Introducing the Stitch SDK Yes. You can program design now. I've been dreaming of shipping this for so long because it's just so much fun to use. I welcome all the stars ⭐️ github.com/google-labs-code/…

🚢a huge @NotebookLM ship today! The new NotebookLM is better at what you love and can do much more of what you expect! 🌟 average win-rate of 15% over OG Notebook across our core chat evals, spiking to 28% win-rate for hard research tasks 🎨 Many new file formats (docx, xlsx, md, csv, json, svg etc) with especially beautiful PDFs, charts and images 🖥️ A cloud computer unlocking complex data analysis workflows for insights and decisions that count 🔍 Helps you find high quality sources online and expand on existing sources using Google Search (eg find and add all the references from a paper) We want Notebook to be the best tool for research and hope you find our latest iteration to be even more useful!

Here's how I avoid these: - Don't use GPT 5.5 to start a design - Always use an image reference or site url - Never prompt without a taste skill or DESIGN.md - Set up design rules in AGENTS.md - Get familiar with their names so you can change them

Introducing Impeccable 3.5, the best way to design in production: iterate on real UI with your AI agent, in the codebase you actually ship. Turns out many popular design skills, including Impeccable and Anthropic's frontend-design, weren't actually very good at...design (the workflow was valuable, but the output didn't magically make LLMs like GPT great designers). We measured it across thousands of generations: 74% of pages used the cream AI-default background, 76% reached for extreme letter-spacing, 90% failed the contrast floor. So we started fixing slop systematically, specific to each model. The skill now compiles rules for the exact defects each model makes, instead of shipping one generic file to everyone. The biggest jump is in GPT-5.5 and Codex. Also new: ◆ It now knows the difference between a new project and an existing one. Existing codebase, it reads your design system and preserves your identity. Greenfield, it seeds a fresh palette from 129 hand-curated anchors so every cold start doesn't drift to the same safe colors. ◆ Live Mode is now in beta, and works at two scales. Type a direction into the new Steer bar, or speak it, and the agent reads the whole page and edits it in place. Or pick a single element, steer it with a sub-command, live-edit any copy, and accept the variant straight back to source. Insert mode scaffolds brand-new elements between the ones already there. Recovery survives HMR, hidden heroes, and dev-tool overlays. ◆ A rebuilt anti-pattern detector. Torn off jsdom and onto a real CSS cascade resolver: roughly 20x faster, dependency-free, and now small enough to run inline inside the skill, not just the CLI and extension. 14 new rules, 41 total. ◆ The skill keeps itself current, checking once a day and offering to update. Plus /impeccable init and a bare /impeccable that reads your repo and tells you the next move. Free, open source. Claude Code, Codex, Cursor, and more. impeccable.style

Okay yeah, we need this

What will you build with Stitch? The Stitch build challenge with Contra starts now! $10k in prizes. Link in 🧵

The Stitch Challenge is coming! $10K in total prizes. May 27th. Fueled by the good folks @contra

We believe our Labs experiments are at their best when they’re helping you create whatever you can imagine. We had some fun and put them to the test ourselves. Take a look at our Labs-inspired creations: 🧵1/5 A brand book that we created with @PomellibyGoogle.

Built a @github Issue Triage Agent with a single curl to the Gemini API. → Clones the repo into a sandbox → Fetches open issues from the GitHub API → Classifies each as Bug/Feature/Question → Executes reproducer code to confirm bugs. No orchestration framework. No containers. No infra.

I loved doing this I/O talk with @_davideast where you see how your CSS knowledge can give you super powers when it comes to getting great design out of AI. In this case we are using @stitchbygoogle ofc :) youtu.be/nC7TrzUYvig?si=JKf8…

At I/O, we announced a big new export partner: Bolt by StackBlitz! ⚡️ @boltdotnew is an AI-powered builder that generates full-stack web apps directly in your browser. Now, you can take your Stitch screens from a visual concept to a fully coded application with a single click. Here is how it works: 🔹 Select your screens in Stitch 🔹 Click export 🔹 Your screens are automatically transferred to Bolt, ready to be built into a working product 🛠️ (Note: Bolt will accept up to 5 screens at a time for Bolt Free users, and up to 20 screens for Paid users)

Your vibe design partner just got more collaborative! To celebrate I/O, here are 5 major upgrades (and one big bonus!): 🌊 Streaming 📄 Start with your existing design ⏩ In-place AI Edits 🎥 Motion on HTML-native Canvas 🚀 More Import / Export Options (.fig, Netlify, Loveable, Bolt) 🌟 BONUS: Import and sync your codebase Rolling out now. Details and product walkthrough video in 🧵

Gemini 3.5 Flash is amazing! - Performs better than 3.1 Pro on coding & agentic tasks - 4x faster than other frontier models - 12x faster in @antigravity - 800 tokens/sec! - Often at less than half the cost And Pro to come… Try it in @antigravity, @GeminiApp & more - enjoy!

Introducing Gemini Spark! Our 24/7 personal AI agent designed to proactively manage tasks and help you navigate your digital life, all under your direction. Coming to trusted testers this week, and as a Beta for US Google AI Ultra subscribers next week!

Real codebase. Real content. Real site. @stitchbygoogle is cooking

In @stitchbygoogle you can now import context for your design right from a GitHub repo. Include file references and Stitch will pull the content into your screens. The best designs start with their content.

stitch

who wants a Neutral Expressive DESIGN.md?

Just off stage at #GoogleIO, some highlights from this morning 🧵 Gemini 3.5 Flash is available today for everyone in @antigravity and across our products and APIs. Compared to 3.1 Pro, 3.5 Flash is better across almost all benchmarks with huge progress in coding. It’s also comparable to the best models but very fast (4x faster tokens/ second than other frontier models). And when looking at the intelligence versus output speed, it’s in a league of its own in the top right quadrant.

Gemini 3.5 Flash scores 55% on SWE Bench Pro while being 4x faster than any frontier model. Benchmarks aren't the end all but wow. What a time to be alive.