Developer Keynote (Google I/O '26)

♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ [Applause] >> JOSH WOODWARD: All right! Welcome back, developers! How's everybody doing? [Cheering] All right! It's great to see you again, and it's wild to think back about where we were just a year ago. This morning, you've heard all about the advancements across Gemini. We've got the new Omni model, the new Gemini 3.5 series models and last month, we also shipped Gemma 4, under an Apache 2 license. It's our smartest open model yet. It's purpose built for advanced reasoning, agentic workflows, and the response has been incredible: 100 million downloads in the first month, and it's pushing Gemma downloads past half a billion. [Applause] Gemma 4 packs massive intelligence into a footprint small enough to run offline on your phone, and it's deployed in everything, from robots to satellites in outer space. And as you saw this morning, the big shift is our move towards agents, from AI that simply assists you to agents that help you get stuff done under your direction and faster. At the center of it all is Google Antigravity. It's our agentic development platform that enables you to build with agents. The core platform is the Antigravity agent itself, and today, we're going to show you how you can build with it anywhere, on our infrastructure, or your own; on Android or the web. And when you step back, you can see how all of these pieces are coming together across Google, from the cutting-edge model, to the agentic tools like Antigravity, to the platforms where users experience the magic, and to the infrastructure that makes it all possible. We're working up and down the stack to help you build. So let's jump into some demos and keep the launches rolling! Please welcome Logan to the stage. [Applause] ♪ ♪ >> LOGAN KILPATRICK: Thanks, Josh. Our latest models help you build for the next era of agents. And we're putting the full power of agents directly into your hands no matter what you're building. Need complex research done? Check. A Data Science task? Check. Your own personal radio show? We'll get to that one. Last December, we introduced the Interactions API. It gives you one simple and powerful interface for both models and agents. Deep Research was the first agent we made available through the Interactions API. It showed what's possible when you give a model a goal and the freedom to go find the answer. But Deep Research was just the beginning. Inside Google, we're using the Antigravity Harness to empower our agents to intelligently tackle the most complex tasks. It's the same technology behind Gemini Spark and our coding agent and Google AI Studio. And today, we're making that same Antigravity harness available to you, with managed agents in the Gemini API. [Applause] You can easily start creating your agents by adding custom instructions, tools, and data through a single call to the Gemini API. But building agents is one part of the puzzle. In production, these workloads need secure, isolated execution. And solving that on your own is an infrastructure nightmare. That's why every managed agent comes paired with a remote Linux environment hosted by Google. In a single API call, you get the agent and the sandbox. We handle infrastructure so you can focus on building. We've been testing this with developers both internally and externally. To give you an example, our team at Stitch, our vibe design product in Labs, used Managed Agents to enable their users to import their project's design system directly from their codebase. Their managed agent connects to a user's GitHub repo, analyzes the codebase and generates a ready-to-use design.md file giving Stitch everything it needs to create on-brand designs. And because it's a managed agent, we handle the infrastructure so Stitch can scale to millions of users. Now, Stitch is just one example of how powerful managed agents can be. Externally, early access customers like Ramp, Resemble AI, and Klipy, are also seeing the power of building agents at a pace like never before. And we can't wait to see what you build. Managed agents are available starting today, and thanks to our ecosystem partners, you can start building with your preferred stack from day 1. Let's jump into a demo. I'm here in the AI Studio playground, where earlier this year, we added support for interacting with agents. To help get you started, we've added a set of new custom agents that you can run instantly. These open-source agent templates come preloaded with instructions, skills and tools as markdown so you can customize the source files like in this Customer Support Agent. So I told you I would come back to my own personal radio show, so let's select the AI talk radio agent. This agent can produce a complete talk radio show about anything you want. You give it a topic and it handles the rest. Of course, I want mine to cover today's top tech news, so let's see what the Hacker News comments have to say. I've asked it to generate a five-minute radio show based on the latest news from Hacker News. What's happening right now is the agent's environment is provisioning, and it's getting ready to run. While that happens, let me show you what's under the hood. In the Agents.md file, you can see we created a specific set of skills for the agent to produce the show, research to pull top text stories from Hacker News, script writing to compose the show script, TTS generation to generate multiple speaker voices, music generation with Lyria to create dynamic background music and audio mixing to bring it all another. Finally, it generates metadata, uses Nano Banana for cover art, and saves a complete ready-to-stream MP3 in its sandbox environment. I didn't write any orchestration logic; I simply defined the skills and tools and markdown files, and the agent does the rest. Honestly, it feels like the hottest new programming language is markdown, and I'm here for it. Since the agent is taking care of everything, it's going to take a few minutes. Let's switch to a tab where the agent finished and left us a nice summary of its work. Research, script, speech, music, mixing, and image generation completed, all from one API call. The playground in AI Studio is great to see what Gemini models and agents can do, but the real magic begins when you bring this to real apps and to show you that magic, here's Paige. ♪ ♪ [Applause] >> PAIGE BAILEY: Awesome! Thank you, Logan! Google AI Studio is the fastest path from prompt to app so let's dive in. I've always wanted to build my own personalized radio station to get the latest news that I care about, and it's not just because Logan just showed us what his AI talk radio agent can do. Okay, maybe. Earlier today, I took the AI radio show agent and wrapped it in a real app with just a few prompts. Since I'm also a huge fan of Hacker News, let's go ahead and give it a try. Just like Logan showed in the playground, my app is calling a managed agent on the Gemini API. The agent spins up in a sandbox environment, reads through the skills, makes a plan and then assembles the complete episode. This is going to take a minute to generate, so I'll switch over to where I ran it a little bit earlier today. Let's hear what Hacker News has to say. >> If you can go from writing 200 lines of code a day to 2,000 with an AI agent, are you actually a better engineer? Or are you just vibing? >> PAIGE BAILEY: Awesome, pretty cool, right? [Applause] Excellent. As you can see, the agent generated the MP3 for the show and created metadata to display the script. So now, I can even jump to different speakers in the show. >> And for the accessibility community, it's massive. >> PAIGE BAILEY: This is so cool. The app defines the UX, and then the agent creates the content and metadata needed for it on the fly. And I love this fun cover art that was generated with Nano Banana. Logan showed you how the playground lets you experiment and what I just showed you is how Build lets you ship. And speaking of shipping, let's go ahead and deploy my app so I can share it with the world. Deploying from AI Studio to Cloud Run is just a few clicks. You can either pick an existing Google Cloud project, or if you don't have one, AI Studio will generate one for you. And starting today, brand-new users can deploy to a live URL on Cloud Run instantly, no credit card required. [Applause] Awesome! Now, while we're waiting, Cloud Run is just our latest integration. We recently rebuilt our coding agent with Antigravity, and added Firebase and Firestore support so you can easily build real-world, full-stack apps backed with databases and OAuth. And today, we're officially announcing support for Google Workspace. [Applause] Yeah! Clap! You can just prompt to connect apps like Docs and Gmail and Calendar and stay completely in the flow. And if you combine that with multichat, web search, image generation with Nano Banana, we Are completely redefining what you can build with agents.. And it looks like my app has deployed so you can see right here, the status, the live URL and even unpublished right here without leaving AI Studio for a second. That really was pretty magical. I love that I can deploy by web app in minutes. But what good is a radio show if I can't listen on the go? So starting today, you can go from an idea to an Android app directly in AI Studio. No software to install, no SDKs to manage, and no local environment needed. [Applause] Hallelujah! Awesome. Yep. To start, all you have to do is select build an Android app and start prompting. Let's switch to one I baked a little bit earlier today. I used the same exact prompts, but this time I asked the agent to build an Android app. Notice the app is built entirely in Kotlin. [Applause] You can preview your new app with the Android Emulator directly in AI Studio. When I'm ready to start testing on my own device, I simply plug in my phone to install it. We're also adding support for Google Play Store publishing in AI Studio. [Applause] Keep clapping! I just open Publish, connect my Play Developer Account, and push The app straight to the test track in minutes and after that, it's ready to install on my phone without ever leaving AI Studio. You can start testing it on your own device today and sharing with trusted testers will roll out later this summer. [Applause] But speaking of apps, great ideas don't just happen at your desk. And that's why we're bringing the AI Studio build experience to your pocket with our brand-new mobile app. [Applause] Yes! The app rolls out in a few weeks, and you can preregister today. With managed agents, you get serious power without the complex setup, but if you want total programmatic control to customize and deploy on your own terms, today, we're launching the Antigravity SDK. It gives developers and researchers the exact same agent harness optimized for Gemini, but with the ultimate flexibility to run it wherever, and however you want. And now, of course, building a great agent just isn't a single event; it's an entire life cycle from that first spark of an idea to a deployed application. And while Google AI Studio is the fastest path from prompt to app, as your team evolves, moving to a local development platform can help with faster iteration. Moving y'all's projects used to mean copying files, losing context, and completely rebuilding states. But not anymore. Today, we're launching a one-click export to Antigravity. And we aren't just sending snippets; we are porting the complete file system and every single ounce of context, so you can pick up exactly where you left off in AI Studio. [Applause] And now, to show you what we're cooking in Antigravity itself, please welcome Anshul! ♪ ♪ [Applause] >> ANSHUL RAMACHANDRAN: All right! Let's talk more about agents, shall we? We aren't just making it easier to build agents; we're making it easier to build with agents. As you heard earlier today, we're introducing Google Antigravity 2.0, a new desktop application that is unabashedly agent first. You can kick off multiple agents in multiple projects simultaneously. One agent vibe-codes your marketing website; another generates brand assets; and a third plans your project architecture, operating in multiple work-trees, collaborating without collisions. For coding tasks, you can use Antigravity 2.0 alongside your IDE of choice, but we all know there is much more to do than just code. Antigravity 2.0 is your mission control for orchestrating agents for all sorts of tasks. Now, we've all seen single agents get overwhelmed by massive tasks. That's why today, we're introducing the Dynamic Subagents. Now, your agent can spin up specialized helpers like a QA or Data Science subagent that work in parallel to get the job done faster and more effectively. Now, that might sound impressive, but what if you want the process to run autonomously? For example, you might have tasks that you want agents to repeat on a predefined schedule. Today, we are making that a reality with Scheduled Tasks. You can now use standard chron scheduling to put your agents on Autopilot. So tell your agent to summarize pending PRs every morning or monitor your cloud health every hour. And this is just the beginning of making your agents truly proactive. To show you Antigravity 2.0 in action, let's invite Kevin on stage. [Applause] >> KEVIN HOU: Thanks, Anshul. Let's give Antigravity 2.0 a challenge. As you heard from Josh at the beginning, the momentum we're seeing behind Gemma 4 is absolutely incredible. Democratizing AI means allowing anyone to take open models like Gemma 4 and fine-tune them. Historically, that meant complex pipeline wrangling by ML engineers. Not anymore. With Antigravity, anyone can do it. Let me show you. The other day, my CI pipeline broke, which gave me this idea: Why not have an LLM automatically self-heal the pipeline? I would just feed it the stack trace with the build errors and say "fix this" to generate a remediation BASH command. Anshul, can you explain while I get this set up? >> ANSHUL RAMACHANDRAN: Yes. The challenge is that LLMs have been trained to be conversational so they bury the bash command in paragraphs of explanation. In fact, when we asked for a simple GIT work tree command earlier, the response came back with two separate code blocks, a conversational introduction and a detailed breakdown explaining how to choose branch names, but all Kevin cares about is the command. So what he needs to do is fine-tune Gemma 4 not to return the fluff and just give him the command. >> KEVIN HOU: Exactly. And rather than watch my type, let's go ahead and use the mic, powered by our latest audio understanding capabilities. Okay. So I want to fine-tune Gemma 4 to directly give me a bash command response with no additional fluff so I can use the response directly in my CI pipeline. I have a data set of prompt-to-bash commands, write the training and eval code for doing a LoRA fine-tuning over this data set, as well as the code to deploy my custom Gemma 4 model on my laptop. >> ANSHUL RAMACHANDRAN: As Kevin runs that, I want to highlight a couple of things. He was able to use just his voice, and the audio model recognized terms, like "LoRA". It seems like the agent's done some research, and it's generating an entire implementation plan for the training code. >> KEVIN HOU: I approved the implementation plan, and it's writing a bit of code to make this happen. Once this is done, I'm going to take this and push it to my repo and because we're training a model, I'll need a GPU-enabled cloud machine. >> ANSHUL RAMACHANDRAN: So while Kevin does that, you just saw Antigravity 2.0, our new stand-alone app that is your mission control for orchestrating agents. But we know that for a lot of developers, the real magic happens in the terminal. So that's why we're thrilled to announce the Antigravity CLI. [Applause] It's a lightweight way to spin up the same Antigravity agents right from the terminal. It gives you the exact same harness, and the same models, but with a product experience that is tailored for the command line. It adapts entirely to you: Your Themes, your workflows, your key bindings. Kevin, are we good to go? >> KEVIN HOU: We're all set. Let's pick up where I left off. I've SSH'ed into my GPU-enabled VM and, as you can see, I just pulled down the training and eval code. I already have the Antigravity CLI installed on this machine And it's running in a separate tab, no GUI necessary. >> ANSHUL RAMACHANDRAN: We know that GUI versus CLI is mostly a preference, but Kevin is already in the terminal, SSH'ed into a machine, the CLI is perfect. >> KEVIN HOU: So I just asked the agent to start the training Job that we just wrote. And to give you a little bit of context, this is a lightweight LoRA fine-tune but even so this is going to take some time before we get results. While it's cooking, let's take a step back for a minute. In minutes we used Antigravity to go from no code to starting a fine-tune of Gemma 4 on our own custom use case. And if all that seems a little too simple, that's the point. Antigravity makes building something of this scale not just possible, but way easier than you would expect. All right. Now that it's been a few moments, let's use the CLI to do a quick sanity check on the first few steps to make sure the loss is trending in the right direction and everything is healthy. I'll head over to my agent and ask, how is the training run going? Is everything healthy? As you can see, it's going to look through some of the output files, actually read the code that it wrote in 2.0, tell us that it needs to look at a couple of the log files and hopefully will give us some indication of how training is going. Looking through the task logs, and you see that sleep 10, it looks like training has not progressed long enough for us to actually get meaningful results so let's come back in a couple of seconds. >> ANSHUL RAMACHANDRAN: Sure. We have some time. Let's ask Gemini for a joke. Using the brand-new slash btw command. >> KEVIN HOU: So I used slash btw in the same conversation will effectively fork and you can see this amazing joke. Why did the neural network refuse to run on the TPU? Because it heard the TPU was always a bit too tensor. >> ANSHUL RAMACHANDRAN: I think we'll give it a 5 out of 10. We'll talk to the Gemini team about humor. Let's scroll back up, because we saw some of the training results. >> KEVIN HOU: So it looks like it did about 1%. It says the gradient norm is stable so it looks like things are going well, I imagine this will probably take some time to finish. >> ANSHUL RAMACHANDRAN: The loss is turning down nicely, the run is perfectly healthy, but we'll fast forward a bit and keep this one cooking in the background. >> KEVIN HOU: Sure. In fact, I actually kicked off the same exact run earlier, I let it run for a few hours so I'm going to use that checkpoint and ask my agent to deploy that resulting model to my laptop so we can all see that this does indeed work. I'll head back over to Antigravity 2.0, I'm going to start a new conversation, and I'm just going to instruct it to run the playground using the fine-tuned model that is specified at this particular path from earlier. As you can see, it is running the server and if we click over here, you can see the logs. It looks like it's running this particular model. It's also starting the client. And if I just go ahead and click on the link that it's telling me to click, and try that same exact prompt in the same playground that you saw earlier, we now see a fine-tune where we just get the command, none of the additional fluff. [Applause] So we just fine-tuned j Gemma 4n stage, which is pretty remarkable and this is really the new reality of building, your workflows across surfaces you already use. >> ANSHUL RAMACHANDRAN: Awesome Thanks, Kevin. >> KEVIN HOU: Thank you. [Applause] >> ANSHUL RAMACHANDRAN: Wrapping up, on the Antigravity CLI, we are unifying on Antigravity as the only platform you need for agent-first development. We took everything we learned from how you use Gemini CLI and rolled those insights into the Antigravity CLI as well, so starting today, the Antigravity CLI is available to all Gemini CLI users. We've published the migration guides to help you port your custom skills over and as always, send us your feedback as you get started. You'll now get the same harness as Antigravity 2.0, and a unified agentic experience across all of your surfaces. All right. Let's move along. Antigravity is completely stack agnostic, letting you use the tools you love with zero vendor lock-in. However, if you are building in the Google ecosystem, we've made it easy with one-click setup across Android, Firebase, and building on the web. [Applause] We're also making it easier to push agents into highly specialized fields by introducing domain-specific skills bundles. Starting today, our first release is a new science skill bundle, equipping your agents with the specific primitives needed to accelerate health, biology, and scientific research workflows. [Applause] All right, everything you just saw is incredible for individual developers, but we are not stopping there. Today, for enterprises, we're allowing Antigravity to be connected directly to your Google Cloud projects, applying the same enterprise terms that you expect. And for our existing Gemini Enterprise customers, you'll soon see Antigravity rolled out in the coming months. [Applause] From cutting-edge research to standard enterprise apps, whether you're one developer with an idea or an organization deploying at scale, Antigravity is your platform. Now, let's take a deep dive into these agentic workflows for your Android development. Here to show us how it's done, please welcome Florina and Adarsh. ♪ ♪ [Applause] >> FLORINA MUNTENESCU: No matter where you are in your development journey, we want to make it fast and easy to build high-quality Kotlin Android apps. As Paige showed you earlier, native Android development is fully supported in AI Studio. Today, we're also bringing official Android support to Antigravity, so you can more easily deliver the most performant experiences for your users, no matter where they are or what kind of devices they have. We want to ensure you have access to the latest innovations on the Android platform, and that's building for the newer form factors is frictionless. >> ADARSH FERNANDO: Okay, we'll have a few demos in the next few minutes, but not that much time. So let's rely on our latest skill: Time travel! We'll use it every once in a while to jump into the future and check out the results. For the demos, we've created a travel app. You can use it to view all your travel plans in one place, or transcribe audio diary entries using our latest on-device model, Gemini Nano 4. >> FLORINA MUNTENESCU: So using Antigravity, let's show how you can build an augmented experience today for Display Glasses. [Applause] >> ADARSH FERNANDO: Now, setting up the environment without Android Studio is kind of a pain, but now, Antigravity has our new Android CLI built in. Now, that it's stable, it comes with a set of tools for agents to handle everything, from downloading the SDK, creating a project, and running your app on devices, all much more easily and efficiently. Okay. Flo, for this app, we've heard from our users they really wish there was an easier way to view important travel info when they're on the go. So let's try this out. In a single prompt, let's add the capability to display updated flight and travel information directly on the glasses, which could be pretty useful for users at the airport with their hands full. >> FLORINA MUNTENESCU: Building for display glasses is new and most LLMs don't know how to do this yet. So as part of Android CLI, we're giving our models access to the latest information with two key resources. First, the Android Knowledge Base. It's our specialized data source that enables agents to search and fetch the latest developer guidance. And second, we open-sourced Android Skills to help LLMs understand and execute best practices. For example, you've told us that building support for edge-to-edge, migrating from XML to Compose or to Jetpack Navigation 3 is time consuming. So we made sure to add skills to help with just that. >> ADARSH FERNANDO: We saw in our internal testing agents leveraging Android CLI skills and Knowledge Base use about 70% fewer tokens and complete tasks up to three times faster. Now, Android CLI also provides access to the powerful capabilities of Android Studio, like finding usages and declarations, analyzing files for issues, and looking up the latest info on dependencies. By running Android Studio alongside Antigravity, the agent can leverage these capabilities to run tasks much more quickly, and efficiently, all while under your control. Okay. Let's jump forward in time to see what the agent did to build our new glasses UI. Okay. So the agent's done its thing, and I can see that it's used the recommended skill to build the UI using Jetpack Compose Glimmer, which is part of the Android XR SDK. If I scroll a little bit further, I can also see it's using Android Studio to look up versions of dependencies it needs. And a little further, it's also analyzing files that it's modified for issues. Finally, it deployed the app to The emulator so I can try it out myself and see flight information, hotel information and more. [Applause] >> FLORINA MUNTENESCU: We're just scratching the surface of the Android capabilities in Antigravity. How about adding a helpful AI Summary of the entire trip, and asking Antigravity to give us before-and-after screenshots of the app? >> ADARSH FERNANDO: So switching to an earlier result, I can see that the agent has implemented hybrid mode by using hybrid Firebase logic, which is great, because that way the app only uses the cloud device model as a fallback when an on-device model isn't available. >> FLORINA MUNTENESCU: But did it actually work? >> ADARSH FERNANDO: That's a good question. So if I scroll a little bit further down, I can see the before and after screenshots that we asked for with the feature implemented, I can also see that the agent used the Android CLI to deploy the app, navigate the UI and take those screenshots. >> FLORINA MUNTENESCU: Okay. So these screenshots are nice and all, but we need to see how this looks across multiple configurations, and whether that AI Summary really works offline. Antigravity enables you to orchestrate your Agent but the ideal setup is to use Antigravity alongside Android Studio. >> ADARSH FERNANDO: That's right, and you can easily transition to Android Studio at any time and get that production-grade polish. For example, with the agent, I can ask "open the Compose previews for the home screen in Android Studio" and pixels percolating, there it is. [Applause] >> FLORINA MUNTENESCU: So we can see how the UI looks across Multiple themes and how it adapts to different screen sizes. And if there's anything we need to tweak, we just go to AI actions. Now, we need a real phone to test the on-device AI capabilities. >> ADARSH FERNANDO: I agree. And in Android Studio, I can deploy to a number of real Android devices whether I own them or not. For example, here's the app running on a real Samsung Galaxy S26 Ultra, which is coming to Android device streaming a little later this summer. While the device is in airplane mode, I can easily check that the AI trip summary feature is using the on-device Gemini Nano. [Applause] >> FLORINA MUNTENESCU: All right. Now, a high-quality app needs to be performant. Since I'm in Android Studio, I can view the App Quality Insights window. And I can see that my app has been crashing too much in production. And on top of that, we also want to be ready for some of the memory limits changes for performance optimization in Android 17. Let's get that fixed. I'll go to the agent, and I'll say, okay Gemini, fix and analyze my app's optimization and performance. The agent knows that one of the main ways it can improve its performance is with R8. It streamlines your app by removing unused code and resources and rewrites vibe-code to optimize for run-time performance. Effective R8 configurations lead to fewer ANRs, reduced app size and quicker startup times. >> ADARSH FERNANDO: Let's use that time machine and jump to the results. Okay. The agent has done its thing. And I can see that it's used the R8 analyzer skill to actually recommend changes to the build configuration to enable R8's full mode. That's great. If I scroll a little further down I can also see it's using the new R8 configuration Analyzer, which means in the final report, I have my updated optimization, obfuscation and shrinking scores. Now to achieve these scores, the agent has audited and suggested updates to my keep rules to maximize the effectiveness of R8. Previously, almost none of my app's code was optimized. With these changes, R8 was able to optimize almost all of the code. It's now faster and smaller, all from a single prompt. >> FLORINA MUNTENESCU: This app is getting better and better, but let's add one more feature before we ship it. We need deep links to maximize engagement and ensure that our users are taken directly to their upcoming trip right inside the app. So if I click on this link in the booking confirmation, it doesn't currently go anywhere. In the latest version of Android Studio, we have a dedicated App Links Assistant that helps you implement new deep links for your app. If I go to tools, App Links Assistant, open the URL mapping editor, and then I have my host stuff background demo, and then I can select, which activity to handle my intent, my deep links, and then I pass a sample URL to process. And that's it. AI is doing its job now. >> ADARSH FERNANDO: All right. You all know the drill. Let's jump over to the results. So here, I can see that the agent has analyzed that URL, along with the app's code, to recommend a custom implementation plan. And with that plan, it's the implemented the exact routing logic that uses the trip data from that URL it parsed, so if I go back to that device and click on that action in the e-mail, it goes to the personalized trip right in the app. Are all PM's like that? Or just me. >> FLORINA MUNTENESCU: Just you. >> ADARSH FERNANDO: Well, the good news is that now, you can publish updates of your app from Android Studio directly to Google Play. Check this out. All I need to do to get started is go to Build and generate a signed app bundle and after a couple of clicks, making sure to check this new option that I want to upload to Play, I'm ready to upload a new version of my app to Play. And after I click next, it's off to the internal test track. So testers can test while I get the Play Store page ready. >> FLORINA MUNTENESCU: Okay. Now one last thing. >> ADARSH FERNANDO: Let's give An early sneak peek -- >> FLORINA MUNTENESCU: Like really early. >> ADARSH FERNANDO: Super early. A suite of tools to easily migrate and extend your app to Android, regardless of whether your source is React Native, a web framework or even iOS. >> FLORINA MUNTENESCU: So let's go say your company is looking to expand an existing iOS app to Android's over 3 billion users. To make this a matter of hours rather than weeks, we're experimenting with a new Migration Assistant in Android Studio. here is how we're thinking of doing this. You go up to File, New Project, and select Migrate to New Project. I select what app I want to migrate, and then I can decide whether I want to let the AI make decisions for me or whether I prefer to be more involved by selecting Guided Migration. I can attach reference images or even some custom skills, but then instead of doing the validation myself, I can let the agent do that for me with Journeys. It creates a set of natural-language instructions following our app's User Journeys and then the agent executes, evaluates and iterates on the app. >> ADARSH FERNANDO: Just for this demo, we selected this open-source project called Metropolist. It's a gamified companion for the Public Transit Network in Paris. It's really fun. You get points when you track your routes and badges when you ride the full length of a transit line. >> FLORINA MUNTENESCU: We ran the migration earlier and spent a bit of time on a few polished tasks like adding maps, SDK support and fancier animations. Do you want to see? >> ADARSH FERNANDO: I want to see. Do you all want to see? [Applause] >> FLORINA MUNTENESCU: All right. Here is the iOS app running in a Simulator and the Android app on an emulator. So let's say we want to take Metro Number 1. Then we press start travel. We go from La Defense to Les Sablons. And then Confirm Journey. Oh, look at all the progress that agent made for us. [Applause] Let's see how we got here. Android Studio's Migration Assistant first creates the feature mapping and only afterwards, the project plan. Since the agent knows the typical iOS and Android projects, the agent looks at the Xcode storyboard and then creates the corresponding Android screens. It also knows how to handle things like migrating strings from iOS to Android, and even how to handle assets like SVGs and PDFs and convert them to vector drawables. And then, when implementing the Android code, libraries like Jetpack Compose, Room and View Models are used together with best practices, like predictive back navigation. To perfect your app and make it production ready, you can use all the great agents and tools that are already within Android Studio, since this is a native Android app. The Migration Assistant is coming to Android Studio later this year. We are also working on providing support for migration to Kotlin Multiplatform to make it even easier to maintain shared business logic for Android and iOS. >> ADARSH FERNANDO: By combining Antigravity and Android CLI with the pro capabilities and production-grade polish of Android Studio, we're unifying our most powerful tools for incredible productivity gains. No matter what form factor you're building for, you can bring your ideas to life easier than ever, while maintaining Android best practices. Teams of all sizes and skill levels can build cutting-edge Kotlin apps and deploy them to Google Play in record time. And in this new era of development with Google, we're extending that same level of agentic coding across every platform. Now, let's hear from Una to tell us how this digital workforce is delivering incredible new web experiences. ♪ ♪ [Applause] >> UNA KRAVETS: AI agents are transforming the landscape of development everywhere, and nowhere is that transformation happening faster than on the web. Take the browser, with Gemini now built in, Chrome has evolved to put AI assistants right at your fingertips, unlocking a new era of interactivity and possibility for users and developers. It's an exciting time to experiment without barriers, to build with confidence, to finally bring to life all those ideas you've envisioned, now with a clarity and a velocity that just a few months ago seemed impossible. What it means to build for the web is rapidly evolving. Today, you'll see how you can harness agentic coding tools, to orchestrate all-new web experiences with intelligent guidance, automated debugging and powerful new APIs. This is the future of the web, imagined by you, and supercharged by AI. Let's dive in. When I talk about modern web capabilities, the question I hear the most from fellow developers is: How do I even keep up with all of these new features? Yes. It's exciting to see the web platform accelerate with dozens of new APIs added every few months, but first, you have to figure out if they'll even work for your users, and then you have to learn how to use them. Baseline solves the first problem, with 100% of web platform features now mapped. Baseline is the definitive industry standard that gives you visibility into web feature availability across the major browsers. Now for that second problem, there really hasn't been a solution to keeping up with features until now. Today, we're launching a new tool to supercharge your agents: Modern Web Guidance, a comprehensive and expert-vetted set of skills providing AI agents with a blueprint for modern web features. Building on our experience with Baseline, it ensures your agent isn't using yesterday's technology but implementing the latest web platform features and most recent Chrome innovations, compatible with your baseline targets. Modern Web Guidance empowers you to stay in the flow of experimenting and iterating while the agent handles the implementation. You can target a specific baseline version, and the agent will constrain its suggestions. The guidance even contains fallback solutions and alternatives for the newest platform features that don't have wide browser support yet. To show you how powerful and easy it is to use Modern Web Guidance with your coding agent, let's welcome Matthias to the demo desk. [Applause] >> MATTHIAS ROHMER: Thanks, Una. Here is something I've been working on: Dynorun, our Chrome Dino-inspired car site built in React. Using CSS program animations, it unfolds as a fluid narrative-led experience and after that leads us into the modern configuration. After that, leads us into the model, let's check it out. Give it a second to load. All right, so what color should we pick for you? What do you think about this green or cerulean? >> This looks amazing, but all of these menus, options and sliders, if I was really using this, I would want a shortcut like a browser agent to do the heavy lifting, and just help me build a car to fit my needs. So you know what I'm going to ask? Can we make this work seamlessly with agents? >> MATTHIAS ROHMER: A few months ago, that could be a really hard question to answer but not anymore. With WebMCP, we can now make this webpage agent-ready in minutes. This proposed browser standard lets you expose web capabilities to browser-based agents. In other words, it lets you tell agents how and where to interact with your site, making those interactions more precise and reliable. >> UNA KRAVETS: Now, we could implement this ourselves on stage, but with Modern Web Guidance, our agent has the skills to do it on its own. All we need to do is ask. Matthias, can you give it a try? >> MATTHIAS ROHMER: Absolutely. Let me open Antigravity and here I can just prompt: Please implement WebMCP tools for the car configurator on this page and off we go. Modern Web Guidance is a set of text-based skills that are internally tested, benchmark proven and token efficient. So for web development tasks, the jump-in pass rate in guided compared to unguided coding is an average of 37 percentage points, and you can even read the markdown files yoursel Let's go ahead and allow this all. There we go. Let me pull up an example for a guide. This skill here contains knowledge about WebMCP, so your coding agent can jump-start the development process and handle the groundwork with confidence, giving you a solid foundation to test and refine. Here you can see how it explains that WebMCP is made up of JavaScript functions that are exposed to agents through an API. We've made accessing and implementing Modern Web Guidance as easy as possible. In Antigravity, it's easy to install with one click during onboarding or later on from Settings. But if Antigravity is not your coding agent of choice, you can install it as a ready-made package of skills for other coding tools. And because the guidance is explaining core platform features, it adapts to your framework of choice, no matter if it's Angular, React, or any other. All right. Let's check on progress in Antigravity. All right, it looks like it's almost Finished, so I'm switching back to Chrome, and I'm going to click and then ask Gemini in the top right. This brings up a prototype of Gemini in Chrome with experimental WebMCP support. Since this is still in active development, the final version may differ from what we'll see today and while this demo was specific for now, once WebMCP stabilizes, these tools will be compatible with any browser-based agent that supports WebMCP. Una, let's prompt away. >> UNA KRAVETS: Okay. Let's have some fun. Can you prompt in Gemini and Chrome: Configure the ultimate party car. I want immersive audio and some interior lighting would be great. Plus, enhanced visibility for night driving to keep me safe, and I don't want to go too crazy so keep it under $40,000 but give me as many add-ons as you can under that. >> MATTHIAS ROHMER: All right. This sounds like an excellent Build. I am briefly doublechecking the prompt, and here we go. So now in Gemini in Chrome creates an autobrowse plan and briefly passes it back to me for confirmation. I'll approve the task and then off it goes. >> UNA KRAVETS: With WebMCP, Gemini and Chrome and other browser agents have one more tool in their box to interact with the website. In test runs with this site, Antigravity has implemented an imperative tool called Update Car Configuration with all configuration options listed in the schema definitions. Now, Gemini and Chrome with use this specific targeted WebMCP tool for the job. >> MATTHIAS ROHMER: And through Modern Web Guidance, we were able to implement it and make this app ready for the agentic web in no time. Una, your build has finished. What do you think? >> UNA KRAVETS: Let's talk about the color later on, but this is so much easier than finding all the right options myself. Modern Web Guidance with support for over 100 use cases for dozen of the latest features is available for early preview today. [Applause] I'm also excited to announce that the experimental WebMCP API will enter Origin Trial starting in Chrome 149. [Applause] And Gemini in Chrome will soon support your WebMCP tools, building on the active experiments we are running with our ecosystem partners. [Applause] Exciting. Okay. So we've added some new features to our website, but could we have the coding agent now test this, like a real user would? >> MATTHIAS ROHMER: Yes. We could. I think by now, most folks here have tried building with agents. They've gotten a lot better but you still don't always get what you prompted for, and that's because your coding agents can't actually see what it's coding. That all changes with the new Chrome DevTools for Agents [Applause] Thanks to incredible feedback from our early preview, we've evolved it to do even more. Now, your agent can finally see how the code it has written performs at runtime. With the MCP server, the CLI and the set of tailored skills, it finally creates a closed feedback loop for agents. That's phenomenal, for building, validating, and debugging. To see its capabilities, let's go back to Antigravity and here I can just prompt, please check the WebMCP implementation with Lighthouse. Now, what will happen in a second is you'll see Chrome popping up, loading our page. Basically, the same thing that would happen if you ran a Lighthouse audit through the DevTools UI. I think I need to allow one more tool call. There we go. There's Lighthouse running. And Lighthouse runs with the new agentic browsing category, which enables Lighthouse to run a comprehensive health check for the agentic web. It validates your WebMCP tool registrations and ensures your forms have declarative metadata that agents need to be successful. >> UNA KRAVETS: It also verifies your llms.txt file, a new standard for giving your models a clear map of your site's contents. And it's reevaluating a lot of the familiar Lighthouse accessibility audits. Because most agents navigate the web using the accessibility tree, every ARIA role or label that you optimize doesn't just help a human; it makes your site more actionable for an agent, too. When an issue is surfaced through Lighthouse, you don't need to be the "human clipboard" anymore, copying from error-prone DevTools, pasting it into a chat and hoping the agen guesses the right fix. The agent reads the report for itself, attempts a solution and can rerun audits to see if that solution works. It's a supercharged workflow that automates the busy work leaving you free to spend your time innovating. If you want to give it a try, Chrome DevTools for Agents is available today for Antigravity and more than 20 other coding agents of your choice. [Applause] Okay, Matthias, I think that we have one more surprise hidden away in this car configurator. >> MATTHIAS ROHMER: Yeah. We do. Let's go back to your party car running in Canvas. Let me switch to the interior view. Do you see the screen here in the center? It's actually interactive. I can click down to the second screen of our car And change the ambient lighting just by pulling the sliders. And you know what? If we do a Quick Inspect in DevTools, the full display UI are actually native HTML elements rendered into the canvas. [Applause] >> UNA KRAVETS: I know what some of you out there might be thinking: HTML elements inside of a canvas? Well, that shouldn't be possible. >> MATTHIAS ROHMER: The new HTML-in-Canvas API now does the impossible. With this, you can now integrate real DOM elements directly into your canvas environment. Now, you no longer have to choose between visually complex and stunning, or interactive and accessible. >> UNA KRAVETS: Exactly. Because it's part of the DOM, every element in your canvas is now searchable, accessible, selectable, translatable and interacts with your built-in browser features like autofill. And that creates some really interesting possibilities. >> MATTHIAS ROHMER: Yeah, for example, you can style them just like any other DOM element by adding a little class like this one. >> UNA KRAVETS: Nice. We've already seen the community build amazing demos with webGL textures, 3D interfaces and entirely new modalities for interaction with real DOM content. HTML-in-Canvas is in Origin Trial now, so you can test, experiment, and build. [Applause] Now, I know a lot of web developers are really excited to try this out, and that's because this is more than just a new feature. Alongside everything else you've seen today, it represents a fundamental shift in how we build, who can build and even what we can build. In this new era of agentic web development, there's never been a more inspiring time to create with tools like Modern Web Guidance to help you quickly and reliably implement new features like WebMCP, HTML-in-Canvas to truly expand accessible, interactive, creative new UI on the Web; and Chrome DevTools for Agents to autonomously debug and test performance. The future of the web is imagined by you, and supercharged by AI. But this isn't just about the web. It's about how we build everything, so to bring it all together, please welcome back Josh. [Applause] ♪ ♪ >> JOSH WOODWARD: All right! What a show! From Google AI Studio to Antigravity, from Android to the open web, today, you've seen agents completely transform the developer experience. The common thread across all of this is simple: You focus on the big idea and the agents can do the heavy lifting. And it's never been a better time to build. We hope you'll take what you've seen today and push it to the limits To get you started, we've created the ultimate platform to make an impact. Today, we are officially launching the Build with Gemini XPRIZE hackathon. This global hackathon offers $2 million in prizes for builders creating apps that solve actual real-world challenges. The premise is simple: Pick a problem worth solving, build with Gemini, and let's all try to positively impact the lives of 1 billion people. To build at that scale, you'll need some serious power and as you heard this morning, we announced a new $100 per month Google AI Ultra plan alongside a simplified pricing structure based on your feedback, and to keep those agents humming over the upcoming holiday long weekend, we're giving Ultra subscribers $100 in bonus credits today. You can claim the offer right in the Antigravity app and the credits will kick in when you hit your limit. So let's get going. You can visit io.google for the livestream sessions and all the on-demand content we'll be releasing over the next few days. Thanks for coming and have an amazing I/O! [Applause] ♪ ♪