←
Rustin Banks2,613 posts
Rustin Banks avatar

Rustin Banks

@rustinb

AI Coding @GoogleLabs, PM @stitchbygoogle, prev @julesagent

◷ Joined March 2008▧ 196 Photos and videos
Kunal Chaturvedi avatar
⟳ Rustin Banks retweeted
Kunal Chaturvedi@chaturvedikun·3h

I've been an early tester for Loop and there is so much I have to share about it: (1/n) 1) It is truly a one of a kind product-first take on the now-conventional coding agents idea. In today's age, it is very easy to become directionless with a product or not understand the next steps of building a product. Loop is built to answer this gracefully by helping you set goals upfront and build in a defined direction over months, while also fixing the long-term product context problem faced by the average use of coding agents.

Introducing Stitch Loop, a new Stitch experiment. Stitch helps you design your product. Stitch Loop helps you keep improving it once it's live: a product agent built for outcomes, not just PRs. Stitch Loop monitors your production data and lets you build loops that work continuously until your goals are met. You can define your own custom loops, or start improving your product on day one with built in Loops for: 🛡️ Security: built with Gemini 4 Carbon and @GoogleDeepMind CodeMender ⌚️ Latency: to keep your product fast 👋Accessibility: so it works for everyone Join the waitlist: stitch.google.com/loop/waitl… Learn more 🧵👇

0:33
Rustin Banks avatar
Rustin Banks@rustinb·4h

This is the way. People focus on the design, creativity, goals and strategy. AI handles the toil of the loop.

Introducing Stitch Loop, a new Stitch experiment. Stitch helps you design your product. Stitch Loop helps you keep improving it once it's live: a product agent built for outcomes, not just PRs. Stitch Loop monitors your production data and lets you build loops that work continuously until your goals are met. You can define your own custom loops, or start improving your product on day one with built in Loops for: 🛡️ Security: built with Gemini 4 Carbon and @GoogleDeepMind CodeMender ⌚️ Latency: to keep your product fast 👋Accessibility: so it works for everyone Join the waitlist: stitch.google.com/loop/waitl… Learn more 🧵👇

0:33
Rustin Banks avatar
Rustin Banks@rustinb·Nov 16

So fun to see Deep Mind really cooking again. Amazing team.

We are cooking at Google. Look at the last few weeks: Models • Gemini 4 Carbon: now GA in the API and AI Studio, rolling out to Ultra • Gemini 4 Hydrogen: ~2.5x faster than 3.8 Flash, 1M context, $1.50/$7.50 per 1M tokens flat • Gemini Omni 1.2 Flash: 15-second clips, 30% cheaper • Gemini Robotics 2.5: new vision-language-action model • Genie 4: real-time interactive world model • Gemini Decisions API: score up to 1,000 questions in one call Agents and dev tools • Antigravity: Orchestrator, Swarm, Dynamic Workflows, Voice mode, Browser Use, Knowledge Work layout and a plugin marketplace • ADK 2.14: execution environments, A2A and eval go stable • A2UI 1.0: open protocol for generative UI • Elephant Goldfish: open-source plugin to design and review with coding agents Hardware • Gemini glasses: pre-orders open with Warby Parker and Gentle Monster • XREAL AURA: first wired Android XR glasses with Gemini • TPU 8tx and 8i Max, plus TPU Sync open-sourced • Gemma 4 running on a TPU in space • Pixel Tag and Gemini Intelligence on Pixel 10 Bullish on Google.

Rustin Banks avatar
Rustin Banks@rustinb·Nov 11

Cry. When we recorded the video Sundar used it was staging hardware and a pre-release model. Now in production the same flow is about twice as fast! (Everything 1x)

0:16

Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio. Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details: - 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring - $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite) - leads on several benchmark evals with lowest calibration error Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)

0:13
Rustin Banks avatar
Rustin Banks@rustinb·Nov 11

Why we built this: A month ago I wanted to explore how users could accomplish a goal. I wanted an agent to sketch some quick mockups. It took my agent minutes, and I forgot and did something else. Now with Stitch Rapid it takes literally 3 seconds...

0:20

What if you could generate an entire product flow in just five seconds? Early design is rapid and iterative. To amplify your creativity, you need a synchronous design partner that keeps up with your train of thought. So we built a rapid design experiment in Stitch. It’s powered by the Gemini Decisions API to help explore what happens when early design iteration takes seconds instead of minutes ⚡️: 5️⃣ seconds from rough prompt to a multi-screen flow 2️⃣ seconds from tap to new variations 1️⃣ click to dive into Stitch for deeper UI polish ⚠️This is an early MVP to test how fast early ideation can feel, and we’ll be folding your favorite parts into the full Stitch experience soon. Look for the banner in Stitch to try it yourself or see how it works below 🧵👇

0:58
Rustin Banks avatar
Rustin Banks@rustinb·Oct 6

Higher quality AND faster. Win + Win.

Nano Banana 2.1 is now live in Stitch 🍌 Try it the next time you’re generating hero graphics or vector-style logos for your UI, and let us know if you get cleaner visuals and more consistent results across your project.

Rustin Banks avatar
Rustin Banks@rustinb·Oct 1

Stitch CLI is here! This was built by an amazing and talented team who really gets developers (not bragging, cause it wasn't me :)

We have a Stitch MCP. We have a Stitch SDK. But, we don't have a Stitch CLI. Well, not until now. Introducing the @google/stitch CLI: 🔷 Connect to your local coding agents 🔷 Generate screens and design systems 🔷 Send a local dev server snapshot to Stitch Do it all without leaving the terminal or better yet, ask your favorite harness like @antigravity 😎 Learn more 👇

0:42
Rustin Banks avatar
Rustin Banks@rustinb·Sep 30

Wow, I knew Argon was good but I didn't know it was that good. Congrats!

Announcing Gemini 4 Argon, our new frontier model. Argon is built to sustain deep reasoning across complex, long-horizon workflows and delivers frontier performance in complex workflows across real-world software engineering, enterprise knowledge work like legal and finance, and cybersecurity defense. We’re also expanding the model’s output token limit to an industry-leading 1M tokens. Argon is currently rolling out to a set of trusted cyber defenders in the Fairwind Program, with broader availability as soon as possible.

Post attachment
Rustin Banks avatar
Rustin Banks@rustinb·Sep 24

I'm impressed with the speed and quality of Gemini 3.8 Flash image analysis. It's enabling some awesome things in Stitch

Your brand assets, brought to life. ⚡️🖼️ Gemini 3.8 Flash excels at understanding visual context. Just drag your brand kit and product shots straight onto the Stitch prompt: ✨ Automatically extracts design systems and styling ✨ Generates cohesive layouts around your brand rules ✨ Seamlessly weaves your product imagery into marketing & product pages Check out the workflow in the video below! 👇

0:28
Rustin Banks avatar
Rustin Banks@rustinb·Sep 17

I thought our video editor did a great job with this video. Would love to hear more from our users about why they love creating dashboards in Stitch?

Spreadsheets are great for storing numbers. They’re terrible for showing them off. 📈👀 Lately, the Stitch community has been using their design partner to turn raw data dumps into sleek, production-ready dashboards: 🔹 Paste in CSVs, analytics exports, or workout logs 🔹 Ask Stitch for a specific vibe, layout, or design system 🔹 Instantly explore high-fidelity charts, stat callouts, and clean data hierarchies 🤖 Automation Hack: Pair Gemini Spark or Antigravity with the Stitch MCP Server. You can automate your daily tracking so a fresh, tailored dashboard is generated before your first cup of coffee. Check out the demo to see how we turn raw data into eye candy! 🔊👇

0:28
Rustin Banks avatar
Rustin Banks@rustinb·Sep 4

Great turnaround. Concern about Antigravity ToS posted on X and 24 hours later... ToS updated.

We’ve heard the feedback loud and clear that we need to be clearer on our terms in @antigravity. We updated the below terms to be super clear that it only impacts your Antigravity and/or Gemini CLI accounts. Keep the feedback coming and continue to make tokens go brrr 🚀

Post attachment
Rustin Banks avatar
Rustin Banks@rustinb·Sep 4

What are you building with Google Stitch and Flash 3.8? Are you finding the designs to be too cluttered? Should we ask the agent to turn down the density a bit?

Rustin Banks avatar
Rustin Banks@rustinb·Sep 4

Let's go Flash 3.8! I think cost / task is under-rated

Gemini 3.8 Flash is now available in Cursor - it is incredibly efficient and has one of the best cost / task ratios of any top 10 model Updated rankings:

Post attachment
Rustin Banks avatar
Rustin Banks@rustinb·Sep 3

This should be 100% rolled out now to everyone, everywhere Stitch is available. Would love your feedback (reminder, Stitch is currently completely free of charge right now)

Gemini 3.8 Flash has landed in Stitch! 🚀 Your design partner just leveled up: 👁️Attention to Detail: Screens look production-ready faster, with more detailed and realistic UI elements 🖼️Richer Visuals: Generates smarter underlying image prompts, delivering visuals that better align with your page content and brand 🎯 Improved Instruction Following: Grasps complex, nuanced design edits on the first try. See the difference Gemini 3.8 Flash makes in the video below. Sound on and enjoy our new default model! 🔊👇

0:14
Priy avatar
⟳ Rustin Banks retweeted
Priy@alwayspriyesh·Sep 2

OpenAI & Anthropic CEOs watching Gemini 3.8 Flash launch right now... - Fable 5.1 launched yesterday - Gemini 3.8 drops within 24 hours 💀 - Beats Opus 5 across many benchmarks - 59 on Artificial Analysis Intelligence Index - Just 7 points behind Fable 5.1 - 13× cheaper at $0.75/M input tokens - And insanely fast

0:20

Introducing Gemini 3.8, our best reasoning & coding model yet. By leveraging long-running agentic loops, we’re building on the momentum of 3.7 Flash from just three weeks ago to release two new 3.8 variants: Meet Gemini 3.8 Flash and Gemini 3.8 Flash Cyber 🧵

Post attachment