Tag Archives: Gemini

Google Workspace Updates Weekly Recap – February 7, 2025

3 New updates

Unless otherwise indicated, the features below are available to all Google Workspace customers, and are fully launched or in the process of rolling out. Rollouts should take no more than 15 business days to complete if launching to both Rapid and Scheduled Release at the same time. If not, each stage of rollout should take no more than 15 business days to complete.




Insert responses from Gemini directly into email drafts in the Gmail app
Last year, we introduced the ability for users to ask Gemini questions about their inbox or do things like find specific details in their emails, show unread messages, and more through Gmail Q&A on iOS and Android devices. To build upon this, users can now quickly insert responses or content received after asking Gemini a question directly into an email draft. To do so, open Gemini in the Gmail app (via the Gemini spark at the top right or from a “summarize this email” chip) > ask Gemini a question about the email or your inbox > insert the response by tapping the insert arrow on Android or “Insert” button on iOS. | Rollout to Rapid Release and Scheduled Release domains is complete. | Available to Google Workspace Business and Enterprise users with access to Gemini in Gmail. | Visit the Help Center to learn more about Gemini in Gmail.

Insert responses from Gemini directly into email drafts in the Gmail app

Improving Google Chat app commands 
Currently, you can use slash commands in Google Chat messages to communicate quickly with apps. To simplify this process, we’re excited to introduce quick commands, a way for users to invoke an app command directly without typing a slash command. Developers should use this resource to learn how to set up and respond to quick commands for their Google Chat app. When users invoke a quick command, your Chat app receives an APP_COMMAND interaction event, instead of the MESSAGE interaction event that is sent for slash commands. To modify an existing slash command into a quick command, please follow these steps. After a developer configures quick commands through the Chat API configuration page, users can access them by clicking the plus button menu next to the Chat compose box and then selecting their desired quick command. | Rolling out now to Rapid Release and Scheduled Release domains at an extended pace (potentially longer than 15 days for feature visibility), with expected completion by March 3, 2025. | The ability to configure app commands is available to all Google Workspace customers. | The ability to use app commands is available to all Google Workspace customers, Workspace Individual Subscribers, and users with personal Google accounts. | Visit this developer documentation to learn more about quick commands for Chat apps.


adding quick commands to google chat apps

The ability to generate images with people powered by Imagen 3 is now available across Workspace
We recently upgraded our AI image generation in Workspace to the latest version of Imagen 3, delivering richer details and textures to help bring your creative vision to life. Today, we’re excited to announce that you can now use this technology as you generate images of people in:


Rollout for generating images with people is complete for Gemini Advanced. | Rollout for generating images with people using Gemini in the side panel of Docs, Sheets, Drive, Slides, Gmail, and Vids is complete (in English only). | Rollout for generating images with people for the Gemini app is expected to complete by March 1, 2025. | Available to all Google Workspace users accessing the Gemini app or Gemini Advanced. | Visit the Help Center to learn more about accessing the Gemini app with your Workspace account.



Previous announcements

The announcements below were published on the Workspace Updates blog earlier this week. Please refer to the original blog posts for complete details.


Now generally available: improved syncing experience between Google Calendar and third-party calendars 
In June of 2024, we introduced an improved email notification experience between Google Calendar and third-party calendar services, like Outlook, via beta. Beginning this week, this update is now generally available. | Learn more about improved syncing between Google Calendar and third-party calendars. 

Additional improvements to everyday actions in Google Sheets 
This week, we announced additional improvements available for everyday actions in Sheets: 1) pasting data is now up to 50% faster when you’re pasting from one spreadsheet to another, 2) filter conditions can now be set up to 50% faster than before, and 3) spreadsheets now load existing data up to 30% faster. | Learn more about Sheets improvements. 

Google Meet adds more screen reader options for in-meeting reactions
To improve access for users with vision disabilities, we are adding several more options for how reactions in Google Meet are experienced through screen readers. You can access and adjust the settings at any time during the meeting by pressing Shift+R or from the Settings menu (Three-dot overflow button > Settings > Reactions > Accessibility). | Learn more about screen reader options. 

Developers can now add form field validation to Google Workspace add-ons and Google Chat app cards 
Workspace add-ons and Chat app developers can add client-side input validation to Chat apps and add-ons. | Learn more about adding form field validation to add-ons and app cards. 

Know who an event is shared with when using shared Google Calendars 
Users with the ability to “Make changes to events” can now see the members of the shared calendar, i.e. who their events are shared with. | Learn more about using shared Google Calendars. 

Now generally available: Easily migrate files from Microsoft OneDrive to Google Drive 
In October 2024, we expanded our data migration services to include the ability for Admins to transfer OneDrive data to Google Drive. This functionality is now generally available. You can migrate the files of up to 100 users at a time, including the files corresponding access permissions with shared members. | Learn more about migrating files.

NotebookLM and NotebookLM Plus now available as a Google Workspace core service with enterprise-grade data protection
NotebookLM and NotebookLM Plus, previously introduced as additional services, are now included as core services for Workspace Business and Enterprise customers. Covered under your Google Workspace terms of service, these apps offer the same enterprise-grade data protections and level of technical support as other Workspace core services. | Learn more about NotebookLM and NotebookLM Plus.

Easily convert data to people chips and update chip format in Google Sheets
Similar to the functionality in Google Sheets that helps you easily convert data to dropdown chips, you can now use bulk chip conversion for people chips. | Learn more about chips in Sheets.

Google Vault now supports the Gemini app
Google Vault now supports the Gemini app (on web and mobile). Going forward, admins can use Vault for eDiscovery tasks to search Gemini app conversations and create an export of your search results. | Learn more about Vault supporting the Gemini app.


Completed rollouts

The features below completed their rollouts to Rapid Release domains, Scheduled Release domains, or both. Please refer to the original blog posts for additional details.


Rapid Release Domains: 
Scheduled Release Domains: 
Rapid and Scheduled Release Domains: 


    For a recap of announcements in the past six months, check out What’s new in Google Workspace (recent releases).        

    Google Vault now supports the Gemini app

    What’s changing 

    Google Vault now supports the Gemini app (on web and mobile). Going forward, admins can use Vault for eDiscovery tasks to search Gemini app conversations and create an export of your search results. Specifically, the following actions can be taken around Gemini app data: 

    • Search prompts and responses with a number of filters, such as user and date to quickly refine your search. These searches can be across groups of users or by Organizational Units (OUs) up to 5000 in size. 
    • Export conversations in an XML format for the above searches via the UI or API.


    Who’s impacted

    Admins

    Why it’s important

    Vault is an eDiscovery and information governance tool for Google Workspace, which enables customers to retain, hold, search, and export users’ Google Workspace data. With this update, customers can now expand their regulatory and legal eDiscovery needs to include the Gemini app. This integration makes it easier for customers to comply with their eDiscovery obligations surrounding Gemini collaborative data, all from a central tool. 

    Additionally, Vault’s integration with Gemini rounds out support for critical Workspace apps such as Gmail, Drive, Docs, Sheets, Slides, Chat, Calendar and Meet, providing customers with a consistent experience across all products that are managed within Vault for eDiscovery. Additional information governance and hold features, such as preview, retention, and litigation holds will follow in future releases. We’ll share more information on the Workspace updates blog when it’s available.

    Additional details

    This update is not applicable for Gemini for Google Workspace, as no prompts or responses are retained for those interactions. Visit our Privacy Hub for more information on how we’re protecting your Google Workspace data in the era of generative AI.

    Getting started


    Rollout pace


    Availability

    Available to Google Workspace
    • Business Plus
    • Enterprise Essentials and Enterprise Essentials Plus
    • Enterprise Standard and Enterprise Plus
    • Education Standard and Education Plus customers
    • Also available to customers with the Vault add-on license

    Resources

    Meet the Android Studio Team: A Conversation with Director of Product Management, Jamal Eason

    Posted by Ashley Tschudin – Social Media Specialist, MTP at Google

    Dive into the world of Android Studio and meet the masterminds behind your favorite development tools! In our recurring blog series, "Meet the Android Studio Team," we'll introduce you to the brilliant engineers, designers, product managers, and more who are shaping the future of Android development.

    Join us each week to uncover the unique perspectives and stories of the people who make Android Studio the best it can be.

    Jamal Eason: Building better Android apps - insights on Gemini, Crashlytics, and App Quality

    Meet Jamal Eason, a Director of Product Management at Google, whose passion for empowering developers shines through in his work on Android Studio.

    His journey, from studying computer science at West Point to developing Android hardware at Intel (including contributions to the Motorola Razr i), showcases a deep understanding of the developer experience. From attending the very first Android Studio unveiling at Google I/O to now shaping its future, Jamal brings a unique perspective to the team.

    Jamal shares his insights on the evolution of Android Studio, the importance of a strong developer community, and the features he's most proud of.


    Can you tell us about your journey to becoming a part of the Android Studio team? What sparked your interest in Android development?

    I have had an interest in programming at an early age especially since studying computer science in undergrad at the United States Military Academy (West Point), and in that time I have had an interest not just in the creation of software but also in the tools developers use to make software.

    My interest in Android development came when I was preparing for my first job after my telecommunications & computer networks military career when I was joining a team at the Intel Corporation that worked with Google to build Android hardware products. I thought the best way to understand Google and mobile was to download the Android SDK and create my own app end to end. My first taste of Android was Froyo 2.2 using the Eclipse based Android Developer Tools IDE.

    At Intel, I worked on creating the x86 based version of the Android Emulator and Emulator system image, and also a new Hypervisor that would accelerate the performance of the Android Emulator on x86 based laptops. After helping ship the Motorola Razr i (xt890) Android phone with Intel technology inside and x86 optimized apps on the device, I made the move to the Android team at Google. With my experience in developing Android apps, and shipping Android developer tools, the Android developer tools team was a natural fit.

    Interestingly, I attended the Google I/O the year Android Studio was first revealed as an attendee, and the following year I was working on the team to bring Android Studio to its Beta release at the following years Google I/O.

    What unique perspective or experience do you bring to the Android Studio team, and how does it influence your work?

    Unique experiences I bring include:

    • Technical Translation - In my prior roles, I worked with highly technical teams, and learned how to take absurd technical concepts and present them to different audiences of different technical skill levels. And in the reverse, I worked with many non-technical customers and colleagues and learned how to translate their pain points into product opportunities solved with technical solutions and innovation.
    • User Empathy - Previously, I was a software developer, and I regularly like to code on small side projects, and really enjoy spending time with developers who use Android Studio. From first-hand experience and user engagement, I regularly bring in the voice of the user into the discussion from the inception of a product idea to the final stages of the release process.
    • UX Design Sense - In a previous career, I designed and created websites, and user interfaces for software. I developed an eye for good UX design and flows particularly in technical software products. These skills aid in complementing the dedicated UX design team in Android Studio, and aids in avoiding productivity pitfalls with poor product and UX flows.

    In your opinion, what is the most impactful feature or improvement the Android team has introduced in recent years, and why?

    It’s hard to nail down just one, but the top three are:

      1) product quality

      2) integration of Gemini and

      3) integrations with Crashlytics and Play with App Quality Insights.

    The most impactful feature we worked on is product quality. We treat quality, especially the core code editing experience as a feature. If a developer can’t write a line of code and deploy it to a device, then everything else is secondary. Since Android is always evolving, it is an on-going effort but critical for the team to stay focused on.

    On top of quality, thoughtful integration of Gemini into Android Studio is a real accelerate for app development. Our focus with AI is to make Android developers more productive, and make the harder tasks and toil easier. So from AI powered code completion, or built-in Gemini chat for Android app development, to enhancing existing tools with AI such as using Gemini to generate Jetpack Compose UI Previews, we are just at the beginning of leveraging AI to make Android app developers more productive.

    Lastly, with App Quality Insights, it is now much easier for app developers to address the performance and quality issues found with Firebase Crashlytics and Android Vitals from Google Play. Surfacing these issues right next to source code and source control, make resolving issues much faster and intuitive.

    How does the Android Studio team ensure that products or features meet the ever-changing needs of developers?

    First step, the Android Studio team works hand-in-hand with the Android OS team so we strive to deliver developer tools in concert with new Android OS and API changes so developers are ready to adopt new Android platform capability into their apps. Then, we constantly review and prioritize developer feedback received via our issue tracker or via our bi-annaul developer survey we post on the Android Developers site. When we can, we sometimes engage with developers via various social media channels. And lastly, we regularly interview developers at various experience levels, and regions around the world in targeted User Research studies.

    What advice would you give to aspiring Android developers who are just starting their journey?

    1. Start with a robust set of code labs and tutorials.
    2. Get inspired on the possibilities of Android and what you can build.
    3. Join the Android developer community:

    Deploy with Confidence

    Inspired by Jamal's journey and dedication to empowering developers? Explore the latest Android Studio features, including App Quality Insights, to improve your app's performance and address issues quickly.

    Stay tuned

    Don't miss the next installment of our "Meet the Android Studio Team" series, where we'll introduce you to another amazing member of our team and share their unique journey. Stay tuned for more!

    Find Jamal Eason on LinkedIn and X.

    Use Gemini in the side panel of Workspace apps to generate images in seven additional languages

    What’s changing

    Following the recent announcement of being able to use Gemini in the side panel of Workspace apps in seven additional languages, we’re excited to announce that image generation is now supported in the following languages as well: 
    • French 
    • German 
    • Italian 
    • Japanese 
    • Korean 
    • Portuguese 
    • Spanish 
    using gemini to generate an image of coffee in Spanish


    Additional details 

    • Although Gemini is generally available in the side panel of Docs, Sheets, Drive, and Gmail in these languages, users with Gemini alpha features enabled may still see the "Alpha" badge as we continue rolling out more alpha features 
    • Image generation of people is not supported at this time in these additional languages. 
    • Gemini in the side panel of Slides is only available in English at this time. 

    Getting started 

    • Admins: There is no admin control for this feature. 
    • End users: You can access the side panel by clicking on “Ask Gemini” (spark button) in the top right corner of Docs, Sheets, Drive, and Gmail on the web. Visit the Help Center to learn more about collaborating with Gemini in the side panel of Docs, Sheets, Drive, and Gmail. Note that for accessing other Gemini for Google Workspace features that are supported in English only, you will need to set your Google Account language to English. 

    Rollout pace 


    Availability 

    Image Generation in the side panel of Gmail only is available for Google Workspace: 
    • Business Starter 
    • Enterprise Starter 

    Image Generation in the side panel of Docs, Sheets, Drive, and Gmail is available for Google Workspace: 
    • Business Standard and Plus 
    • Enterprise Standard and Plus 
    • Customers with the Gemini Education or Gemini Education Premium add-on 
    • Google One AI Premium 

    Anyone who previously purchased these add-ons will also receive this feature: 
    • Gemini Business* 
    • Gemini Enterprise* 
    *As of January 15, 2025, we’re no longer offering the Gemini Business and Gemini Enterprise add-ons for sale. Please refer to this announcement for more details. 


    Resources 

    Production-ready generative AI on Android with Vertex AI in Firebase

    Posted by Thomas Ezan – Sr. Developer Relation Engineer (@lethargicpanda)

    Gemini can help you build and launch new user features that will boost engagement and create personalized experiences for your users.

    The Vertex AI in Firebase SDK lets you access Google’s Gemini Cloud models (like Gemini 1.5 Flash and Gemini 1.5 Pro) and add GenAI capabilities to your Android app. It became generally available last October which means it's now ready for production and it is already used by many apps in Google Play.

    Here are tips for a successful deployment to production.

    Implement App Check to prevent API abuse

    When using the Vertex AI in Firebase API it is crucial to implement robust security measures to prevent unauthorized access and misuse.

    Firebase App Check helps protect backend resources (like Vertex AI in Firebase, Cloud Functions for Firebase, or even your own custom backend) from abuse. It does this by attesting that incoming traffic is coming from your authentic app running on an authentic and untampered Android device.

    A flow diagram illustrating App Check, with green lines depicting 'User Request' going through App Check to 'Backend'. A red line depicting 'Bad Request' is being blocked by App Check.
    Firebase App Check ensures that only legitimate users access your backend resources

    To get started, add Firebase to your Android project and enable the Play Integrity API for your app in the Google Play console. Back in the Firebase console, go to the App Check section of your Firebase project to register your app by providing its SHA-256 fingerprint.

    Then, update your Android project’s Gradle dependencies with the App Check library for Android:

    dependencies {
    // BoM for the Firebase platform
   implementation(platform("com.google.firebase:firebase-bom:33.7.0"))

    // Dependency for App Check
    implementation("com.google.firebase:firebase-appcheck-playintegrity")
}

    Finally, in your Kotlin code, initialize App Check before using any other Firebase SDK:

    Firebase.initialize(context)
Firebase.appCheck.installAppCheckProviderFactory(
    PlayIntegrityAppCheckProviderFactory.getInstance(),
)

    To enhance the security of your generative AI feature, you should implement and enforce App Check before releasing your app to production. Additionally, if your app utilizes other Firebase services like Firebase Authentication, Firestore, or Cloud Functions, App Check provides an extra layer of protection for those resources as well.

    Once App Check is enforced, you’ll be able to monitor your app’s requests in the Firebase console.

    An area chart of the Apps Check metrics page in Firebase console, showing the percentages of verified and unverified requests over several days. Numerical breakdowns of verified (51%) and unverified requests (49%) are shown.
    App Check metrics page in the Firebase console

    You can learn more about App Check on Android in the Firebase documentation.

    Use Remote Config for server-controlled configuration

    The generative AI landscape evolves quickly. Every few months, new Gemini model iterations become available and some models are removed. See the Vertex AI in Firebase Gemini models page for details.

    Because of this, instead of hardcoding the model name in your app, we recommend using a server-controlled variable using Firebase Remote Config. This allows you to dynamically update the model your app uses without having to deploy a new version of your app or require your users to pick up a new version.

    You define parameters that you want to control (like model name) using the Firebase console. Then, you add these parameters into your app, along with default "fallback" values for each parameter. Back in the Firebase console, you can change the value of these parameters at any time. Your app will automatically fetch the new value.

    Here's how to implement Remote Config in your app:

    // Initialize the remote configuration by defining the refresh time
val remoteConfig: FirebaseRemoteConfig = Firebase.remoteConfig
val configSettings = remoteConfigSettings {
    minimumFetchIntervalInSeconds = 3600
}
remoteConfig.setConfigSettingsAsync(configSettings)

// Set default values defined in your app resources 
remoteConfig.setDefaultsAsync(R.xml.remote_config_defaults)

// Load the model name
val modelName = remoteConfig.getString("model_name")

    Read more about using Remote Config with Vertex AI in Firebase.

    Gather user feedback to evaluate impact

    As you roll out your AI-enabled feature to production, it's critical to build feedback mechanisms into your product and allow users to easily signal whether the AI output was helpful, accurate, or relevant. For example, you can incorporate interactive elements such as thumb-up and thumb-down buttons and detailed feedback forms within the user interface. The Material Icons in Compose package provides ready to use icons to help you implement it.

    You can easily track the user interaction with these elements as custom analytics events by using Google Analytics logEvent() function:

    Row {
   Button (
      onClick = {
         firebaseAnalytics.logEvent("model_response_feedback") {
            param("feedback", "thumb_up")
         }
      }
   ) {
      Icon(Icons.Default.ThumbUp, contentDescription = "Thumb up")
   },
   Button (
      onClick = {
         firebaseAnalytics.logEvent("model_response_feedback") {
            param("feedback", "thumb_down")
         }
      }
   ) {
      Icon(Icons.Default.ThumbDown, contentDescription = "Thumb down")
   }
}

    Learn more about Google Analytics and its event logging capabilities in the Firebase documentation.

    User privacy and responsible AI

    When you use Vertex AI in Firebase for inference, you have the guarantee that the data sent to Google won’t be used by Google to train AI models (see Vertex AI documentation for details).

    It's also important to be transparent with your users when they're engaging with generative AI technology. You should highlight the possibility of unexpected model behavior.

    Finally, users should have control within your app over how their activity related to AI model interactions is stored and deleted.

    You can learn more about how Google is approaching Generative AI responsibly in the Google Cloud documentation.

    Generate charts and valuable insights using Gemini in Google Sheets

    What’s changing 

    Building data visualizations and identifying trends in data is a critical business function, however it can be time consuming and oftentimes overwhelming. To improve upon this experience, we’re making it easier for Sheets users, ranging from small business owners to marketing analysts, to visualize and analyze data using Gemini in Sheets. 

    Starting today, Gemini in Sheets can perform actions or answer questions to address a wide variety of scenarios. Specifically, you can ask Gemini questions about your data and Gemini can provide valuable insights, such as contextual trends, patterns, and correlations between different variables in your data. Gemini will also generate charts based on your data that you can insert as static images over cells in your spreadsheet. For example: 
    • A marketing manager analyzing campaign performance can ask "Provide some insights on my top 3 performing channels by conversion rate" and can receive a detailed breakdown with supporting visualizations. 
    • A small business owner managing cash flow can ask "Predict my net income for the next quarter based on historical data" to proactively identify potential shortfalls. 
    • A financial analyst investigating inventory trends can ask "Identify any anomalies in inventory levels for Product X" to uncover potential supply chain issues or unusual demand patterns. 
    Ask Gemini in Sheets to share insights and trends from the data.
    Ask Gemini in Sheets to share insights and trends from the data.

    Ask Gemini in Sheets to visualize data with a chart or bar graph.
    Ask Gemini in Sheets to visualize data with a chart or bar graph.



    Who’s impacted 

    End users 


    Why you’d use it 

    This update reflects Gemini in Sheets’ enhanced intelligence as it now yields valuable outputs by transforming your requests into Python code, executing on them and then analyzing the results to perform multi-layered analysis. As a result, you’re able to do things like identify top-performing products and then instantly dive into their sales trends — all without writing a single line of code. 


    Additional details 

    • For the most accurate results, ensure your data is in a consistent format, with clear headers and no missing values. 
    • When asking Gemini in Sheets to analyze your data, be as specific as possible in your prompts to ensure Gemini understands your request. 
    • For complex analysis, Gemini in Sheet's performance is most consistent in files below 1 million cells. 
    • For some simpler questions about your data, Gemini in Sheets may still provide answers using formulas instead of Python code. 
    • Charts are generated as static images and can be easily inserted into your sheet. 
    • Charts are not linked to your sheet data, so they won't update automatically if your data changes. 
    • Once inserted, charts cannot be modified. If you need to make changes, you'll need to generate a new chart. 

    Getting started 

    Rollout pace 

    Availability 

    Available for Google Workspace:
    • Business Standard and Plus 
    • Enterprise Standard and Plus 
    • Customers with the Gemini Education or Gemini Education Premium add-on 
    • Google One AI Premium 
    Anyone who previously purchased these add-ons will also receive this feature: 
    • Gemini Business* 
    • Gemini Enterprise* 
    *As of January 15, 2025, we’re no longer offering the Gemini Business and Gemini Enterprise add-ons for sale. Please refer to this announcement for more details. 

    Resources 

    Generate vocabulary lists using Gemini in Google Classroom

    What’s changing 

    Since May of last year, education institutions have been leveraging new and powerful ways of working, teaching and learning with Gemini for Google Workspace. This includes products and features such as the Gemini app, Gemini Learning Tools Interoperability (LTI™), Gemini in Google Vids and Gemini in Classroom.

    In continuing our efforts to ensure AI helps educators save time, create captivating learning experiences, and inspire creativity, we’re introducing a new way to generate vocabulary lists with the help of Gemini. 

    Starting today, educators can generate custom word lists that are tailored to specific grade levels and topics identified by the educator. Specifically, the list will provide the word’s grammatical category, a clear definition, and a relevant example sentence to help students understand and use the vocabulary effectively. This functionality is accessible via the “Gemini Education” tab in Google Classroom. 

    creating a vocab list using gemini in classroom


    Who’s impacted 

    Admins and end users 


    Why it’s important 

    This update helps educators create vocabulary lists tailored to specific grade levels and topics while simultaneously empowering students to master vocabulary and deepen their understanding of language – all right within Google Classroom. 


    Getting started 


    Rollout pace 


    Availability 

    Available for Google Workspace customers with these add-ons: 
    • Gemini Education and Education Premium 

    Resources