Important Stay updated with the latest news from The Blaze Times! Follow our official WhatsApp channel: Click here to join

Welcome to AI on Android Spotlight Week

Posted by Joseph Lewis – Technical Writer, Android AI

AI on Android Spotlight Week this year runs September 30th to October 4th! As part of the Android “Spotlight Weeks” series, this week’s content and updates are your gateway to understanding how to integrate cutting-edge AI into your Android apps. Whether you're a seasoned Android developer, an AI enthusiast, or just starting out on your development journey, get ready for a week filled with insightful sessions, practical demos, and inspiring success stories that'll help you build intuitive and powerful AI integrations.



Throughout the week, we'll dive into the core technologies driving AI experiences on Android. This blog will be updated throughout the week with links to new announcements and resources, so check back here daily for updates!


Monday: Getting started with AI

September 30, 2024

Learn how to begin with AI on Android development. Understand which AI models and versions you can work with. Learn about developer tools to help you start building features empowered with AI.

We'll guide you through the differences between traditional programming and machine learning, and contrast traditional machine learning with generative AI. The post explains large language models (LLMs), the transformer architecture, and key concepts like context windows and embeddings. It also touches on fine-tuning and the future of LLMs on Android.

Read the blog post: A quick introduction to large language models for Android Developers


An illustration of a smartphone with a blank screen, set against a dark background. There is a blue speech bubble icon on the screen and a white speech bubble with ellipses above the phone. The design also incorporates blue and green lines and shapes.

A quick introduction to large language models for Android Developers

Explore key concepts and understand the differences between traditional ML and generative AI; discover resources to integrate gen AI into your apps.


We'll then provide a look behind the scenes at our work improving developer productivity with Gemini in Android Studio. We'll discuss Studio's new AI code completion feature, how we've been working to improve the accuracy and quality of suggested code, and how this feature can benefit your workflow.

Read the blog post: Gemini in Android Studio: Code Completion gains powerful model improvements


An illustration of a web browser window with the Android Studio logo in the bottom right corner. The background is dark with blue and green lines and shapes.

Generate useful prompts for app development in Android Studio

The Android Studio team has been experimenting with several enhancements to code completion, resulting in a 40% relative increase in acceptance rate.


Tuesday: On-device AI capabilities with Gemini Nano

October 1, 2024

We're excited to offer developers experimental access to the latest version of Gemini Nano starting with the Pixel 9 series devices. Access to experiment with Gemini Nano gives you the ability to test on-device integrations with your apps. Note that experimental access is for development purposes, and is not for production usage at this time.

Read the Gemini Nano experimental access blog post and developer guide.


An illustration of the Android bot and a smartphone on a dark background with glowing blue and green lines and shapes.

Gemini Nano is now available on Android via experimental access

Gemini Nano with Multimodality, Google's on-device generative AI model offers privacy, offline functionality, integration guides, and more.


As we bring powerful AI capabilities to your Android devices, we're equally committed to building privacy and safety into every interaction. Read our blog post for an intro into privacy and safety for Gemini Nano. It provides an introductory look into how Gemini Nano and AICore work together to deliver powerful on-device GenAI capabilities while prioritizing users’ privacy and safety.

Read the blog post: An Introduction to Privacy and Safety for Gemini Nano


An illustration of a smartphone on a dark background with a shield icon and a graphic that looks like a molecule, along with green lines and shapes.

An Introduction to Privacy and Safety for Gemini Nano

Gemini Nano and AICore work together to enable on-device generative AI while preserving user privacy and safety.


Ready to dive into the technical side of things? This video walks you through the process of accessing and utilizing Gemini Nano's capabilities, and how you can use open models on Android-powered devices. Discover how to integrate this cutting-edge technology into your own applications and unlock the potential of on-device AI. Whether you're a seasoned developer or just starting your AI journey, this video provides valuable insights and practical knowledge.

Watch the video: A Walkthrough for Android’s on-device GenAI solutions



Wednesday: On-device AI with custom models

October 2, 2024

On Wednesday, we'll help you understand how to bring your own AI model to Android devices, and how you can integrate tools and technologies from Google and other sources. The ability to run sophisticated AI models directly on devices – whether it's a smartphone, tablet, or embedded system – opens up exciting possibilities for better performance, privacy, usability, and cost efficiency.

Read the blog post: How to bring your own AI model to Android devices


An illustration of the metallic Android bot standing to the left of the MediaPipe and LiteRT logos.

How to bring your own AI model to Android devices

Bring your AI models to Android devices using Google's AI Edge platform, with tools and frameworks for building, deploying, and optimizing AI models.


We'll also give you a detailed walkthrough of how Android developers can leverage Google AI Edge Torch to convert PyTorch machine learning models for on-device execution, using the LiteRT and MediaPipe Tasks libraries. This walkthrough includes code examples and explanations for converting a MobileViT model for image classification and a DIS model for segmentation, and highlights the steps involved in preparing these models for seamless integration into Android applications. By following this guide, developers can harness PyTorch models to enhance their Android apps with advanced machine learning capabilities.

Read the blog post: PyTorch Machine Learning Models on Android


An illustration of the Android bot, with a colorful, iridescent finish, standing to the right. The Google AI Edge logo is in the center, with a chat bubble on the left

PyTorch Machine Learning Models on Android

Use Google AI Edge Torch to convert PyTorch models for use on Android devices. Convert a MobileViT model for image classification and add metadata.



Thursday: Access cloud models with Android SDKs

October 3, 2024

Tap into the boundless potential of Gemini 1.5 Pro and Gemini 1.5 Flash, the revolutionary generative AI models that are redefining the capabilities of Android apps. With Gemini 1.5 Pro and 1.5 Flash, you'll have the tools you need to create apps that are truly intelligent and interactive.

On Thursday, we'll give you a codelab that'll help you understand how to integrate the Gemini API capabilities into your Android projects. We'll guide you through crafting effective prompts and integrate Vertex AI in Firebase. By the end of this hands-on tutorial, you'll be able to implement features like text summarization in your own app all powered by the cutting-edge Gemini models.

Try the codelab: Add Gemini capabilities to your Android app


Three side by side screenshots show the Jetnews application on device, including the home screen, a screen listing articles related to Android development, and an article view.

Add Gemini capabilities to your Android app

Learn how to add a simple Gemini API feature to an Android app with Vertex AI for Firebase.



We'll publish a blog post exploring the potential of the Gemini API with case studies. We'll delve into how Android developers are leveraging generative AI capabilities in innovative ways, showcasing real-world examples of apps that have successfully integrated the Gemini API. From meal planning to journaling and personalized user experiences, the article highlights examples of how Android developers are already taking advantage of Gemini transformative capabilities in their apps.

Read the blog: Gemini API in Action: Showcase of Innovative Android apps


An illustration of a smartphone with a blank screen, set against a dark background. There is a blue speech bubble icon on the screen and a white speech bubble with ellipses above the phone. The design also incorporates blue and green lines and shapes.

Gemini API in action: showcase of innovative Android apps

Enhance user experience in your app with features like meal planning, journaling, and username generation by leveraging the power of generative AI.



We've recorded a podcast episode with Jomin George from the team behind Life, a journaling app that integrated the Gemini API. Jomin shared his experience building a chatbot with Vertex AI in Firebase.

Listen to the podcast: Integrating Gemini API in Android or watch the video version.


An illustration of  The Android bot, wearing black headphones, peeks over the top of text that reads 'Android Build Time'.

Android Build Time with Christopher Cartland

Welcome to Android Build Time! Listen to this episode to learn more about how you can leverage Gemini API in your app.



We'll also share with you examples of advanced features of the Gemini API to go beyond simple text prompting. You'll learn how system instructions can shape the model behavior, how JSON support streamlines development, and how multimodal capabilities and function calling can unlock exciting new use cases for your apps.

Read the blog: Advanced capabilities of the Gemini API for Android developers


An illustration of a smartphone with a blank screen, set against a dark background. There is a blue speech bubble icon on the screen and a white speech bubble with ellipses above the phone. The design also incorporates blue and green lines and shapes.

Advanced capabilities of the Gemini API for Android developers

Developers can leverage advanced features of the Gemini API, like JSON support and function calling, to build generative AI features into their apps.


Friday: Build with AI on Android and beyond

October 4, 2024

As the capstone for AI on Android Spotlight Week, we'll host a discussion with Kateryna Semenova, Oli Gaymond, Miguel Ramos, and Khanh LeViet to talk about building with AI on Android. We'll explore the latest AI advancements tailored for Android engineers, showcasing how these technologies can elevate your app development game. Through engaging discussions and real-world examples, we will unveil the potential of AI, from fast, private on-device solutions using Gemini Nano to the powerful capabilities of Gemini 1.5 Flash and Pro. We'll discuss building generative AI solutions rapidly using Vertex AI in Firebase. And we'll dive into harnessing the power of AI with safety and privacy in mind.

Watch the video: Build with AI on Android and beyond



Work with Gemini beyond Android

As we wrap things up for AI on Android Spotlight Week, know that we're striving to provide comprehensive AI solutions for cross-platform Gemini development. The AI capabilities showcased during Android AI Week can extend to other platforms, such as built-in AI in Chrome. Web developers can leverage similar tools and techniques to create web experiences enhanced by AI. Developers can run Gemini Pro in the cloud for natural language processing and other complex user journeys. Or, you explore the benefits of performing AI inferenceclient-side, with Gemini Nano in Chrome.

Build with usability and privacy in mind

As you embark on your AI development journey, we want you to keep in mind a few important considerations:

    • Privacy: Prioritize user privacy and data security when implementing AI features, especially when handling sensitive user information. When it becomes available, opt for on-device AI solutions like Gemini Nano whenever possible to minimize data exposure.
    • Seamless user experience: Ensure that AI features seamlessly integrate into your app's overall user experience. AI should enhance the user experience, not disrupt it.
    • Ethical considerations: AI technologies are developed and deployed in a way that benefits society while minimizing potential harm. By considering fairness, transparency, privacy, accountability, and societal impact, developers can play a vital role in creating a future where AI serves humanity's best interests. Be mindful of the ethical implications of AI, such as potential biases in your AI models. Strive to create AI-powered features that are fair and inclusive.

That's a wrap

Android AI Spotlight Week 2024 is an opportunity to explore the latest in AI and its potential for Android app development. We encourage you to delve into the wealth of resources shared during the week and begin experimenting with AI in your own projects. The future of Android is rooted in AI and machine learning, and with the tools and knowledge shared during Android AI Week, developers are well-equipped to build the next generation of AI-powered apps.


Next Steps

If you are building generative AI features we would love to have a conversation with you! Complete this form to keep in touch.

Follow Android Developers on X and Android Developers at LinkedIn, and remember to use the hashtag #AndroidAI to share your AI-powered Android creations, and join the vibrant community of developers pushing the boundaries of mobile AI.

Creative Director | Designing Impactful Visual Stories | Transforming Ideas into Engaging Experiences

Post a Comment