Loïc Yabili

After my general explanation of Gemini and its use cases, today I present to you a concrete project: an AI writing assistant similar to Grammarly, integrating Flutter and Dart, and using the artificial intelligence of Gemini API. This assistant can correct errors, provide explanations in 5 languages (French, English, Swahili, Lingala, Hindi) and suggest textual improvements. To learn more, see the following links: 🖥 Source code: github.com/lyabs243/flutt… 📝 Blog: lyabs.hashnode.dev/creating-a-gra… 🎥 Explanatory video: youtu.be/IJ3g-L7aooA #FlutterDev #GeminiAI #BuildWithGemini #buildinpublic #BuildWithAI

@GoogleAI @GoogleAIStudio @antigravity @Firebase

We're making AI agents and assistants more helpful for Android apps and users. goo.gle/47d7ojU See AppFunctions in action with the @SamsungMobile Gallery integration with Gemini on the Galaxy S26 ⬇️

Learn more and check out the WAXAL dataset here: goo.gle/4cxNHae

Today, we’re releasing Gemini 3.1 Pro. It’s the same core intelligence that powers Gemini 3 Deep Think, now scaled for your practical applications. It’s a smarter model for your most complex tasks. See 3.1 Pro in action 🧵↓

You told us you’re running multiple AI agents and wanted a better UX. We listened and shipped it! Here’s what’s new in the latest @code release: 🗂️ Unified agent sessions workspace for local, background, and cloud agents 💻 Claude and Codex support for local and cloud agents 🔀 Parallel subagents 🌐 Integrated browser And more...

So… they actually replaced their product manager with an AI 🤦‍♂️😂

Meetings in real life be like 🤣🤣

@NondineI124 Almost 2years ago! thanks for your feedback I appreciate 😊

@lyabs243 You saw ai before us 👌🏿

After my general explanation of Gemini and its use cases, today I present to you a concrete project: an AI writing assistant similar to Grammarly, integrating Flutter and Dart, and using the artificial intelligence of Gemini API. This assistant can correct errors, provide explanations in 5 languages (French, English, Swahili, Lingala, Hindi) and suggest textual improvements. To learn more, see the following links: 🖥 Source code: github.com/lyabs243/flutt… 📝 Blog: lyabs.hashnode.dev/creating-a-gra… 🎥 Explanatory video: youtu.be/IJ3g-L7aooA #FlutterDev #GeminiAI #BuildWithGemini #buildinpublic #BuildWithAI

Guiding AI is like mentoring a new contributor. Has working with AI changed how you review or give feedback? In our final GitHub Podcast episode @cassidoo, @abbycabs and @helenhousandi explore tiny wins, accessibility-driven UX, and what AI can teach us about better collaboration. the-github-podcast.simplecast.com/episodes/tiny-…

Stop repeating your instructions. 🛑 Copilot now supports Agent Skills, the open standard by @AnthropicAI. Package your specialized expertise into skills once and use them everywhere. Try it in: ✅ agent mode in @code Insiders ✅ Copilot coding agent ✅ Copilot CLI Here's how to get started. 👇 github.blog/changelog/2025…

GitHub Copilot is smart, but it can’t read your mind. 🧠 Think of custom instructions like onboarding a new teammate. You need to transfer that "institutional knowledge" to get the best results: 🛠️ The stack 📋 The rules 🎯 The goal Here are 5 tips to write instruction files that actually work. ⬇️ github.blog/ai-and-ml/gith…

GPT-5.2 is now rolling out to everyone. openai.com/index/introduc…

Why did we build Antigravity? Our Head of Product Engineering @kevinhou22 breaks this down in his keynote from @aiDotEngineer

gemini 3 vibe coding hackathon starts now build your best app to solve a real-world problem across science, health, education or business. $500,000 in Gemini API credit prizes competition ends dec 12

The VS Code ecosystem is unreal. • You can write Python in VS Code • You can write Java in VS Code • You can write Shell scripts in VS Code • You can build Dockerfiles in VS Code • You can write Terraform in VS Code • You can manage Git from VS Code • You can edit YAML files in VS Code

Install MCP servers in your workspace 🚀

Learn how to build a Gemini 3 Deep Agents with this video from @langchain. These agents can reason through complex, long horizon tasks by: > Breaking goals into actionable steps > Delegating specific work for specialized models > Leveraging file systems and code execution

Claude Opus 4.5 is now rolling out to GitHub Copilot in public preview, and will be available at a promotional 1x premium request multiplier through December 5! 🙌 Early testing shows Claude Opus 4.5 👀 - Surpassed internal coding benchmarks, while cutting token usage in half - Is great for code migration and code refactoring See it in action, and try it for yourself. github.blog/changelog/2025…

Nano Banana Pro combines state-of-the-art text rendering with Gemini 3’s advanced reasoning to unlock a whole new world of possibilities for your product mockups, posters, infographics and more. Dive into some of our favorite use cases 🧵

🍌🍌🍌Nano Banana Pro is rolling out incrementally to Google Antigravity users. Our agents have gotten even better at generating UI mockups, system diagrams, or relevant embeddable assets, all grounded in your existing codebase and knowledge.