Collaborate with Gemini in Google Docs (Workspace Labs)

With Gemini in Google Docs, you can:

Write and refine content in context.
Summarize your files from Drive and emails from Gmail.
Create images.
Get creative ideas.

Feature availability

This feature is available as part of our early access testing program, Google Workspace Labs.
To turn off Google Workspace Labs features, exit the Workspace Labs program.
This feature is also available to users on work or school accounts through a Gemini for Google Workspace add-on, and to users on personal accounts through Google One AI Premium. Learn about Gemini features and plans.

Supported languages

You can use the Gemini in Docs side panel in some languages. Learn more about language availability.

Get started with Gemini in Docs

An animation that shows how to ask Gemini in Docs about a proposal for a new electric bike

On your computer, open a document from Google Docs.
At the top right, click Ask Gemini .
In the side panel, select a suggested prompt or write your own prompt.
Select a suggestion
1. Select from the list of suggestions.
  - To get more options, select More suggestions.
2. At the bottom, in the prompt box, replace the example text with the information you want.
3. Press Enter.
Enter a prompt in Gemini
1. At the bottom, in the prompt box, enter a prompt.
2. Press Enter.
Optional: To remove your history, click More options Clear history.

Tip: To avoid losing your history, insert generated output in the document. You lose your conversation history when:

You refresh your browser.
You close and reopen the document.
Your computer goes offline.

Explore Gemini in Docs

Action	Description
Ask Gemini	Open Gemini.
More options	Clear your recent Gemini history and ask for more suggestions.
Expand	Make Gemini larger.
Collapse	Return Gemini to its original size.
Close	Close Gemini.
Clear history	Remove all generated text and images you did not insert into the document yet.
More suggestions	Find more suggestions from Gemini.
More image suggestions	Find more suggestions of images from Gemini.
Insert	Insert generated text into your document.
Insert image	Insert a generated image into your document.
Copy	Copy a suggestion.
Retry	Generate a different response from Gemini.
Preview	Preview the full suggestion before you insert it.
Retry with Google Search	Search on Google for more information about your question or request.
View more	View more of the response from Gemini.
View less	Minimize the response from Gemini.
Good suggestion	Give positive feedback about a response from Gemini.
Bad suggestion	Report an issue with a response from Gemini.

Things to ask Gemini in Docs

Summarize text with Gemini

On your computer, open a document from Google Docs.
At the top right, click Ask Gemini .
- When you open a document that has text, on the side panel, you’ll find a summary of your document.
- To get a summary of your document, ask Gemini.
  - Examples:
    - “Summarize this document in 3 bullet points.”
    - “Explain this document like I'm 5 years old.”
  - To summarize a specific section of your document:
    1. Highlight the text.
    2. On the side panel, ask Gemini to summarize your text.
You can also:
- Add the text to your document: Click Insert .
- Find a different version: Click Retry .
- Send feedback about the suggested text: Click Good suggestion or Bad suggestion .

Write or rewrite with Gemini

On your computer, open a document from Google Docs.
At the top right, click Ask Gemini .
On the side panel, select a prompt or create your own.
Press Enter.
Generate text and refine it.
- Examples:
  - “Write an announcement email about a new feature.”
  - “Make the announcement more fun.”
You can also:
- Add the text to your document: Click Insert .
- Find a different version: Click Retry .
- Send feedback about the suggested text: Click Good suggestion or Bad suggestion .

Create images with Gemini

You can ask Gemini to generate images in Docs.

On your computer, open a document from Google Docs.
At the top right, click Ask Gemini .
On the side panel, create your own prompt.
- Example: “Create an image of a dog with glasses.”
On the image that you like, you can hover over to:
- Insert an image: Click Insert .
- Find similar images: Click Generate more .
You can also:
- Find more images: At the bottom, click Generate more .
- Change your prompt: Click Edit prompt .
- Send feedback about the generated images: At the bottom, click Good suggestion or Bad suggestion .

Reference your Drive files with Gemini

You can use Gemini to reference files from your Drive to generate responses in Docs.

On your computer, open a document from Google Docs.
At the top right, click Ask Gemini .
On the side panel, ask questions about your Drive files.
- Example: “What are the main points of @Meeting Notes: Core Team sync?"
To check which files were used, at the bottom of the response, click Sources.
You can also:
- Add the text to your document: Click Insert .
- Generate a new suggestion: Click Retry .
- Send feedback about the suggested text: Click Good suggestion or Bad suggestion .

Reference your Gmail emails with Gemini

You can ask Gemini to reference emails to generate responses.

On your computer, open a document from Google Docs.
At the top right, click Ask Gemini .
On the side panel, ask questions about your Gmail emails.
- Example: “Catch me up on the latest Monthly Review emails.”
To check which emails were used, at the bottom of the response, click Sources.
You can also:
- Add the suggested content to the document: Click Insert .
- Generate a new suggestion: Click Retry .
- Send feedback about the suggested text: Click Good suggestion or Bad suggestion .

Get help with Google Docs

“How do I make my document pageless?”
“Can I add markups to my document?”

Get answers from the web

Important: To get answers from the web, make sure to include phrases like “Use Google Search” or “Using web search” in your prompt.

“Write a paragraph describing the weather today in Mountain View, California using web search.”
“Help me write a paragraph explaining if lightning can strike the same place twice using only information from the web.”

Give feedback on generated output

Gemini for Google Workspace is constantly learning and may not be able to support your request. Because feedback may be human readable, please do not submit data that contains personal, confidential, or sensitive information.

If you get a suggestion that’s inaccurate or that you feel is unsafe, you can submit feedback. Your feedback can help improve AI-assisted Workspace features and broader Google efforts in AI.

At the bottom of the generated output, click Good suggestion or Bad suggestion .
If you select Bad suggestion , you can select the issue you found and enter additional feedback.
- Optional:
  - To review data that will be attached with your feedback, at the bottom, select What data will be attached?
  - If you don’t want to include the data with your feedback, uncheck Attach collected data to your feedback to help us improve the product experience.
Click Next.
Review additional context that you can share with your feedback.
- If you don’t want to include the additional context with your feedback, uncheck Additional context (content referenced to create outputs).
Click Submit.

To provide general feedback on this feature, at the top, go to Help Help Docs improve.

To report a legal issue, create a request.

Turn off Gemini in Docs

To turn off any of the features on Google Workspace Labs, you must exit Workspace Labs. If you exit, you’ll permanently lose access to all Workspace Labs features, and you won’t be able to rejoin Workspace Labs. Learn more about how to exit Workspace Labs.

Learn about Workspace Labs feature suggestions

Workspace Labs feature suggestions don’t represent Google’s views, and should not be attributed to Google.
Don’t rely on Workspace Labs features as medical, legal, financial, or other professional advice.
Workspace Labs features may suggest inaccurate or inappropriate information. Your feedback makes Workspace Labs more helpful and safe.
Don’t include personal, confidential, or sensitive information in your prompts.
Google uses Workspace Labs data and metrics to provide, improve, and develop products, services, and machine learning technologies across Google.
Your Workspace Labs Data may also be read, rated, annotated, and reviewed by human reviewers. Importantly, where Google uses Google-selected input (as described in the Privacy Notice) to generate output, Google will aggregate and/or pseudonymize that content and resulting output before it is viewed by human reviewers, unless it is specifically provided as part of your feedback to Google.
Your conversations with Gemini in Docs are not saved to Gemini Apps Activity. When you delete your Gemini in Docs conversation history, it doesn't delete any information that is saved to your Gemini Apps Activity. Learn how to delete your Gemini Apps Activity.
Generated images are for use only within Google Docs.
Workspace Labs generated images are designed to bring your imagination to life in Google Docs, and may not represent real world situations.

How Workspace Labs data in Google Docs is collected

When you use the Gemini in Docs side panel, Google uses and stores the following data:

Prompts you enter or select.
Generated text and images.
Google Workspace content that you have access to that is referenced to generate content (both Google-selected input and user-provided input).
Your feedback on Gemini in Docs side panel.

To understand how this data is used, review the Google Workspace Labs Privacy Notice and Terms for Personal Accounts.