Matt Pocock's Skills 1.1 just dropped: 🧭 Wayfinder: progressive discovery for multi-session work 🔬 Background research agents 📋 Consolidated planning pipeline 🔍 12 Fowler smells in code review 🎯 Grilling won't answer its own questions ✂️ TDD trusts the agent npx skills@latest add mattpocock/skills

2 major model releases today! You can generate cost-efficient images in 4 seconds with Nano Banana 2 Lite (GA). And with Omni Flash, you can generate video with real-world knowledge and perform conversational video editing (Preview). And yes, the infographic was created with Nano Banana 2 Lite!

Most developers don't think of AI agent skills as dependencies. But they behave just like them. An agent skill is a package of instructions and scripts that help an agent accomplish tasks. Just like code libraries, these instruction sets drift as the underlying APIs and systems evolve.

Infrastructure setup is the ultimate "stop energy" for new ideas. How many times have you abandoned a side project because configuring billing accounts, APIs, and security poliicies stalled your momentum? The Starter Tier on Google Cloud demolishes this friction 👇

I will show you how to prevent your AI coding agent from building the wrong thing. Use the /grill-me skill so it knows what you really want. A few extra questions upfront saves lots of refactoring and frustration later.

The happy medium is here in Gemma 4 12B: powerful capabilities at a size that fits well on your laptop. Multimodal, Apache 2 license, reasoning, and much more.

The app generates audio diagnostic reports, and suggests changes to improve the quality. 🛠️ AI Studio: ai.dev 💻 Code: github.com/kweinmeister...

Medium doesn't support markdown tables. So I built an MCP server that converts them to styled PNG images right from Antigravity. Wrote up how the rendering works and how to build your own. medium.com/google-cloud...

Gemini Spark - all new AI agent. It’s going to help me stay organized and even create slide decks. #GoogleIO

Can’t wait to try out the Gemini Omni model. Stay tuned for a video on how to edit video with it! #GoogleIO

Agents: meet IoT! 🤖 @rsamborski.bsky.social is having fun connecting his @raspberrypi.com to the Google ADK. Check out how he did it with all the code and a video demo in the 🧵.

Developers in NYC, Austin, SF, Seattle, Toronto, and Chicago: Registrations now open for hands-on workshops May 26-June 30. Hope to see you there! goo.gle/ai-toolkit

Now you can put a small “drafter” model in front of Gemma 4. Multi Token Prediction, AKA speculative decoding, is here. This configuration guarantees the same quality at up to 3x the speed!

Google Cloud Next 2026 kicks off today with 3 developer announcements: * Google Agent Skills: github.com/google/skills * 75+ new codelabs: codelabs.developers.google.com * New Builder Hub: builders.google Give me a shout if you're in Las Vegas this week!

You can now combine Google built-in tools with your own custom tool! I'm excited to see this feature in the Gemini 3 API. Google Search, Google Maps, File Search, or URL Context, Code Execution, and Computer Use can now be directly integrated with your agent.

LLM Checker recommends the best model for your hardware. It scans 200+ Ollama models for optimal quality, speed, fit, and context. Here it selects Gemma 3 270M to run my coding task.

Need to automate deep research? Use the Gemini Interactions API with the right async pattern. 🧵

Did you know there's a benchmark for writing quality? Hemingway-bench from Surge AI goes beyond "vibes" and robotic checks, to measure coherent and relatable storytelling.

Watch out for 4 pitfalls when you create infographics. Nano Banana 2 🍌 can help you out!

Are you using the skills CLI? My Gemini CLI and Google Antigravity skills are well-organized, thanks to this great tool from Vercel.

Want to try out two awesome pieces of tech? Cloud Run now supports NVIDIA RTX 6000 Pro GPUs with 96GB VRAM and scale-to-zero inference. And the new Qwen 3.5 multimodal models are achieving outstanding benchmark results.

Reasoning has been supercharged in Gemini 3.1 Pro, and your agents will benefit. Industry-leading abstract thinking translates into strong performance on agentic workflows and MCP tool-calling.

Not only is Valentine's Day ♥️ approaching - the 2026 Build with AI North America Tour is kicking off tomorrow! I'm here in Dallas to keynote two action-packed days. And yes, we still have a few spots available! 👉 Registration for Dallas and 5 more cities: cloud.google.com/blog/topics/...

2025 was a great year! And 2026 started off with a bang with a productive team offsite. So, what's a better way to reflect on 2025 than my Gemini CLI usage? 😂 Try it out yourself with `npx gemini-wrapped`. Fingers crossed for an Antigravity Wrapped tool, the way 2026 is shaping up so far. 😉

Today's antigravity.google release includes Gemini 3 Flash support. With 78% on SWE-Bench Verified and low latency, it's a great choice for everyday coding tasks.

Human-in-the-Loop is an architectural pattern that inserts a manual approval step into an automated process. It's used to mitigate AI errors when agents are given tools. Learn more: GitHub: github.com/kweinmeister... Website: kweinmeister.github.io/agent-design...

I put antigravity.google to the test as my daily editor. Here's my story of how building a full-stack app went.

Agent Sandbox debuted at #Kubecon, unlocking a critical capability for agents: running untrusted actions. Safely validate generated code, test user input, and more. Blog post: cloud.google.com/blog/product... Documentation: docs.cloud.google.com/kubernetes-e... Code: github.com/kubernetes-s...

Now you can see two websites in a single tab, with Chrome's new Split View. Enable with "Split View" flag at chrome://flags. ⚠️ As an experimental feature, it could change or be removed at any time. #browser #googlechrome #techtips

n8n AI automation docs for Cloud Run are now here! docs.n8n.io/hosting/inst...