Category Archives: Google Developers Blog

News and insights on Google platforms, tools and events

Create smart chips for link previewing in Google Docs

Posted by Chanel Greco, Developer Advocate

Earlier this year, we announced the general availability of third-party smart chips in Google Docs. This new feature lets you add, view, and engage with critical information from third party apps directly in Google Docs. Several partners, including Asana, Atlassian, Figma, Loom, Miro, Tableau, and Whimsical, have already created smart chips so users can start embedding content from their apps directly into Docs. Sourabh Choraria, a Google Developer Expert for Google Workspace and hobby developer, published a third-party smart chip solution called “Link Previews” to the Google Workspace Marketplace. This app adds information to Google Docs from multiple commonly used SaaS tools.

In this blog post you will find out how you too can create your own smart chips for Google Docs.

Example of a smart chip that was created to preview information from an event management system
Example of a smart chip that was created to preview information from an event management system


Understanding how smart chips for third-party services work

Third-party smart chips are powered by Google Workspace Add-ons and can be published to the Google Workspace Marketplace. From there, an admin or user can install the add-on and it will appear in the sidebar on the right hand side of Google Docs.

The Google Workspace Add-on detects a service's links and prompts Google Docs users to preview them. This means that you can create smart chips for any service that has a publicly accessible URL. You can configure an add-on to preview multiple URL patterns, such as links to support cases, sales leads, employee profiles, and more. This configuration is done in the add-on’s manifest file.

{
  "timeZone": "America/Los_Angeles",
  "exceptionLogging": "STACKDRIVER",
  "runtimeVersion": "V8",
  "oauthScopes": [
    "https://www.googleapis.com/auth/workspace.linkpreview",
    "https://www.googleapis.com/auth/script.external_request"
  ],
  "addOns": {
    "common": {
      "name": "Preview Books Add-on",
      "logoUrl": "https://developers.google.com/workspace/add-ons/images/library-icon.png",
      "layoutProperties": {
        "primaryColor": "#dd4b39"
      }
    },
    "docs": {
      "linkPreviewTriggers": [
        {
          "runFunction": "bookLinkPreview",
          "patterns": [
            {
              "hostPattern": "*.google.*",
              "pathPrefix": "books"
            },
            {
              "hostPattern": "*.google.*",
              "pathPrefix": "books/edition"
            }
          ],
          "labelText": "Book",
          "logoUrl": "https://developers.google.com/workspace/add-ons/images/book-icon.png",
          "localizedLabelText": {
            "es": "Libros"
          }
        }
      ]
    }
  }
}
The manifest file contains the URL pattern for the Google Books API

The smart chip displays an icon and short title or description of the link's content. When the user hovers over the chip, they see a card interface that previews more information about the file or link. You can customize the card interface that appears when the user hovers over a smart chip. To create the card interface, you use widgets to display information about the link. You can also build actions that let users open the link or modify its contents. For a list of all the supported components for preview cards check the developer documentation.

function getBook(id) {
// Code to fetch the data from the Google Books API
}

function bookLinkPreview(event) {
 if (event.docs.matchedUrl.url) {
// Through getBook(id) the relevant data is fetched and used to build the smart chip and card

    const previewHeader = CardService.newCardHeader()
      .setSubtitle('By ' + bookAuthors)
      .setTitle(bookTitle);

    const previewPages = CardService.newDecoratedText()
      .setTopLabel('Page count')
      .setText(bookPageCount);

    const previewDescription = CardService.newDecoratedText()
      .setTopLabel('About this book')
      .setText(bookDescription).setWrapText(true);

    const previewImage = CardService.newImage()
      .setAltText('Image of book cover')
      .setImageUrl(bookImage);

    const buttonBook = CardService.newTextButton()
      .setText('View book')
      .setOpenLink(CardService.newOpenLink()
        .setUrl(event.docs.matchedUrl.url));

    const cardSectionBook = CardService.newCardSection()
      .addWidget(previewImage)
      .addWidget(previewPages)
      .addWidget(CardService.newDivider())
      .addWidget(previewDescription)
      .addWidget(buttonBook);

    return CardService.newCardBuilder()
    .setHeader(previewHeader)
    .addSection(cardSectionBook)
    .build();
  }
}
This is the Apps Script code to create a smart chip.

A smart chip hovered state.
A smart chip hovered state. The data displayed is fetched from the Google for Developers blog post URL that was pasted by the user.


For a detailed walkthrough of the code used in this post, please checkout the Preview links from Google Books with smart chips sample tutorial.



How to choose the technology for your add-on

When creating smart chips for link previewing, you can choose from two different technologies to create your add-on: Google Apps Script or alternate runtime.

Apps script is a rapid application development platform that is built into Google Workspace. This fact makes Apps Script a good choice for prototyping and validating your smart chip solution as it requires no pre-existing development environment. But Apps Script isn’t only for prototyping as some developers choose to create their Google Workspace Add-on with it and even publish it to the Google Workspace Marketplace for users to install.

If you want to create your smart chip with Apps Script you can check out the video below in which you learn how to build a smart chip for link previewing in Google Docs from A - Z. Want the code used in the video tutorial? Then have a look at the Preview links from Google Books with smart chips sample page.

If you prefer to create your Google Workspace Add-on using your own development environment, programming language, hosting, packages, etc., then alternate runtime is the right choice. You can choose from different programming languages like Node.js, Java, Python, and more. The hosting of the add-on runtime code can be on any cloud or on premise infrastructure as long as runtime code can be exposed as a public HTTP(S) endpoint. You can learn more about how to create smart chips using alternate runtimes from the developer documentation.



How to share your add-on with others

You can share your add-on with others through the Google Workspace Marketplace. Let’s say you want to make your smart chip solution available to your team. In that case you can publish the add-on to your Google Workspace organization, also known as a private app. On the other hand, if you want to share your add-on with anyone who has a Google Account, you can publish it as a public app.

To find out more about publishing to the Google Workspace Marketplace, you can watch this video that will walk you through the process.



Getting started

Learn more about creating smart chips for link previewing in the developer documentation. There you will find further information and code samples you can base your solution of. We can’t wait to see what smart chip solutions you will build.

Global developers use Google tools to build solutions in recruiting, mentorship and more

Posted by Lyanne Alfaro, DevRel Program Manager, Google Developer Studio

Developer Journey is a monthly series highlighting diverse and global developers sharing relatable challenges, opportunities, and wins in their journey. Every month, we will spotlight developers around the world, the Google tools they leverage, and the kinds of products they are building.

This month we speak with global developers across Google Developer Experts, and Women Techmakers, to learn more about their favorite Google tools, the applications they’ve built to serve diverse communities and the role of inclusive design in their process.


Miguel Ángel Durán Garcí

Headshot of Miguel Ángel Durán Garcí, smiling
Barcelona, Spain
Google Developer Expert, Web Technologies
Content Creator & Software Engineer

What Google tools have you used to build?

I've been using Firebase, Google Cloud Platform, CrUX Dashboard, and Chrome DevTools for years. As a web developer, I'm always excited about the new features that DevTools brings to us to improve our productivity and the performance of our applications.


Which tool has been your favorite to use? Why?

Lately, I've been trying Project IDX, an entirely web-based workspace for full-stack application development, and I'm really excited about the future of this project. I love the idea of being able to develop and deploy applications from the browser, without having to install anything on my computer.


Please share with us about something you’ve built in the past using Google tools.

Most recently, I've deployed AdventJS, a holiday calendar for developers. For optimizing the images, I've used Squoosh from the GoogleChromeLabs team. To ensure the website was accessible and to tweak performance, I've used Lighthouse from Chrome DevTools. Also, I used Google Bard to translate the content of the website into English and Portuguese.


What will you create with Google Bard?

I'm planning to expand a website I've created for the Spanish-speaking community to teach JavaScript from scratch. With Google Bard, I can check the content, create some code, and make it help me create challenges for the students.


What advice would you give someone starting in their developer journey?

I would tell them to be patient and to enjoy the process. It's a long journey, but it's worth it. Also, I would tell them to be curious and avoid sticking to only a few technologies. And finally, I would tell them to share their knowledge with the community, because it's the best way to learn and meet new people. You don't need to be an expert to share your knowledge; you just need to be one step ahead of the people you're teaching.


Marian Villa

Headshot of Marian Villa, smiling
Medellín, Colombia
Google Developer Expert, Web Technologies
Co-founder / Director Pionerasdev

What Google tools have you used to build?

Development and Creativity:

  • Google Chrome DevTools
  • Bard
  • TensorflowJS

Productivity and Communication:

  • Gmail
  • Google Calendar
  • Google Drive
  • Google Docs
  • Google Sheets
  • Google Slides
  • Google Meet

Marketing and Business:

  • Google Ads
  • Google Analytics
  • Google My Business
  • Google Workspace
  • Google Cloud Platform
  • Google Marketing Platform

Education and Learning:

  • Google Classroom
  • Google Forms
  • Google Sites
  • YouTube

Which tool has been your favorite to use? Why?

Choosing a favorite tool is quite a task given the unique strengths of Bard, TensorflowJS and Google Chrome DevTools, but I'd have to say that Google Chrome DevTools stands out for me. Its versatility in inspecting and debugging web pages, testing code variations, and providing insights into JavaScript behavior has been crucial in my web development endeavors. That being said, both Bard and TensorFlow.js have incredible capabilities. Bard plays a vital role in generating creative content, answering queries, and even composing code. TensorFlow.js, on the other hand, is a game-changer, enabling machine learning in JavaScript, and making it accessible for a wide range of applications. Each tool has its unique appeal, and the choice will depend on the context and specific requirements of the task at hand.


Please share with us about something you’ve built in the past using Google tools.

On our latest website, we use all the Google technologies at hand to enhance our image as an NGO. Find it here.


What will you create with Google Bard?

We are once again resuming a winning mentorship project to advance our career as developers, so Bard and Duet AI are great allies to inspect our code and once again create an MVP of this product for our community.


What advice would you give someone starting in their developer journey?

First, think about the problem you want to solve, or what you want to contribute to the world, then create and make it come true. This is easier if you rely on communities, and people who help you as mentors, sponsors and guides.


Rubens de Almeida Zimbres

Headshot of Rubens Zimbres, smiling
São Paulo - Brazil
Google Developer Expert, Machine Learning and Google Cloud
ML Engineer

What Google tools have you used to build?

I’ve been using the full stack of Google Products. I use Google Workspace daily in my life, my personal website is made on Google Sites, and Google Cloud; I started with Compute Engine and Jupyter Notebooks, customized to my needs.

As I acquired more knowledge through practical experience, Coursera and Google Cloud Skills Boost, I started building end to-end solutions using BigQuery, SQL, lots of Vertex AI (Generative AI Studio, Matching Engine, Speech-to-text, Pipelines, AutoML, Model Fine-Tuning), Cloud Run (and a little GKE - Kubernetes), Cloud Functions, Dialogflow and Document AI.

As the requirements of clients change according to the industry, like recruiting (Virtual Career Center) and contact center (Contact Center AI), I was able to test and deploy in production different Google products to solve the clients’ needs.


Which tool has been your favorite to use? Why?

Vertex AI is my favorite, as it is pure ML and Deep Learning optimized. Using AutoML with NAS (Neural Architecture Search) was a very interesting experience with awesome results. Developing Machine Learning pipelines with Kubeflow is a special pleasure, as this is going into production and the whole MLOps is involved.


Please share with us about something you’ve built in the past using Google tools.

I’ve built a recruiting solution that was implemented in six countries of Latin America, benefiting more than 365,000 people. This solution automatically analyzes resumes using OCR via Document AI.

I delivered a revenue prediction for a hotel chain using Tensorflow, where we increased the accuracy of the client’s model by 0.95%. I also built a Contact Center solution which uses Google Speech-to-Text and analytics to make management easier and also to generate strategic insights.

Lately, I was part of the team that delivered an end-to-end Virtual Career Center solution that matches job candidates to job vacancies using Vertex AI Matching Engine via text embeddings and SCANN. Both the recruiting solution and the contact center solution generated patents in Brazil, in the field of NLP (Natural Language Processing).


What will you create with Google Bard?

Google Bard is part of my daily routine. It helps me while coding, it helps me to plan trips, get to the right public transportation, visit interesting places around the world and it also helps by retrieving the Google search in an organized way, with updated content. My idea is to use Bard along with LangChain to perform optimizations in the finance industry.


What advice would you give someone starting in their developer journey?

Learn the basics first.

The temptation of learning this magnificent field as Machine Learning is gigantic, but coding is a great part of the solution. Learn to code properly, in whatever language you want. This brings efficiency and security if your solution needs to scale, decreasing infrastructure costs and improving user experience.

The same applies to Machine Learning: learn basic disciplines such as Calculus, Computer Science fundamentals and you will understand most of the content is shared today online. Only after learning ML you should dive into Deep Learning and the disciplines associated. Don’t fake it. Make it.

#WeArePlay | Meet Steven from Indonesia. More stories from around the world

Posted by Leticia Lago, Developer Marketing

As we bid farewell to 2023, we're excited to unveil our last #WeArePlay blog post of the year. From Lisbon to Dubai, let’s meet the creators behind the game-changing apps supporting communities, bringing innovation and joy to people.



We’re starting off in Indonesia, where Steven remembers his pocket money quickly running out while traveling around rural areas of Indonesia with his parents. Struck by how much more expensive food items were in the villages compared to Jakarta, he was inspired to create Super, providing more affordable goods outside the capital. The app allows shop owners to buy items stored locally and supply them to their communities at lower prices. It's helped boost the hyperlocal supply chain and raise living standards for rural populations. Steven is keen to point out that “it’s not just about entrepreneurship”, but “social impact”. He hopes to take Super even further and improve economic distribution across the whole of rural Indonesia.

ALT TEXT

Next, we’re crossing the Java Sea to Singapore, where twin brothers – and marathon runners – Jeromy and Kenny decided to turn their passion for self-care into a journaling app. On Journey, people can log their daily thoughts and work towards their mental health and self-improvement goals using prompts. With the guidance of coaches, they can practice gratitude, record their ambitions, and learn about mindfulness and building self-confidence. “People tell us it helps them find time to invest in themselves and dedicate space to self-care”, says Jeromy. In the future, the pair want to bring in additional coaches to support even more people to achieve their wellness goals.

ALT TEXT

Now we’re landing in the Middle East where former kindergarten friends Chris and Rene decided to use their experience being expats in Dubai to create a platform for connecting disparate communities across the city. On Hayi حي, locals can share information with their neighbors, find help within the community and connect with those living nearby. “Community is at the heart of everything we do and our goal is to have a positive effect”, says Chris. They’re currently working on creating groups for art and sport enthusiasts to encourage residents to bond over their interests. The pair are also dedicated to sustainability and plan on launching environmental projects, such as wide-scale city clean-ups.

ALT TEXT

And finally, we’re off to Europe where Lisbon-based university chums Rita, João and Martim saw unexpected success. Initially, the trio created a recipe-sharing platform, SaveCook. When they launched its accompaniment, Super Save, however, which compared prices of recipe ingredients across different supermarkets, it exploded in popularity. With rising inflation, people were hugely thankful to the founders “for providing a major service” at such a crucial time. Next, they’re working on a barcode scanner that tells shoppers where they can buy cheaper versions of products “to help people save as much as they can.”

Discover more founder stories from across the globe in the #WeArePlay collection.



How useful did you find this blog post?

Congratulations to the winners of Google’s Immersive Geospatial Challenge

Posted by Bradford Lee – Product Marketing Manager, Augmented Reality, and Ahsan Ashraf – Product Marketing Manager, Google Maps Platform

In September, we launched Google's Immersive Geospatial Challenge on Devpost where we invited developers and creators from all over the world to create an AR experience with Geospatial Creator or a virtual 3D immersive experience with Photorealistic 3D Tiles.

"We were impressed by the innovation and creativity of the projects submitted. Over 2,700 participants across 100+ countries joined to build something they were truly passionate about and to push the boundaries of what is possible. Congratulations to all the winners!" 

 Shahram Izadi, VP of AR at Google

We judged all submissions on five key criteria:

  • Functionality - How are the APIs used in the application?
  • Purpose - What problem is the application solving?
  • Content - How creative is the application?
  • User Experience - How easy is the application to use?
  • Technical Execution - How well are you showcasing Geospatial Creator and/or Photorealistic 3D Tiles?

Many of the entries are working prototypes, with which our judges thoroughly enjoyed experiencing and interacting. Thank you to everyone who participated in this hackathon.



From our outstanding list of submissions, here are the winners of Google’s Immersive Geospatial Challenge:


Category: Best of Entertainment and Events

Winner, AR Experience: World Ensemble

Description: World Ensemble is an audio-visual app that positions sound objects in 3D, creating an immersive audio-visual experience.


Winner, Virtual 3D Experience: Realistic Event Showcaser

Description: Realistic Event Showcaser is a fully configurable and immersive platform to customize your event experience and showcase its unique location stories and charm.


Winner, Virtual 3D Experience: navigAtoR

Description: navigAtoR is an augmented reality app that is changing the way you navigate through cities by providing a 3 dimensional map of your surroundings.



Category: Best of Commerce

Winner, AR Experience: love ya

Description: love ya showcases three user scenarios for a special time of year that connect local businesses with users.



Category: Best of Travel and Local Discovery

Winner, AR Experience: Sutro Baths AR Tour

Description: This guided tour through the Sutro Baths historical landmark using an illuminated walking path, information panels with text and images, and a 3D rendering of how the Sutro Baths swimming pool complex would appear to those attending.


Winner, Virtual 3D Experience: Hyper Immersive Panorama

Description: Hyper Immersive Panorama uses real time facial detection to allow the user to look left, right, up or down, in the virtual 3D environment.


Winner, Virtual 3D Experience: The World is Flooding!

Description: The World is Flooding! allows you to visualize a 3D, realistic flooding view of your neighborhood.


Category: Best of Productivity and Business

Winner, AR Experience: GeoViz

Description: GeoViz revolutionizes architectural design, allowing users to create, modify, and visualize architectural designs in their intended context. The platform facilitates real-time collaboration, letting multiple users contribute to designs and view them in AR on location.



Category: Best of Sustainability

Winner, AR Experience: Geospatial Solar

Description: Geospatial Solar combines the Google Geospatial API with the Google Solar API for instant analysis of a building's solar potential by simply tapping it.


Winner, Virtual 3D Experience: EarthLink - Geospatial Social Media

Description: EarthLink is the first geospatial social media platform that uses 3D photorealistic tiles to enable users to create and share immersive experiences with their friends.


Honorable Mentions

In addition, we have five projects that earned honorable mentions:

  1. Simmy
  2. FrameView
  3. City Hopper
  4. GEOMAZE - The Urban Quest
  5. Geospatial Route Check

Congratulations to the winners and thank you to all the participants! Check out all the amazing projects submitted. We can't wait to see you at the next hackathon.

It’s time for developers and enterprises to build with Gemini Pro

Posted by Jeanine Banks – VP/GM, Developer X and Developer Relations, and Burak Gokturk – VP/GM, Cloud AI and Industry Solutions

Learn more about how to integrate Gemini Pro into your app or business at ai.google.dev

This article is also published on the Keyword blog.

Last week, we announced Gemini, our largest and most capable AI model and the next step in our journey to make AI more helpful for everyone. It comes in three sizes: Ultra, Pro and Nano. We've already started rolling out Gemini in our products: Gemini Nano is in Android, starting with Pixel 8 Pro, and a specifically tuned version of Gemini Pro is in Bard.

Today, we’re making Gemini Pro available for developers and enterprises to build for your own use cases, and we’ll be further fine-tuning it in the weeks and months ahead as we listen and learn from your feedback.


Gemini Pro is available today

The first version of Gemini Pro is now accessible via the Gemini API and here’s more about it:

  • Gemini Pro outperforms other similarly-sized models on research benchmarks.
  • Today’s version comes with a 32K context window for text, and future versions will have a larger context window.
  • It’s free to use right now, within limits, and it will be competitively priced.
  • It comes with a range of features: function calling, embeddings, semantic retrieval and custom knowledge grounding, and chat functionality.
  • It supports 38 languages across 180+ countries and territories worldwide.
  • In today’s release, Gemini Pro accepts text as input and generates text as output. We’ve also made a dedicated Gemini Pro Vision multimodal endpoint available today that accepts text and imagery as input, with text output.
  • SDKs are available for Gemini Pro to help you build apps that run anywhere. Python, Android (Kotlin), Node.js, Swift and JavaScript are all supported.
A screenshot of a code snippet illustrating the SDKs supporting Gemini.
Gemini Pro has SDKs that help you build apps that run anywhere.

Google AI Studio: The fastest way to build with Gemini

Google AI Studio is a free, web-based developer tool that enables you to quickly develop prompts and then get an API key to use in your app development. You can sign into Google AI Studio with your Google account and take advantage of the free quota, which allows 60 requests per minute — 20x more than other free offerings. When you’re ready, you can simply click on “Get code” to transfer your work to your IDE of choice, or use one of the quickstart templates available in Android Studio, Colab or Project IDX. To help us improve product quality, when you use the free quota, your API and Google AI Studio input and output may be accessible to trained reviewers. This data is de-identified from your Google account and API key.

A screen recording of a developer using Google AI Studio.
Google AI Studio is a free, web-based developer tool that enables you to quickly develop prompts and then get an API key to use in your app development.

Build with Vertex AI on Google Cloud

When it's time for a fully-managed AI platform, you can easily transition from Google AI Studio to Vertex AI, which allows for customization of Gemini with full data control and benefits from additional Google Cloud features for enterprise security, safety, privacy and data governance and compliance.

With Vertex AI, you will have access to the same Gemini models, and will be able to:

  • Tune and distill Gemini with your own company’s data, and augment it with grounding to include up-to-minute information and extensions to take real-world actions.
  • Build Gemini-powered search and conversational agents in a low code / no code environment, including support for retrieval-augmented generation (RAG), blended search, embeddings, conversation playbooks and more.
  • Deploy with confidence. We never train our models on inputs or outputs from Google Cloud customers. Your data and IP are always your data and IP.

To read more about our new Vertex AI capabilities, visit the Google Cloud blog.


Gemini Pro pricing

Right now, developers have free access to Gemini Pro and Gemini Pro Vision through Google AI Studio, with up to 60 requests per minute, making it suitable for most app development needs. Vertex AI developers can try the same models, with the same rate limits, at no cost until general availability early next year, after which there will be a charge per 1,000 characters or per image across Google AI Studio and Vertex AI.

A screenshot of input and output prices for Gemini Pro.
Big impact, small price: Because of our investments in TPUs, Gemini Pro can be served more efficiently.

Looking ahead

We’re excited that Gemini is now available to developers and enterprises. As we continue to fine-tune it, your feedback will help us improve. You can learn more and start building with Gemini on ai.google.dev, or use Vertex AI’s robust capabilities on your own data with enterprise-grade controls.

Early next year, we’ll launch Gemini Ultra, our largest and most capable model for highly complex tasks, after further fine-tuning, safety testing and gathering valuable feedback from partners. We’ll also bring Gemini to more of our developer platforms like Chrome and Firebase.

We’re excited to see what you build with Gemini.

Bazel 7 Release

Posted by the Google Bazel team

Bazel 7 is now released. Bazel is Google's open source build system for fast and correct builds. It has built-in support for building both client and server software, including client applications for both Android and iOS platforms. It also provides an extensible framework that you can use to develop your own build rules. Bazel builds almost all Google products, including Google Search, GMail, and Google Docs.


What’s new in Bazel 7?

Bazel 7 is the latest major release on the long-term support (LTS) track. It includes:

Bzlmod: Bzlmod, Bazel's new modular external dependency management system, is now enabled by default (i.e. --enable_bzlmod defaults to true). If your project doesn't have a MODULE.bazel file, Bazel will create an empty one for you. The old WORKSPACE mechanism will continue to work alongside the new Bzlmod-managed system. Learn more about what’s changed since Bazel 6 and what’s coming up in Bazel 8 and 9.

Build without the Bytes (BwoB): Build without the Bytes for builds using remote execution is now enabled by default (i.e. --remote_download_outputs defaults to toplevel). Bazel will no longer try to download any intermediate outputs from the remote server, but only the outputs of requested top-level targets instead. This significantly improves remote build performance. Learn more about BwoB.

Merged analysis and execution (Skymeld): Project Skymeld aims to improve multi-target build performance by removing the boundary between the analysis and execution phases and allowing targets to be independently executed as soon as their analysis finishes.

Platform-based toolchain resolution for Android and C++: This change helps streamline the toolchain resolution API across all rulesets, obviating the need for language-specific flags. It also removes technical debt by having Android and C++ rules use the same toolchain resolution logic as other rulesets. Full details for Android developers are available in the Android Platforms announcement.


What's next?

Read the full release notes for Bazel 7, and follow along as we work together towards Bazel 8:

If you have any questions or feedback, or would like to share something you’ve built, reach out to [email protected]. We would love to hear from you!

Announcing the inaugural Google for Startups Accelerator: Women Founders program, Europe & Israel – applications now open.

Posted by Karina Govindji Senior Director – LEAD - Global Workforce Diversity, and Noa Havazelet – Head of Google's accelerator programs across Europe and Israel

Applications are also open for underrepresented founders in North America

Artificial intelligence (AI) stands at the forefront of transformative technologies, reshaping industries and redefining the way we live and work. Yet, a closer look at the AI startup ecosystem reveals a stark gender disparity. Women, despite their profound capabilities and innovative prowess, often find themselves navigating a maze of obstacles in their entrepreneurial journey. Despite investment in AI software is booming globally, the venture capital funding problem for women is even more marked. Women-founded startups accounted for only 2.1% of VC deals involving AI startups1. This is a reality that demands attention and action. Globally in 2023, all-women founding teams raised just 3% of all dollars invested in the year, with mixed gender founding teams taking 15%, leaving 82% of dollars to flow to founding teams that are all men2.

Google's accelerator programs have actively taken a leading role in championing diversity and empowering women and minority founders - having supported 1100+ startups across the globe since 2016, 36% of which are women-led startups. As such, we are pleased to announce the launch of the Google for Startups Accelerator: Women Founders program (Europe & Israel), a 12 week program for Seed to Series A AI startups based in Europe and Israel.

The Google for Startups Accelerator: Women Founders program (Europe & Israel) provides a comprehensive mix of mentorship, technical support, and workshops, establishing a robust foundation for participants. Beyond Google's expert guidance, the accelerator cultivates a collaborative network among women founders, propelling innovation within the tech startup space. By empowering women founders, the Google for Startups Accelerator: Women Founders program (Europe & Israel) proactively contributes to creating a more inclusive and equitable tech community.

Applications for the Google for Startups Accelerator: Women Founders Europe & Israel program are open until January 19th, 2024. You can learn more and apply here.

In a similar vein, in North America, two other Google for Startups Accelerator programs for underrepresented founders have opened applications for the fifth Women Founders and Black Founders programs. These 10 week equity- free programs are best suited for Seed to Series A, high potential revenue generative women-led and black-led startups with growing teams (5+ employees). Applications for both programs close on February 1st, 2024.

To further explore these opportunities and why you should apply - listen to what past participants of the North American Women Founder and Black Founder programs have to say here.



How it’s Made: Interacting with Gemini through multimodal prompting

Posted by Alexander Chen, Creative Director


Let’s try an experiment. We’ll show this picture to our multimodal model Gemini and ask it to describe what it sees:

A close up of a hand with five fingers spread out, palm facing down on a wooden surface.
Tell me what you see
Gemini:  I see a person's right hand. The hand is open with the fingers spread apart.

Ok, let’s try this one:

A closeup of the same hand, now balled up in a fist.
Gemini: A person knocking on a wooden door.

How about this one?

A closeup of the same hand, with two fingers extended like that of a peace sign.
Gemini: I see a hand with two fingers extended, which is a common symbol for the number two.

But wait … what if we asked Gemini to reason about all of these images together?

A sequence of three frames depicting the same hand in different formations. The first frame shows the hand with all five fingers spread out, palm facing down. The second frame shows the hand balled up in a fist. The third frame shows the hand with two fingers extended, like that of a peace sign.
What do you think I'm doing? Hint: it's a game.
Gemini: You're playing rock, paper, scissors.

Nice. What else could we try? Let's see if Gemini can notice this pattern:

A sequence of six frames that alternate between a hand that is balled up in a fist, and a hand that has two fingers extended.
I’m playing rock paper scissors. Do you notice a pattern in my gameplay?
Gemini: You are alternating between rock and scissors.

Neat, it spotted the pattern! But does Gemini really know how this game works? Let’s try asking:

Hmm ... do you think it's a good strategy?
Gemini: No, it is not a good strategy. Your opponent will quickly learn your pattern and will be able to win every time. You should try to randomize your choices more.

Good advice, Gemini! Okay, for this last one, let’s put your multimodal reasoning capabilities to the test. Here’s your prompt:

This is a secret message. What does it say?

A six by eight grid of frames of a hands balled up in a fist or the hand with all five fingers spread out, palm facing down. The series of photos spells 'Gemini' in ASCII binary.

Can you figure it out? We have gotten Gemini to solve it, but we won’t spoil it by putting the answer in this post. 🙂



What is multimodal prompting?

Everything we did just now is an example of “multimodal prompting.” We’re basically giving Gemini combinations of different modalities — image and text in this case — and having Gemini respond by predicting what might come next. Gemini’s ability to seamlessly combine these modes together enables new possibilities for what you can do.

In this post, we’ll explore some of the prompting approaches we used in our Hands on with Gemini demo video. We’ll soon be rolling out Gemini for people to try in Google AI Studio, our free, web-based developer tool where you’ll be able to try your own multimodal prompts with Gemini. We’re hoping this guide of starter prompts and ideas helps inspire you to start exploring your own ideas.



🧮 Spatial reasoning and logic

Logic and puzzles are fun way to test Gemini. Let’s try one that requires both left-to-right spatial reasoning and knowledge about our solar system:

Three sticky notes on a wooden surface, each featuring a hand-drawn sketch of a solar-body. The left-most note depicts a drawing of the sun. The middle note has a drawing of saturn. The right-most note shows a drawing of earth.
Is this the right order? Consider the distance from the sun and explain your reasoning.

Gemini: No, the correct order is Sun, Earth, Saturn. The Sun is the closest to the center of the solar system, followed by the Earth, and then Saturn.

Nice! Here’s another, inspired by pinewood derby challenges:

Two sticky notes depicting two different hand-drawn cars going down-hill. The car on the left is blocky and awkwardly shaped, the car on the right is slanted and smooth.
Which of these cars is more aerodynamic? The one on the left or the right? Explain why, using specific visual details.

Gemini: The car on the right is more aerodynamic. It has a lower profile and a more streamlined shape. The car on the left has a higher profile and a more boxy shape, which makes it less aerodynamic.



📷 Image sequences

Next, what if we showed Gemini a sequence of images? Let’s see we can show a few still frames from a game of charades and have Gemini guess the movie:

Four frames from a video of a person leaning back and moving their arms wildly.
Guess what movie I'm acting out.
Gemini: The Matrix
Nice! But which part specifically? Look at my body movements.
Gemini: The part where Neo dodges bullets.



🪄 Magic tricks

Exploring image sequences really lets you dig into how Gemini reasons over time. Let’s try a classic magic trick.

An image of two hands with palms facing the camera, there is a coin in the right hand.
Explain what I'm doing.
Gemini: You are holding a coin in your right hand.
An image of two hands in motion, palms turning inward and away from the camera.
An image of two hands, palms facing down and away from the camera.
Where do you think the coin is?
Gemini: The coin is in your right hand.

Sure, that’s a logical answer given what it’s seen. But let’s pull a sleight of hand as we reveal this next image to Gemini...

An image of two hands, the left palm is facing down and the right hand is tilted upwards revealing nothing under the right palm.
Look here, what happened?
Gemini: The coin is gone.

Gemini notices it’s gone. But can it summarize what may have happened?

Summarize what may have happened, step by step, starting with the first image.

Gemini: 
1. You started with a coin in your right hand.
2. You then made a motion with your hands, and the coin disappeared.
3. You then showed that the coin was gone.

Gemini is leveraging the entire context of this conversation – both text and image – to summarize its answer. Finally, let’s ask:

Can you explain how it disappeared?
Gemini: The coin was palmed.

Gemini makes a really solid guess! But we won’t reveal our secret 🙂.



🔀 Cup shuffling

Let’s try a trick that requires memory and logic: the classic ball and cup shuffling game. For this one, we’ll break it down into steps for Gemini. First, let’s establish the basics with these instructions:

Instructions: There are three cups in position 1 (left), position 2 (middle), position 3 (right).

Next, we’ll need to tell Gemini where we’re placing the ball:

Starting position: The ball is in position 3.
Current state: empty, empty, ball

Notice how we came up with a simple format for remembering where the ball is with “empty, empty, ball.” Next, let’s show Gemini two example turns:

Images:
Three frames depicting a person shuffling three green cups. The person switches positions of the middle and right-most cups. 
Swap: 2 and 3
Current state: empty, ball, empty

Images:
Three frames depicting a person shuffling three green cups. The person switches positions of the middle and left-most cups. 
Swap: 1 and 2
Current state: ball, empty, empty

In these two example turns, we’re both showing it what a swap looks like, and how to update the ball position. Now, let’s see if Gemini can generalize to a swap it hasn't seen:

Images:
Three frames depicting a person shuffling three green cups. The person switches positions of the left-most and right-most cups. 
Swap: 

Here's Gemini's response:

1 and 3
Current state: empty, empty, ball

Gemini got it! It looked at these images and correctly inferred that cups 1 and 3 are being swapped. And it reasoned correctly about how to update the ball position. Let’s ask:

Tell me where the ball is and summarize how it got there, in paragraph form.

Gemini: The ball is in cup 3. 

Starting with the ball in cup 3, the first swap was cup 2 and 3. This put the ball in cup 2. The second swap was cup 1 and 2. This put the ball in cup 1. The third swap was cup 1 and 3. This put the ball in cup 3.

Not only did Gemini get the answer correctly, it accurately summarized the game history. Of course, it won’t always get this challenge right. Sometimes the fake out move (where you swap two empty cups) seems to trip it up, but sometimes it gets that too. But simple prompts like this make it really fun to rapidly test Gemini. You can change the variables in your prompt, including the order of swaps, and see how it does.



🔨 Tool use

If you want to use Gemini in your own apps, you’ll want it to be able to connect to other tools. Let’s try a simple idea where Gemini needs to combine multimodality with tool use: drawing a picture to search for music.

A musical instruments and palm tree sketch on a notebook. The sketch features a guitar, an amplifier, a drum set, and a palm tree drawn in a loose and expressive style. The notebook sits on a wooden desk.
Step 1. Look at this drawing, describe everything in it, and come up with a fun, specific idea for a good musical soundtrack genre, mood, or soundtrack. 
Step 2. Provide a search query in the form: "Search [insert query]"

Gemini: 
The drawing is of a guitar, drums, and an amplifier. There is also a palm tree. The mood is fun, upbeat, and tropical. The genre is reggae. The soundtrack could be used for a movie or TV show set in a tropical location. 

Search "Reggae music for a tropical vacation"

Nice! Gemini both reasons about what it sees and then generates a search query you can parse to do a search. It’s like Gemini is acting like a translator for you – but instead of translating between languages, it’s translating modalities – from drawing to music in this case. With multimodal prompting, you can use Gemini to invent your own entirely new translations between different inputs and outputs.



🕹️Game creation

What if we tried using Gemini to quickly prototype a multimodal game? Here’s an idea: a geography guessing game where you have to point at a map to make your guess. Let’s start by prompting Gemini with the core idea:

Instructions: Let's play a game. Think of a country and give me a clue. The clue must be specific enough that there is only one correct country. I will try pointing at the country on a map.

Next, let’s give Gemini an example turn of gameplay, showing it how we want it to handle both incorrect and correct answers:

Country: This country is huge island that is mostly covered in ice.
(Answer: Greenland) 

Guess:
An image of a world map, a hand icon with the index finger pointing at Canada
I am pointing at the country of Canada *incorrect*

Guess:
An image of a world map, a hand icon with the index finger pointing at Greenland
I am pointing at the country of Greenland *correct*

Let’s give it a go and prompt Gemini to generate a clue:

Clue:
This country is known for its unique wildlife, including kangaroos and koalas. (Answer: Australia)

Ok, that’s a good clue. Let’s test out whether pointing will work. Just for fun, let’s try pointing at the wrong place first:

Guess:
A person pointing at Brazil on a map of the world with their right index finger. The map includes blue oceans, and green continents with no country borders.
I am pointing at the country of Brazil *incorrect*

Great! Gemini looked at my image and figured out I’m pointing at Brazil, and correctly reasoned that’s wrong. Now let’s point at the right place on the map:

A person pointing at Brazil on a map of the world with their right index finger. The map includes blue oceans, and green continents with no country borders.
I am pointing at the country of Australia *correct*

Nice! We’ve basically taught Gemini our game logic just by giving it an example. You'll also notice that it generalized from the illustrated hand in the examples.



⌨️ Coding

Of course, to bring your game idea to life, you’ll eventually have to write some executable code. Let’s see if Gemini can make a simple countdown timer for a game, but with a few fun twists:

Implement a simple timer in HTML/CSS/Javascript. Use a sans serif font and dark mode. Start it at 10 seconds and start counting down. When it reaches zero, replace the timer with a random emoji that is associated with excitement and motivation! Then go back to the timer at 10 seconds and start counting down again.

With just this single instruction, Gemini gives us a working timer that does what we asked for:

An animated gif of a countdown timer starting from 10. At the end of the countdown, a rocket emoji is shown followed lightning bolt emoji and a confetti emoji.

My favorite part is scrolling through Gemini’s source code to find the array of motivational emojis it picked for me:

 const emojis  = ['🚀', '⚡️', '🎉', '🎊', '🥳', '🤩', '✨'];



👀 A sneak peek

Throughout this post, we’ve been giving Gemini an input, and having Gemini make predictions for what might come next. That's basically what prompting is. And our inputs have been multimodal – image and text, combined.

But so far we've only shown Gemini responding in text. Maybe you’re wondering, can Gemini also respond with a combination of image and text? It can! This is a capability of Gemini called “interleaved text and image generation.” While this feature won’t be ready in the first version of Gemini for people to try, we hope to roll it out soon. Here’s a sneak peek of what’s possible.

Let’s see if we could use Gemini to provide everyday creative inspiration. And let’s try it in a domain that requires a bit of multimodal reasoning ... knitting! 🧶. Similar to our map game above, let's provide one example turn of interaction:

Give me three ideas for crochet creations I could make with these two colors:

Balls of blue and yellow yarn on a wooden table.

Colors: I see blue and yellow yarn.
Idea 1: How about a cute dog with one yellow ear? 
Image 1:

A blue and yellow crocheted dog head with ears placed on a wooden table.

Idea 2: Or how about a jellyfish with a few yellow tentacles?
Image 2:

A blue and yellow crocheted octopus with tentacles placed on a wooden table.

Idea 3: Or how about a blue cat with a yellow nose?
Image 3:

A blue and yellow crocheted cat with whiskers placed on a wooden table.

We’re essentially teaching Gemini about how we want each interaction to go: “I’ll take a photo of two balls of yarn, and I expect you (Gemini) to both come up with an idea for something I could make, and generate an image of it.”

Now, let’s show it a new pair of yarn colors it hasn't yet seen, and see if it can generalize:

Give me three ideas for crochet creations I could make with these two colors:

Balls of blue and pink yarn on a wooden table.

Gemini:
Colors: I see blue and pink yarn.
Idea 1: How about a pig with blue ears?
Image 1:

A blue and pink crocheted pig face with ears placed on a wooden table.

Idea 2: Or an octopus with pink and blue tentacles?
Image 2:

A blue and yellow crocheted octopus with tentacles placed on a wooden table.

Idea 3: Or a bunny with a pink nose?
Image 3:

A blue and pink crocheted bunny placed on a wooden table.

Nice! Gemini correctly reasoned about the new colors (“I see blue and pink yarn”) and generated these ideas and the images in a single, interleaved output of text and image.

What Gemini did here is fundamentally different from today’s text-to-image models. It's not just passing an instruction to a separate text-to-image model. It sees the image of my actual yarn on my wooden table, truly doing multimodal reasoning about my text and image together.


What's Next?

We hope you found this a helpful starter guide to get a sense of what’s possible with Gemini. We’re very excited to roll it out to more people soon so you can explore your own ideas through prompting. Stay tuned!

Global Google Developer Experts Share Their Favorite Tools and Advice for New Developers

Posted by Lyanne Alfaro, DevRel Program Manager, Google Developer Studio

Developer Journey is a monthly series highlighting diverse and global developers sharing relatable challenges, opportunities, and wins in their journey. Every month, we will spotlight developers around the world, the Google tools they leverage, and the kinds of products they are building.

This month we speak with global Google Developer Experts in Firebase, Women Techmakers, and beyond, to learn more about their favorite Google tools, the applications they’ve built to serve diverse communities, and their best advice for anyone just getting started as a developer.

Juan Lombana

Headshot of Juan Lombana, smiling
Mexico City, Mexico
Founder, Mercatitlán

What Google tools have you used to build?

Google Analytics and Firebase's A/B testing features have been pivotal in our data-driven approach, enabling continuous improvement in our conversion strategies. More recently, Bard has become a significant asset in developing new products and in our educational endeavors, especially with the introduction of our AI course. Its utility in both product development and educational settings is profound.


Which tool has been your favorite to use? Why?

If I had to choose, it would be Google Ads. Its ability to consistently drive new customers and provide unparalleled visibility to quality products is unmatched. While it may not traditionally be considered a 'tool' in the strictest sense, its impact on business growth and visibility is indisputable.


Please share with us about something you’ve built in the past using Google tools.

My entire business, Mercatitlán, has been built and scaled using Google Tools. We have cultivated a community of over 40,000 paid students, educating them on effective use of Google Ads, leveraging Bard for enhanced website content, and employing Google Analytics for strategic A/B testing to boost sales. The transformational impact of these tools on both my business and my students' ventures is a testament to their potential.


What will you create with Google Bard?

The integration of Bard AI into our daily operations is revolutionizing the way we approach digital marketing. Beyond its current uses in social media content creation, ad ideas generation, email composition, and customer support enhancement, we're exploring several innovative applications:

  • Personalized Marketing Campaigns: Using Bard AI, we can analyze customer data and preferences to create highly personalized marketing campaigns. This helps in delivering more relevant content to our audience, thereby increasing engagement and conversion rates. 
  • Competitive Analysis: By analyzing competitor data, Bard AI can help us understand their strategies, strengths, and weaknesses. This intelligence is crucial for refining our marketing approach and differentiating our brand in the marketplace.
  • Content Optimization for SEO: Bard can assist in optimizing website and blog content for search engines. By understanding and integrating key SEO principles, it can help us rank higher in search results, thus improving our online visibility. 
  • Automated Reporting and Insights: Automating the generation of marketing reports and insights with Bard saves time and resources, allowing our team to focus on strategy and creativity rather than manual data analysis.

What advice would you give someone starting in their developer journey?

The key is to start with action rather than waiting for perfection. Adopt a mindset focused on experimentation and analytics. This approach allows you to follow data-driven insights rather than solely relying on innovation, leading to significant societal impact through technology.


Jirawat Karanwittayakarn

Headshot of Jirawat Karanwittayakarn, smiling
Bangkok, Thailand
Tech Evangelist, LINE Thailand

What Google tools have you used to build?

I have used a variety of Firebase services to build LINE chatbots for a number of years. These services have included Cloud Functions, Cloud Firestore, Cloud Storage, Firebase Hosting, and etc. Recently I have also used the PaLM API, a very powerful tool that allows me to build Generative AI chatbots.


Which tool has been your favorite to use? Why?

Firebase is my favorite tool because it is a platform that provides a complete set of tools for building and managing mobile, web, and chatbots. It is very easy to use and has a wide range of features that make it a great choice for developers of all levels. Furthermore, Firebase services have allowed me to scale my chatbots and make them more reliable.


Please share with us about something you’ve built in the past using Google tools.

  • LINE Developers TH is a chatbot that allows Thai developers to learn about LINE APIs and get started with building services. It also provides users with the ability to try out demos of LINE APIs.
  • TrueMoney is a wallet app that I have built in the past using Firebase. The app allows users to store money, send money, and pay bills. It is a very popular app in Thailand, with over 10 million users.
  • Sanook is an app that allows users to access news, articles, and other content from the number one web portal in Thailand on their mobile devices.

What will you create with Google Bard?

I would like to create a use case of building a powerful LINE chatbot using PaLM API and Firebase for developers. I believe this will be a great way to showcase the power of these tools and how they can be used to create innovative solutions.


What advice would you give someone starting in their developer journey?

First and foremost, I would encourage them to be curious and always be willing to learn new things. The world of technology is constantly changing, so it's important to stay up-to-date on the latest trends and technologies. This can be done by reading articles, attending conferences, and taking online courses.

Secondly, I would recommend that they find a mentor or role model who can help guide them on their journey. Having someone who has been through the process can be invaluable in providing support and advice. They can help you identify areas where you need to improve, and provide you with tips and tricks for success.

Finally, I would encourage them to never give up. The road to becoming a developer can be challenging, but it's also incredibly rewarding. If you're passionate about technology, then don't let anything stop you from pursuing your dreams.


Laura Morinigo

Headshot of Lauren Moringo, smiling
London, England
Women Techmakers Ambassador
Principal Engineer and Consultant, Samsung Electronics UK

What Google tools have you used to build?

I have used tools like Google Cloud and Firebase.


Which tool has been your favorite to use? Why?

I would say Firebase! It helped me to build web apps and explore new technologies easily while saving a lot of time and resources. Additionally, a lot of functionalities have been added recently. Over the years, I've witnessed its evolution, with the addition of numerous functionalities that continually enhance its utility and user experience. This constant innovation within Firebase not only simplifies complex tasks but also opens doors to creative possibilities in web app development.


Please share with us about something you’ve built in the past using Google tools.

I've been leading a project in partnership with the United Nations to help share information about its worldwide global goals. We used Firebase hosting and Cloud functions for the first release of the web app and it was a success! It felt very good to help create tools that support a good cause.


What will you create with Google Bard?

I'm experimenting with the current extensions to improve personal productivity. It's very interesting how you can improve the way that you do your daily tasks.


What advice would you give someone starting in their developer journey?

Remember that as a developer you will have the power to create! Use this power to build personal projects and combine it with things that you enjoy. You will start building a portfolio and have fun while learning. Finally, don't hesitate to find a mentor and connect with a community of developers to support and guidance in your journey. You can find a lot of help, improve your networking, and even have friends for life!

Women in ML Symposium 2023: Meet the presenters



Posted by Sharbani Roy – Senior Director, Product Management, Google

We’re back with the third annual Women in Machine Learning Symposium on December 7, 2023

Join us virtually from 9:30 am to 1:00 pm PT for an immersive and insightful set of deep dives for every level of Machine Learning experience.

The Women in ML Symposium is an inclusive event for anyone passionate about the transformative fields of Machine Learning (ML) and Artificial Intelligence (AI). Meet this year’s women in ML as they uncover practical applications across multiple industries and discuss the latest advancements in frameworks, generative AI, and more.


Joana Carrasqueira, presenter for “Enabling Anyone to Build with Google AI”

Joana is a Developer Relations Lead for AI/ML at Google and her mission is to empower individuals and organizations to harness the power of AI to address real-world challenges.

She is a business leader with a track record of bringing strategic vision and global cross-functional programs to life. She’s also the creator of Google’s Women in ML program and flagship symposium, a pioneering initiative that has equipped thousands of developers with knowledge and skills in AI/ML.

Prior to Google, she worked at the Silicon Valley Innovation Center on innovation consulting for Forbes top500, startups and Venture Capital firms. Served as Education Manager at the International Pharmaceutical Federation, working closely with WHO, UNESCO, the United Nations and started her career at the Portuguese Pharmaceutical Society.

Joana holds an MBA from IE Business School, a Master in Pharmaceutical Sciences and a Leadership Certificate from U.C. Berkeley in California.



Sharbani Roy, presenter for “What’s New in Machine Learning?”

Sharbani is Sr. Director in Google’s Core Machine Learning group.

Before joining Google, Sharbani led engineering and product teams in Amazon Alexa, focused on media streaming, real-time communication, and applied ML (e.g., NLU, CV, and AR) for 1P/3P developers and end consumers.

Sharbani holds degrees in physics and mathematics from the University of Chicago and an MBA from Stanford University, and lives in Seattle with her husband and three children.



Eve Phillips, presenter for “Future of Frameworks: Navigate the OSS Landscape"

Eve is a Director of Product Management at Google.

Currently, Eve leads the ML Frameworks product team, which includes responsibility for TensorFlow, JAX and Keras. Previously, she led product teams within Google for Clinicians and ChromeOS. Prior to Google, she served as CEO of Empower Interactive, delivering tech-enabled behavioral health.

Earlier, she held roles in leading technology companies and investors including Trilogy, Microsoft, and Greylock.

Eve earned a BS and M.Eng in EECS from MIT and an MBA from Stanford.



Meenu Gaba, presenter for “Data-Centric AI: A New Paradigm"

Meenu leads the Machine Learning infrastructure team at Google, with a mission to power AI innovation with world-class ML infrastructure and services.

She is a technology leader with years of experience launching new products and growing small teams into mature scalable, multi-tiered organizations that are poised to deliver high quality products. Meenu enjoys fast-paced, dynamic, highly iterative/innovative environments and has lots of experience in balancing these disciplines while fostering a people-first culture and forming solid grounds for cross-functional relationships.

Meenu holds a Master's degree in Computer Science. In her free time, she enjoys hiking, solving crosswords, and watching movies.



Kelly Shaefer, presenter for “Maximize Your Data Exploration”

Kelly leads product teams at Google Labs, building both entirely new AI products and AI-enabled features into Google's largest existing products.

In the past, she led the Growth team for Google Workspace, including Gmail, Drive, Docs, and many more.

Outside of Google, she led the Enterprise product team at Stripe and was the P&L owner for Stripe's multi-billion dollar Payments area.

Kelly has an undergraduate degree from Wharton at UPenn, and an MBA from Harvard Business School.



Divyashree Sreepathihalli, presenter for “Keras: Shortcut to AI Mastery”

Divya is a talented machine learning software engineer who is currently a part of the Keras team at Google.

In this role, she specializes in developing Keras core modeling APIs and KerasCV to improve the functionality of the software.

Prior to joining Google, Divya worked as a Deep Learning Scientist for Zazu Sensor, a startup group in Intel's Emerging Growth Incubation (EGI) group. Her work there focused on computer vision and deep learning algorithm development for object detection and tracking, resulting in significant advancements for the startup.

Divya completed her Masters in Computer Engineering from Texas A&M University where she focused on Artificial intelligence in 2017.



Na Li, presenter for “Prototype ML with Visual Blocks”

Na Li is a software engineer manager from Google CoreML.

She leads a team to build developer tools to support ML development journey, from prototyping to model visualization and benchmarking.

Prior to Google, she was a research scientist at Harvard, working in HCI domain.

Throughout her career, Na strives to make ML accessible for everyone.



Zoe Wang, presenter for “Deploying ML Models to Mobile Devices”

Zoe is a technical program manager at Google.

Her career has been focused on Machine Learning (ML) productionization.

Currently she works with her team bringing ML models to mobile devices that power some of AI features for Pixel and other edge devices.

Prior to Google, Zoe worked at Meta on ML Platforms for end-to-end ML lifecycles.



Yvonne Li, presenter for “New GenAI Products and Solutions on Google Cloud”

Yvonne Li is a software engineer on the Duet Platform team at Google, where she focuses on improving the quality of generative AI models.

As a machine learning engineer and developer advocate at IBM, she designed and developed language models and curated open source datasets.

She has over 3 years of experience in the big tech industry, and is passionate about using machine learning to solve real-world problems.

Yvonne is the author of two Coursera courses: Data Analysis with R, and, Data Visualization with R.



Nithya Natesan, presenter for “AI-powered Infrastructure: Cloud TPUs”

Nithya Natesan is a Group Product Manager in the Cloud ML Accelerators team focussing on GPU / TPU offerings for Google Cloud.

Prior to Google, she was head of product management at NVIDIA, launching several products like DGX Cloud, Base Command Platform.

She has ~14 years of experience in hyper convergence Data Center software products, with recent focus on ML / AI Infra and Platform products. She is passionate about building rock solid PM teams, and shipping high quality usable ML / AI products.

Nithya has also won industry accolades namely WomenImpactTech 2023.



Andrada Vulpe, presenter for “Community Matters: 8 Reasons Why You Should Be Involved with Kaggle”

Andrada is a Data Scientist at Endava, a Notebooks Grandmaster on Kaggle, a Dev Expert at Weights and Biases and a proud Z by HP Data Science Global Ambassador.

She is highly passionate about Python, R, Machine and Deep Learning, powerful visualizations and everything in between.

Andrada finished her MSc in Data Science and Analytics in the UK and won 2 Kaggle Analytics competitions.



Jeehae Lee, presenter for “From Recovering Pro Golfer to AI Entrepreneur”

Jeehae Lee is a golf industry executive who has worked to create and build transformational sports technology businesses.

As the Co-Founder & CEO of Sportsbox AI, Jeehae is currently developing products using AI-enabled 3D motion analysis technology that will help participants of various sports and fitness activities learn and improve their skills.

Before founding Sportsbox, she spent five years between 2015 and 2020 at Topgolf Entertainment Group, leading strategy and new business development for various divisions including Toptracer. Between 2012 and 2013, she was at global sports and entertainment marketing agency, IMG, representing professional golfer icon Michelle Wie West. Prior to her career in sports business, she played professional golf at the highest level in the sport, competing on the LPGA tour for three years between 2009 and 2011.

Jeehae is a proud graduate of Phillips Academy in Andover, MA, and has a BA in Economics from Yale and an MBA from The Wharton School at University of Pennsylvania.



Jingwan (Cynthia) Lu, panelist for “The Impact of Generative AI in Different Industries”

Cynthia is a senior director from Adobe leading an applied research organization focusing on developing the Adobe Firefly family of GenAI models built from the ground up.

Her team started training Adobe’s first large-scale foundational model and helped rally together the rest of the company to roll out a new web-based product called Firefly featuring the image generation model as the first step in early 2023.

The same technology and its extension power Adobe Photoshop’s Generative Fill and Generative Expand features giving users intelligent image inpainting and outpainting experience. Time recognizes Adobe Photoshop Generative Fill and Generative Expand as best inventions of 2023 in the AI category.

Before Firefly, Jingwan was a computer vision research scientist and team lead who pioneered and led a large group effort to explore early generative models such as GANs within Adobe.



Wei Xiao, panelist for “The Impact of Generative AI in Different Industries”

Wei is the Director of Developer Relations at NVIDIA for the Middle East, Africa, and emerging regions. Her primary focus is to drive AI and accelerated computing integration within the ecosystem.

Before assuming her current role, Wei Xiao headed Ecosystem Engineering and Evangelism teams at both ARM and Samsung Semiconductor.

In addition to her professional endeavors, Wei dedicates her free time to teaching AI courses at the Graduate School of Computer Science at Santa Clara University.



Priya Mathur, panelist for “The Impact of Generative AI in Different Industries”

Priya is a Staff Data Science Manager at Google and she is the founder of Sparkle – GenAI Data Analyst.

At Google, she leads Data Science for Home Platform Monetization and GenAI efforts for DSPA.

Previously at Groupon, she led Data Science for App Push Notifications and TV Ads.



Katherine Chou, panelist for “The Impact of Generative AI in Different Industries”

Katherine is the Senior Director of Research and Innovations at Google with a specific focus on nurturing scientific and technical breakthroughs that can lead to global impact for science, health, climate, and advancement of platform technologies for our developers and researchers.

Katherine is focused on improving the availability and accuracy of healthcare using machine learning. She is a serial intrapreneur, particularly interested in removing health inequities and improving health and well-being outcomes across all populations.

She previously developed products within Google[x] Labs for Life Sciences (now Verily) and co-founded Medical Brain (now “Health AI'') at Google. She also headed up global teams to develop partner solutions and establish developer ecosystems for Mobile Payments, Mobile Search, GeoCommerce, YouTube, and Android.

Outside of Google, she is a Board member and Program Chair of Lewa Wildlife Conservancy, a Scientific Advisor to the ARCS Foundation, a fellow of the Zoological Society of London, and collaborates with other wildlife NGOs and the Cambridge Business Sustainability Programme in applying the Silicon Valley innovation mindset to new areas.

Katherine holds a double major in Computer Science and Economics at Stanford University and an M.S. in CS specialized in graphics.



Jaimie Hwang, presenter for “Take Action, Learn More, Start Building with Google AI”

Jaimie Hwang is a global product marketing leader with over a decade of experience, specifically in AI/ML.

She has built and led global product marketing teams at a number of AI companies, including an award-winning computer vision startup and tech giant Amazon.

She specializes in executive thought leadership, product storytelling, and integrated GTM strategy. She is passionate about promoting AI technology that is built responsibly and solves real-world problems in a human-centric way.

Jaimie holds a BS in Journalism and Integrated Marketing and Communications from Northwestern University. She lives in Seattle, Washington.


Save your spot at WiML Symposium 2023

The Women in ML Symposium offers sessions for all expertise levels, from beginners to advanced practitioners. RSVP today to secure your spot and explore our comprehensive agenda. We can’t wait to see you there!