André Bandarra
@andreban
Followers
823
Following
7K
Media
106
Statuses
2K
Developer Relations Engineer for Chrome and the Web at @Google, technology addict.
London, England
Joined April 2008
Your next project could be worth up to $14,000. The Google Chrome Built-in AI Challenge 2025 is your chance to win big by building a web app or Chrome Extension with our built-in AI APIs → https://t.co/NtXx2HagY2
24
114
926
✨Looking for inspiration on what to build for the Google Chrome Built-in AI Challenge 2025? Here's a demo I built that implements a smart filtering feature with the Prompt API's structured output and accepts voice input with the Multimodal feature. https://t.co/3ch9F2PyXd
The wait is over! The Google Chrome Built-in AI Challenge 2025 is here. Today's the day to start building with our built-in AI APIs. Create a web app or Chrome Extension to compete for our $70K prize pool. Let the coding commence → https://t.co/NtXx2HagY2
2
0
4
The wait is over! The Google Chrome Built-in AI Challenge 2025 is here. Today's the day to start building with our built-in AI APIs. Create a web app or Chrome Extension to compete for our $70K prize pool. Let the coding commence → https://t.co/NtXx2HagY2
19
78
576
Mashups 2.0 https://t.co/21gTsJv74V My buddy @andreban discusses that we might be back to an era that we lost. Mashups! Maybe they will live only side chat apps, maybe they will be back on the web.
aifoc.us
Paul Kinlan recently wrote about how latency of AI models to generate UIs with HTML, CSS and JavaScript is decreasing significantly, and how that can lead to user UIs that are ephemeral, dynamically...
0
2
3
My default LLM recommendation for anyone messing about building AI-powered apps is still... Gemini Dirt cheap Huge context window You have a Google account already Nice choice of reasoning/fast/midrange models
14
11
298
Chrome's built-in AI APIs provide the essential ingredients for web innovation. Just like a barista's carefully curated setup, they empower developers to create powerful applications. Read more about these APIs → https://t.co/vorw9DUxZo
6
28
154
Scale client-side summarization in small context windows! → https://t.co/IY4EsmtWmt The Summarizer API and Gemini Nano in Chrome can help you generate summaries of information in various lengths and formats.
0
7
27
Gemini 2.5 Pro codes a TV. 📺 With just one prompt, it came up with its own ideas for 10 channels and coded each one! Link + details in 🧵
18
67
617
Ever wondered what really happens when you tweak the temperature on an LLM? 🤔 I built a visualizer to show you! See how probabilities shift & creativity blooms (or shrinks!). Dive in! ✨ https://t.co/65chnRIx3w
#AI #LLM
https://t.co/AyTruqmi8n
0
3
3
A new use case for the Background Fetch API: downloading your AI models 😛
Improve the AI model download user experience with the Background Fetch API → https://t.co/B9GtQGr8hF The Background Fetch API is a progressive enhancement that can significantly improve the user experience. If (cont) https://t.co/Xlllgks9kn
1
3
9
Regardless of using a Cloud model, or a client-side model in the browser, Tom Steiner's article shows how to render the streaming LLM responses with top notch performance!
Render streamed LLM responses securely with these best practices → https://t.co/1nvEgwUr96 Learn how to display streamed text and Markdown when using the Gemini API, sanitize model output, and optimize rendering for better UX.
2
0
1
Excited to share the slides of my “AI in the Browser: Smarter Angular Apps with WebGPU and WebNN” from @NGVeniceConf! 🚀 Learn how to integrate Generative AI with #Angular using #WebGPU and #WebNN for offline, secure execution: https://t.co/FN05jE0Ct8 🌐✨ #BuiltInAI #NGVenice
thinktecture.com
0
2
6
Yo Dawg, I heard you like to use AI to generate Summaries, so @AlexandraScript and I have put together a blog post on summarizing your summaries to overcome context window limitations of the Summarizer API and get awesome summaries: https://t.co/cyQx59TYxm
#webai #builtinai
1
0
1
Chrome is investing in the future of AI on the web! We're excited to announce the Web AI Acceleration Fund, which supports open-source projects focused on browser AI performance, libraries, and developer resources. Shape the future of AI→ https://t.co/jQ0y6V4lMV
1
11
46
Another day, another launch. Cooking shall continue. 🎉
Gemini 2.0 Flash-Lite is now generally available ⚡️ → https://t.co/Gay2PkqLh9 Our newest model offers improved performance unlocking new AI applications like voice AI, video editing, and data analytics.
0
1
6
New Gemini 2.0 updates for developers: Starting today, you can use Gemini Code Assist for free in your favorite IDE. It’s Gemini 2.0 fine-tuned for coding, including 180K code completions/ month - *90x* what others currently offer 👀 Plus, Gemini 2.0 Flash-Lite is now GA and
292
939
9K
Really cool demo by @erickwendel_ mixing the Translator API, Prompt API, Web Speech API and Three.js to create an interactive 3D avatar that can answer to users requests (in this demo's case, asking it to tell a joke) #webai
Criei um NPC em realidade virtual com AI 100% Web, offline e com JavaScript 🤯 Meus amigos! Que projeto incrível! Estou usando nesse projeto: - A-frame + Three.js para o visual em realidade virtual - Animações e modelos 3D do Adobe Mixamo - API do chrome de text to speech
1
1
5
big up 4 ai-humans！ @andreban, @tomayac, @jason_mayes, @alexandrascript Meet the https://t.co/4SWr4wyRzY AI Team | Articles
web.dev
Meet the tech writers and developer relations team.
1
3
4
Great series of posts by @christianliebel on https://t.co/Jt30qsIA7I, covering the capabilities and limitations of LLMs running in the browser, and a walkthrough on building an on-device chatbot. #WebAI #PromptAPI #WebLLM #GenAI
Check out my three-part article series about the benefits of on-device large language models and learn how to add AI capabilities to your web apps: https://t.co/ubzPkK6LnL
#GenAI #WebLLM #PromptAPI
0
1
4