This official feed from the Google Workspace team provides essential information about new features and improvements for Google Workspace customers.


Google Docs makes it easy to create, structure, and collaborate on complex documents across formats, including viewing and editing Microsoft Word (.docx) files directly in Docs. Today, we are introducing three new Google Docs features—inline captions, cross-references, and tables of captions—to help you more easily organize, reference, and navigate figures, tables, equations, and other items in your documents.

  • Inline captions: Insert numbered labels (such as “Figure 1” or “Table 1”, or define your own custom labels) that automatically order and renumber themselves in sequence as captions are added, reordered, or removed. 
  • Cross-references: Link directly to existing captions in your document with dynamic display text. Unlike standard hyperlinks, the display text of cross-references updates to reflect the caption they’re referencing. 
  • Table of captions: Automatically generate a clickable list of captions and page numbers—organized by label type—so readers can jump straight to any figure, table, or equation.

Until now, keeping numbered figures, tables, and references in sync across complex documents (like contracts or schematics) required manual updates after every edit. These new Google Docs capabilities automate the process and work seamlessly with Microsoft Word (.docx), so your formatting stays intact on import and export.


Getting started

  • Admins: There is no admin control for this feature.
  • End users: This feature will be available by default in Google Docs. To insert a caption, open a document and go to Insert > Page elements > Inline caption. Once your document contains at least one caption, go to Insert > Page elements > Cross reference to link to a caption, or Insert > Page elements > Table of captions to generate a navigable list of captions. Visit the Help Center to learn more about adding captions, cross-references, or a table of captions in a document.

Rollout pace

Availability

  • Available to all Google Workspace customers, Workspace Individual subscribers, and users with personal Google accounts

Resources

Gemini Notebook can now turn sources into interactive sites to help you quickly make sense of complex information. To get started, users can simply type “make me a site” in the Gemini Notebook chat along with a description of what they want to build for work or study, then select “Open in a new tab” to interact with it, or share it with others. For example, students and professionals can build:

  • Visual explainers to help prepare for exams, like an interactive periodic table or a historical timeline
  • Interactive dashboards to explore data, such as quarterly sales performance
  • Project management trackers to outline tasks and deadlines

This feature is available globally on the web for users who are 18 years and older, and coming soon to mobile users.

Getting started

Rollout pace

Availability

  • Available to all Google Workspace customers, Workspace Individual subscribers, and users with personal Google accounts who are 18 years or older

Resources

Developers can now add starter prompts and descriptions to their Google Chat apps, helping users understand what an app or AI agent can do from their very first conversation. When a user opens a direct message with a Chat app, they’ll see the app’s description and up to three suggested prompts to help them get started. Both features can be set up in the Google Cloud console without writing any code.

Developers can choose between two types of starter prompts:

  • Text prompts: Clicking the prompt sends the message to the app or agent.
  • Command prompts: Clicking the prompt runs one of the app's existing slash commands or quick commands. 

Prompts can also be localized, so users see them in their preferred language.

App descriptions give users context about what an app does, who it’s for, and how to use it. For example, an IT help desk agent could describe the types of requests it handles and offer starter prompts like “Reset my password” or “Check ticket status.”

Starter prompts and app descriptions also work with agent sessions, which are now in developer preview. For agents with sessions turned on, users see the app’s description and starter prompts on the sessions home page when they start a new conversation. Visit the developer documentation to learn more about organizing conversations into sessions.



Starter prompts and an app description appear when a user opens a direct message with a Google Chat app.

Getting started

  • Admins: There is no admin control for this feature.
  • End users: There is no end-user setting for this feature. Starter prompts and app descriptions appear in Chat apps whose developers have set them up.
  • Developers: Starter prompts and app descriptions can be configured on the Chat API configuration page in the Google Cloud console. Visit the Google Chat API documentation to learn more about configuring starter prompts.

Rollout pace

Availability

  • Available to all Google Workspace customers and Workspace Individual subscribers

Resources

Gemini-powered AI classification in Google Drive is now generally available. Following our open beta, administrators can now deploy natural-language classification instructions at scale with two new capabilities designed to provide admins a better understanding of automated data classification for their files:

  • Test your instructions: Before deploying the new instructions, admins can test and refine Gemini instructions directly in the Admin console to preview which label Gemini will apply to files.
  • Real-time reporting: Admins can monitor near real-time metrics on the files that AI classification has labeled. On the model details page, admins can view the number of labeled files, user acceptance for labels, and Drive inventory reporting.

By automating file identification and labeling across Drive, AI classification helps organizations enforce granular data loss prevention (DLP) policies at scale, establish retention rules, and utilize label metadata during audit investigations. This also becomes a critical aspect in elevating an organization’s security posture in the agentic era, preventing agentic workflows from accessing and acting autonomously on sensitive data.



Test instructions before deployment


Real-time reporting on files AI classification has labeled

Additional details

This feature leverages Gemini models to apply data classification labels to files in Google Drive. Previously, AI classification required admins to identify and manually label training files for the AI model to learn the types of data associated with each data classification level. With this new capability, Gemini models offer admins an alternative method for data classification that is faster and more efficient, eliminating the need for manual model training and replacing it with administrator-defined instructions.



In the Admin console, Gemini models interpret instructions, evaluate files, and apply appropriate data classification labels.


Administrators maintain full control of the Gemini-based data classification process. They select the label, provide Gemini with instructions, and scope the audience for the files being evaluated. For Gemini-labeled files, editors and owners of those files with the appropriate label permissions will have the opportunity to either review and accept, or modify the automatically-applied label. Audit logs capture when files are labeled, including any user acceptance or modification of a Gemini-applied label.

Key capabilities and limits

  • Model limits: Organizations are limited to 1 active Gemini instruction model, however, they can create up to 5 AI classification models in total (combining custom-trained ML models and Gemini instruction models). 
  • Eligible files and content: Files must be stored in Shared Drives or owned by users with supported licenses. Typically the Gemini model needs at least 50 words and 200 characters of readable or OCR-extracted text to yield a high quality verdict. Client-side encrypted files and non-text media without readable text are skipped.
  • Label eligibility and priority: Labels must use a published single-select options list or badge list field. Gemini classification will not overwrite labels manually applied, accepted, or modified by users, nor labels applied by data loss prevention (DLP) rules.
  • Automatic backfill: Enabling auto-apply initiates a one-time scan of existing and inactive files (typically starting within 1 to 2 weeks, though completion may take weeks or months depending on size and volume of files that need to be backfilled. When instructions are updated, they apply to future uploads and new content. On-demand rescanning of previously evaluated files is not included in this release.
  • Data regions & privacy: Gemini-based AI classification respects your Google Workspace Data Regions settings. Eligible Drive content is processed and stored within your designated region (US or Europe) based on the file owner or Shared Drive policy. Your Drive files and prompts remain isolated to your organization and are never used to train Google's global models.

Rollout pace

Getting started

  • Admins: For customers on a supported product license, the option for configuring Gemini-based AI classification instructions will appear in the Workspace Admin Console under the Data Classification option in the Security section (Security > Access and data control > Data classification). Use our Help Center to learn more.
  • End users: There is no end user setting for this feature.

Availability

  • Enterprise: Enterprise Plus
  • Education: Google AI Pro for Education
  • Other Editions: Frontline Plus

Resources

Building on our recent launch allowing you to view up to three time zones in Google Calendar on the web, we’re making cross-time-zone scheduling even clearer by replacing raw GMT+/- offsets (such as GMT-5 or GMT-8) with familiar, locale-aware time zone abbreviations (such as ET, CT, MT, or PT for users in the United States or MEZ in Germany).

Previously, unless you manually entered a custom label in Calendar Settings, time zone columns on your calendar grid and guest local times in “Find a time” only showed numeric GMT offsets.

Whether you’re an executive assistant coordinating global leadership schedules or a team member booking meetings across regions, you’ll now see recognizable time zone abbreviations and detailed hover tooltips across Google Calendar on the web:

  • Time zone abbreviations on calendar axes: Unlabeled primary, secondary, and tertiary time zone columns now display localized short time zone abbreviations. Any custom time zone labels you’ve set in Settings > Time zone always take top precedence, and time zones without an unambiguous local abbreviation for your language and region gracefully fall back to a compact GMT+/- format (such as GMT+2).
  • Attendee local times in “Find a time”: When checking guest availability in the Find a time tab, each attendee’s column header now displays their local time alongside their time zone abbreviation (for example, “2:00pm (ET)” or “8:00pm (GMT+2)”), so you can immediately see each guest’s local context.
  • Full time zone name on hover: Hovering over any time zone column header on the calendar grid or an attendee’s local time in Find a time now displays a tooltip with the full GMT offset and time zone name (for example, “(GMT-05:00) Eastern Time - New York”).

Getting started

  • Admins: There is no admin control for this feature.
  • End users: This feature will be ON by default. Time zone abbreviations are automatically selected based on your Calendar Language and Country settings (Settings > General > Language and region). If you have configured custom labels for your primary, secondary, or tertiary time zones (Settings > General > Time zone), your custom labels will continue to be displayed instead. Visit the Help Center to learn more about using Google Calendar in different time zones.

Rollout pace

Availability

  • Available to all Google Workspace customers, Workspace Individual subscribers, and users with personal Google accounts

Resources