Use Gemini Spark to manage your tasks & workflows in Gemini Apps

Do not enter sign-in info, payment details, or info you may find sensitive directly into the task thread. If needed, take control of Gemini’s browser or the local browser. Then, enter relevant details directly on the webpage.

Gemini is still learning and can make mistakes. To help keep your information safe and prevent unintended actions, avoid tasks or schedules that use information or perform actions that you find sensitive. These tasks may need your supervision and input.

If a schedule runs when you are offline, you may not be able to stop Gemini from completing an unintended action. Some tasks may require your confirmation before Gemini completes them. Learn more about tasks and schedules.

With Chrome auto browse, you can ask Gemini Spark to complete tasks that involve browsing the web, like shopping, booking travel, or making dinner reservations. To work on your tasks, Spark uses your info from sources like Connected Apps, skills, chats, tasks, websites you’re logged into, Personal Intelligence, location, and more.

Gemini Spark can browse the web in multiple ways, one of which is by connecting to your own device (aka your local Chrome browser). Currently, only Gemini Spark in desktop Chrome can use auto browse. It might also use a remote browser (which is a separate, new browser instance, not your local browser in the cloud).

If you use your local browser: Gemini Spark has access to all the same sites that you do, including sites you’re signed into. When acting on your behalf, Gemini Spark will share necessary info with third parties. This could include your name, contact information, files, preferences, and info you might find sensitive. With your permission, it can also use login info you saved in Password Manager to sign into loyalty programs and online accounts.

To use Spark via your local browser, you’ll need to keep your device and Google Chrome awake and running. If you later close or turn off your device before the task is finished, or the device isn’t available, Spark might use a remote browser to complete the task.

If you use the remote browser: Your task can continue even if you close your device. Note that at some stages -- like when a website asks you to sign in -- the task will stop until you take over and do it yourself.

Notes:

• The first time Gemini Spark needs to browse the web for you on this device, Chrome will ask you for permission to connect Chrome to Spark.
• After that, for every task that involves web browsing, Spark will ask for confirmation first.
• You can turn off Gemini Spark’s ability to autobrowse on a device. Click More Settings AI Innovations Gemini in Chrome.

Keep track of tasks

If Gemini Spark is busy using auto browse for a task, you’ll see it in your Recent Tasks. At any time, you can stop Gemini from web browsing. In the Gemini in Chrome side panel, click Stop . If you do, Gemini tries to figure out the next steps to continue your task. This may involve use of the remote browser to web browse or activation of a different tool. Or it could mean that Gemini abandons the task.

If you want to completely cancel a task yourself, in the Gemini Spark text box, click Stop .

Under “Progress,” you can find the steps and progress of tasks in a thread.

Completed step Current step Planned step

1. Under “Schedules,” tap the schedule you want to pause or resume.
2. To pause a schedule, tap More Pause .
3. To resume a schedule, tap More Resume .

Gemini can complete some of your tasks in a local or remote browser. For example, it can navigate to a website and interact with the page, like adding items to your cart. You can take control of the browser at any time. For certain actions, Gemini will ask you to take over the task.

In the Gemini mobile app

1. Open the task’s work panel.
2. Under “Skills & apps,” tap View Remote browser View live. This opens Gemini’s browser on a remote computer.
   • When Gemini is browsing the web, there’s a Remote computer icon at the top of the task thread. You can also tap Remote computer to view Gemini’s browser.
3. Tap Take over task Take over task.
4. Complete your steps.
5. To give back control to Gemini, at the top, tap Go back to Gemini.

In the Gemini web app

1. Open the task’s work panel.
2. Under “Skills & apps,” tap Remote browser. This opens Gemini’s browser on a remote computer.
   • When Gemini is browsing the web, there’s a Remote computer icon at the top of the task thread. You can also tap Remote computer to view Gemini’s browser.
3. Tap Take over task Take over task.
4. Complete your steps.
5. To give back control to Gemini, at the top, tap Go back to Gemini.

When Gemini uses the remote browser to complete tasks, browser data, like cookies that contain your website authentication info (your sign-in details), is saved for future sessions for your convenience. You can delete all saved browser data from past sessions, at any time. To help protect your privacy, Gemini may automatically delete saved browser data on your behalf, and you may need to sign back in to websites.

1. On your phone or tablet, open the Gemini mobile app or go to gemini.google.com.
2. At the top, tap Menu .
3. At the bottom, tap Settings & help Gemini Spark Settings .
4. Under “Delete remote browser data,” tap Delete .

When Gemini uses a remote computer to run code or perform complex tasks, it saves data on the remote computer for future sessions for your convenience. You can delete all the data saved on the remote computer at any time in Gemini Spark settings. This will delete all saved remote code execution files and data from previous sessions.

1. On your phone or tablet, open the Gemini mobile app or go to gemini.google.com.
2. At the top, tap Menu .
3. At the bottom, tap Settings & help Gemini Spark Settings .
4. Under “Delete remote code execution data,” tap Delete .

Gemini Spark can use:

• Skills: reusable instructions with additional context. Learn how to create and manage skills.
• Schedules: automated triggers for a task that tell Gemini Spark when to execute your instructions. Learn how to create and manage schedules.

Gemini Spark can use some Connected Apps and certain Google services for your tasks, including:

• Custom apps. Learn how to connect custom apps.
• These Google Connected Apps and services:
  • Google Workspace, which includes Calendar, Docs, Drive, Gmail, Keep, Sheets, Slides, and Tasks. Learn which actions are supported.
  • Google Search services, which includes Search, Finance, Flights, Hotels, and Maps.
  • YouTube.
• These third-party apps:
  • Canva
  • Dropbox
  • Instacart
  • OpenTable
  • Zillow

Gemini Spark can use a remote browser with automatically saved info and remote computer with code execution data for your tasks. Learn how to delete remote browser and computer data.

Gemini Spark can use Personal Intelligence, which includes:

• Memory of your past Gemini chats
• Instructions for Gemini
• Google Connected Apps that work with Personal Intelligence

Below are some of Gemini’s other features that Gemini Spark can use to work on your tasks.

Canvas panel for Google Docs

• In the Gemini web app at gemini.google.com, you can edit Google documents that Gemini Spark creates in the Canvas panel.
• When Gemini Spark uses Canvas, the “Create” menu and certain quick edit options in Canvas are not available.

Learn more about Canvas

Agentic AI technologies, which power some of the capabilities of Gemini Spark, are helpful and powerful tools, but it's important to be aware of some possible risks. Remember that Gemini can make mistakes and do unexpected things.

About prompt injection

Prompt injection is an attempt to elicit an unintended or harmful response from AI tools like Spark. This happens when content, like a website, an email, a document, .md file, or multimedia, has malicious instructions or code that might be hidden from you but visible to the AI agent.

If an AI agent reads these instructions while doing a task, it may be misled into doing unintended things. For example, a malicious instruction could tell the agent to:

• Take your private info from your emails or documents and post it on a public website.
• Send your emails in Gmail to an external service without you knowing.
• Expose insights about you based on your data in connected apps.
• Run a command that can be malicious or install compromised software, to achieve persistent data exfiltration through arbitrary code execution. To help protect against this, you can delete your remote browser data and clear your code execution history and files in your Gemini Spark settings.

Gemini can share your info with websites

When you use Spark, Gemini can share information from your chat and other available sources, like your Connected Apps and Personal Intelligence, with websites while using the local or remote browser. This could include your name, contact info, files, preferences, and info you might find sensitive. This can create privacy risks, for example when Spark uses connected apps like Google Workspace which allow Gemini to access your private info. Gemini can choose sites to visit to fulfill your request. 

Gemini has access to your local browsing state

When using the local browser Chrome, Gemini Spark has access to the same sites that you do, including sites you're signed into. 

• Prompts for user confirmation: Gemini is designed to ask for your review and confirmation before it completes certain actions, such as:
  • Sending communications, modifying your data, making purchases, and submitting web forms.
  • Before starting a browser task, Gemini will choose which sites to use to complete the task, and it may share your personal info with those sites.
    • Review the plan Gemini in Chrome will use. Check that it understood your prompt, the page context, and your personal info correctly.
• Prohibited task recognition: Gemini has safeguards designed to help it recognize and not act on certain types of requests that could be harmful or are outside of its intended purpose, including certain tasks that may violate the Generative AI Prohibited Use Policy.
• “Take control” mode: Gemini may pause and ask you to “take control” of the browser to complete specific actions, including entering specific types of information (such as passwords or payment details).
• Planning info: Gemini is designed to show you what it’s planning to do after you submit a prompt, its progress as it works on your task, and any relevant Skills, Connected Apps, and files used or created.
• Site and action restrictions: Spark restricts its browsing activity to the websites and actions relevant to your task. This helps protect your data on other unrelated sites and helps prevent actions that don't align with your task. These are just some ways we protect against prompt injection.

Gemini’s safeguards for Spark described above don’t guarantee protection against all risks.

Supervise important & sensitive tasks

• Handles an important task
• Is signed in to websites with sensitive access or info you find sensitive
• Does anything where a mistake could be a problem
• Uses connected apps, like Google Workspace
• Requires sharing data that you consider sensitive.

You’re in control

If Gemini is doing something you don't like, you can stop it by selecting Stop response   in the chat or Take control over Gemini’s browser. Gemini’s safeguards aren’t intended to replace your active supervision. You can also help keep your info safe by deleting your local or remote browser data and remote computer data after sensitive sessions. 

Important:

• For Spark to connect with your data in Google Workspace services, Google Workspace needs to be connected to Gemini Apps. Learn how to use & manage Connected Apps in Gemini.
• To undo Gemini Spark’s action, click the link in Spark’s confirmation and make your changes in the Workspace service.

Calendar

• Manage your schedule: Check your calendar, RSVP to invitations, and schedule new events.
• Reschedule & clean up: Update meeting times, change locations, or cancel events.
• Smart scheduling: Check your calendar and suggest open slots that fit everyone's availability.

Gmail

• Search & summarize emails: Search across your email threads to find specific topics or summarize conversations.
• Draft & reply: Compose email drafts, forward emails, or reply to existing email threads.
• Use labels: Organize your inbox with labels.

Docs, Sheets, Slides, & Drive

Important: To edit shared documents, spreadsheets, and presentations, you’ll need to review and confirm Gemini Spark’s planned edits.

• Search & manage your Google Drive files: Search for files, read file contents, rename or delete files, check metadata, and view recent documents.
• Write & edit documents: Create documents in Google Docs or edit existing ones—adding summaries, notes, or editing specific sections.
• Read comments: Read comments in Google documents, spreadsheets, and presentations.
• Create & edit spreadsheets: Build, format, and edit custom spreadsheets in Google Sheets with data, tables, and formulas.
• Generate & edit presentations: Create presentations in Google Slides from a prompt, and edit, add, and remove slides in a presentation.
• Add images to documents & presentations: Add an image to your prompt and ask Gemini to add it to a document or presentation.

Google Keep

• Find notes & lists: Search for and retrieve notes and lists across Google Keep.
• Create notes & lists: Create private lists and notes in Google Keep.

Google Tasks

Important: Gemini can perform bulk actions on private tasks in Google Tasks without your confirmation. Please review your request before you submit or manage directly in Google Tasks.

• Find reminders & tasks: Search for and retrieve reminders and tasks from Google Tasks.
• Manage reminders & tasks: Add, update, and delete reminders and tasks in Google Tasks.