Published: May 19, 2026 | Source: Chrome for Developers Blog
Agents are transforming development everywhere, and nowhere is that transformation happening faster than on the web. It’s redefining what we build, how we build, and who builds. As we enter the era of the agentic web, we see a shift that bridges the gap between complex developer workflows, underlying platform capabilities, and everyday user experiences.
At Google I/O 2026, Google unveiled a vision for this era — one that ties together three core areas of the web ecosystem: empowering AI agents to build and interact with websites through new capabilities, pushing the boundaries of web UI and performance, and transforming the browser into a powerful, proactive assistant for everyday users with Gemini in Chrome. By integrating efficient, built-in AI models directly into the browser and bringing powerful automation tools like auto browse to Chrome, the web is becoming smarter, faster, and more accessible for everyone.
Here are the 15 biggest updates shared at Google I/O 2026 to help you build and thrive in the agentic era of web browsing.
Part 1: Empowering AI Agents for the Web
Agents are changing how we interact with software, and the web must be equipped to guide them. Google is introducing powerful new capabilities and tools — like WebMCP and Modern Web Guidance — that allow developers to build modern web experiences with greater clarity and speed. They’re also providing AI-assisted tools needed to build, debug, and optimize code faster and more accurately than ever before.
1. WebMCP: Transform Your Websites into Agentic Toolkits
WebMCP is a proposed open web standard that lets developers expose structured tools like JavaScript functions and HTML forms to browser-based agents. By defining these tools, developers can instruct agents exactly how and where to interact with a site. An agent can now call machine-friendly functions to complete complex tasks in seconds with greater reliability, precision, and personalization.
Imagine a user planning a multi-city vacation. Instead of watching an agent click through travel forms, they can authorize it to query backend APIs directly to instantly build a personalized, weather-optimized itinerary for their approval.
The experimental WebMCP origin trial starts in Chrome 149. Gemini in Chrome will soon support WebMCP APIs. Global consumer brands — including Expedia, Booking.com, Shopify, Credit Karma, TurboTax, Redfin, Etsy, Instacart, and Target — are already experimenting with WebMCP to create more delightful and engaging experiences for their users.
2. Modern Web Guidance: A Blueprint to Guide Coding Agents to Build for the Modern Web
Modern Web Guidance, now available in early preview, is a set of evergreen and expert-vetted skills that guide coding agents across many common use cases to build modern web experiences that are more accessible, performant, and secure. It integrates directly with Baseline, letting developers focus on what they want to build while tools automatically figure out the right features and fallbacks to use within the chosen Baseline target.
Install with a single click in Google Antigravity, through npx, or as an extension in a coding agent. Modern Web Guidance features support for over 100 use cases for dozens of the latest features with continuous updates added regularly.
3. Automate Debugging with Chrome DevTools for Agents
Chrome DevTools for agents provides visibility to verify, debug, and optimize code in real time. By providing agents with direct access to DevTools capabilities — such as console logs, network traffic, and accessibility trees — they can verify and automate fixes without manual oversight. Chrome DevTools for agents is available today for Antigravity and more than 20 other coding agents.
A great real-world example: LY Corporation used Chrome DevTools for agents to build an automated AI-based performance auditing system, reducing manual analysis by 96–98% and enabling on-demand audit reports for every team.
4. Gain Deep Insights with AI-Assisted Debugging in Chrome DevTools
AI assistance in Chrome DevTools now has access to Lighthouse data and can automatically search for context to answer more open-ended questions than were previously possible. Additionally, widgets give full visibility into Gemini’s reasoning to help with debugging.
This dramatically reduces the complexity of performance debugging while allowing seamless human-agent collaboration.
5. Skip Servers, Budgets, and Red Tape: Unlock AI Features with Built-In AI
Running entirely in the browser, built-in AI lets developers deploy personalized, proactive features that would be cost-prohibitive on the server. The browser manages and shares optimized models across sites, enabling more users to enjoy AI experiences on the web.
Key updates to the web AI toolkit include:
- Prompt API is now stable: Chrome 148 uses Gemini Nano with multimodal inputs and structured output for rich experiences, reliable JSON for seamless integrations, and access to expanded language support.
- Gemma 197M: This ultra-efficient expert model can transparently power task-specific APIs like the Summarizer API, automatically scaling features to a broader spectrum of devices.
Trip.com is already using built-in AI to generate personalized travel summaries locally on-device — bypassing server overhead and scaling to unlimited queries with zero budget worries.
Part 2: Pushing the Boundaries of Web UI and Performance
Google is developing next-generation platform features that continue to blur the line between web and native apps. New declarative APIs — such as HTML-in-Canvas and Declarative Partial Updates — handle complex rendering and performance tasks, making it easier than ever to build beautiful, high-fidelity, and performant interactive experiences on the web.
6. HTML-in-Canvas and Element-Scoped View Transitions: Break the Boundaries with Next-Gen UI
The new HTML-in-Canvas API and element-scoped view transitions enable previously impossible UIs that bring high-fidelity, app-like interactivity to the web. With the HTML-in-Canvas API, developers can integrate real DOM elements directly into a canvas with WebGL and WebGPU to build immersive 3D experiences that are searchable, accessible, natively translatable, and interact seamlessly with built-in browser features.
Element-scoped view transitions are available now in Chrome 147, and two-phase transitions are currently in testing. These create layered UI motion and animate intermediate states without blocking page interactivity. The HTML-in-Canvas API origin trial is available now.
7. Performance and UI Wins: Core Web Vitals for SPAs and More
Chrome is enabling new ways to improve performance for modern app-like web experiences. New updates include the Soft Navigations API — available in an upcoming Chrome release — to bring Core Web Vitals measurement to Single Page Applications. New Declarative Partial Updates primitives bring native out-of-order HTML updates to the platform, as well as new streaming APIs to make it easier to insert HTML into the page without heavy DOM manipulation. These APIs are available for testing now.
8. Modernize Authentication with Immediate UI Mode
Immediate UI mode unifies passwords and passkeys into a single, browser-managed sign-in flow. When a user clicks “Sign In” on a site, Chrome automatically surfaces the available credentials — allowing for seamless authentication using saved passwords or passkeys.
9. Plan Your Baseline Target with Real-World Traffic Data
The new Baseline Checker tool connects directly to the updated Google Analytics API and shows exactly what percentage of actual users support modern features. Developers can pick a Baseline target and confidently ship the latest features to users, while knowing when to use fallbacks — no more shuffling data around with exported TSV files.
Part 3: Supercharging the Browsing Experience with Gemini in Chrome
With Gemini in Chrome on desktop, iOS, and now Android, Google is giving users powerful new ways to browse, create, and get things done. From automating complex, multi-step tasks with auto browse to intuitive multimodal interactions using cursor or voice, Gemini in Chrome puts powerful productivity directly at users’ fingertips.
10. Gemini in Chrome for Android: A Browsing Assistant on Your Phone
Coming in June, Gemini in Chrome on Android is designed to be a personal browsing assistant — helping users better understand content on the web. It lets users summarize long articles, ask specific questions, and get detailed explanations without having to switch apps. Beyond answering questions, it acts as a versatile productivity tool that connects with Google apps like Calendar, Keep, and Gmail to help complete tasks quickly.
With Personal Intelligence, if users choose to connect apps like Gmail and Google Photos, this secure, context-aware browsing assistant can even provide tailored responses based on unique interests, hobbies, and more.
Gemini in Chrome on Android will be launching in late June; it will initially be available on devices with 4GB of RAM or more with their language set to English-US.
11. Use Auto Browse to Take Care of Tedious Tasks
Already available on desktops, auto browse for Android lets users get the most out of Gemini in Chrome by automating digital chores so they can focus on more important tasks. With auto browse, users can easily complete tasks from appointment booking to party planning, finding in-stock items and more, all from an Android phone.
For example, if you’re about to head out to a comedy show but forgot to book parking, auto browse has you covered — just ask Gemini in Chrome, and it will gather event details from your ticket to find you a spot.
On desktop, auto browse will be integrating with Gemini Spark in the coming months, so that a 24/7 personal AI agent can take actions in the browser on users’ behalf.
12. Transform Images on the Go with Nano Banana
With Nano Banana, users can instantly create or customize images while browsing the web on their Android device. Just ask Gemini in Chrome to “turn this page into an informative infographic” while studying, or “alter the image to include modern living room essentials” when browsing for apartments.
13. Skills in Chrome: Turn Your Best AI Prompts into One-Click Tools
Skills in Chrome let users save and reuse their most helpful AI prompts in Gemini in Chrome on desktop. Save a multi-tab workflow once — like generating side-by-side spec comparisons while shopping or scanning long documents for key information — and run it again instantly with a single click any time.
14. Select from Your Screen to Prompt Gemini in Chrome
Users can now use their mouse pointer to ask Gemini in Chrome about specific parts of a webpage, saving the effort of describing exactly what they mean. For example, selecting two products on a page and instantly comparing their key features, or selecting exactly the part of an image to change with Nano Banana.
15. Use Your Voice Across the Web
Soon it will be possible to use voice to type into websites across Chrome on desktop. With voice, it will be easier and more natural to draft comments, fill in long form fields, or write emails. This will use Gemini models to either clean up transcription — removing filler words and fitting it to the context while keeping true to the user’s voice — or fill in the field as directed.
What’s Next
The transition to the agentic web is unfolding right now. By bridging the gap between powerful underlying AI capabilities and everyday web development, Google is removing the friction that has historically slowed down and constrained innovation.
The web is moving away from requiring users to do all the heavy lifting, and towards a web that proactively works for them — whether that means seamlessly integrating with browser-based agents, pushing the absolute visual limits of what a webpage can do, or simply streamlining a debugging workflow.
The future of the web is here. Are you ready to build it?
For full technical guides and deep-dives on all these features, visit developer.chrome.com and web.dev.