Storage data store, connected Google Drive and Google Calendar data stores, interacted with different agents for search and summarization, built a custom agent with Agent Designer (Workflow Builder), created a reusable skill, generated a Deep Research report, and performed focused document analysis with Gemini Notebook, including multimodal Studio overviews. These hands-on skills are invaluable for leveraging Google's advanced AI to unlock enterprise knowledge and streamline decision-making.

Next steps / learn more

For more information about Gemini Enterprise, see the following pages:

• Gemini Enterprise Overview
• Gemini Enterprise Quick Start
• Gemini Enterprise Concepts

Manual Last Updated October 07, 2026

Lab Last Tested October 07, 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.