I've been using Google @antigravity for a few days, here are my impressions:
To me, it's not an IDE, it's a coding agent UI, powered by Gemini 3 Pro.
Notably, the agent can control a Chrome browser, enabling it to validate open and use the app and it builds.
Some @NotebookLM ✨polish✨ release notes from the last week:
1. Resizable panels! Notebook's panels can now be flexibly adjusted to fit your screen and workflow!
2. Improved chat input visual design for all those text-baseline obsessives (me)
3. The share icon, is now.... a share icon! (it was a padlock icon for some reason before...)
4. We pass 4x longer context to Flashcards and Quizzes unlocking more diverse, detailed card decks
5. Drive file URLs in the URL source import box works!
6. Tables are streamed in chat instead of blocking until the whole table is all done. Much better experience for large tables.
Love seeing improvements to core journeys. @NotebookLM team is cooking🔥
My comprehensive guide on building #AI#agents in #Java with the #ADK framework! 🤖☕
I've bundled everything you need to get started: my full article, the video recording at @Devoxx, a codelab, the slides, an updated template project, and code samples, all in one place.
I built a complete multi-agent, multi-player game using Google ADK.
Google ADK is the best agentic framework I've tried.
I had to use a ton of the features they offer (workflow and custom agents, callbacks, state management, tool management, etc.)
It's really cool!
Here are the four agents in the system:
1. Tournament Agent
This is the entry point of the system. You can ask this agent to start a new game, provide a tally of the results, and calculate several statistics about past games.
2. Game Agent
This is the engine behind each game. This agent is responsible for managing the board's status, giving each player their turn, and determining the winner.
3. Player Agent
This agent represents a player. This agent is responsible for selecting the strategy they'll use during a game and following it on each turn.
3. Commentator Agent
This agent examines the board and the current player's move, and it provides colorful commentary on the game's status. It's a fun narrator that keeps the user engaged throughout a game.
Seeing how these four agents collaborate is pretty magical, especially when you have an LLM running the strategy of the game, so you never know what will happen.
You can power the game with any model you want, but I tested it with gemini-2.5-flash and gpt-5-mini.
I'm really happy with the way things came out.
The source code of this game is part of the AI/ML Engineering program that I'll be running in November (starts in less than four weeks!).
I teach people how to build end-to-end AI/ML production-ready applications.
If you join, you'll leave one order of magnitude smarter than when you joined.
Here is the link to join: https://t.co/iZifcK7UTF
Introducing the first-ever Google Agents Development Kit (ADK) Community Call.
Come meet the team, learn about our AI Agents roadmap and ask any question you may have.
Happening next Wednesday at 9:30-10:30am PT (link below)
So many new AI terms are scaring both developers and leaders.
Once you dig into what they are technically, they feel very familiar.
- "Agent"? just code calling an an LLM and other APIs in a loop.
- "MCP server"? just a web server implementing a standard API.
Hosting these in the cloud? they just are container workloads.
* There are 100M knowledge workers in the US
* That's $10T/year in salaries
* My new startup can make them 10% more productive
* Even if we only capture 10% of the value, that's $100B/year
* We're selling coffee
* Invest in my coffee startup at a $1T valuation
August at Google DeepMind was like 🧞♂️ 🖼️ 🍌 🚀 🔍 🤏🏻
- Nano Banana (Gemini 2.5 Flash Image)
- Gemini Embedding
- Veo 3 Fast
- Genie 3
- Imagen 4 Fast
- Gemma 3 270M
- Perch 2
- Kaggle Game Arena
- Gemini API Url Context
- AI Studio Builder (UI Rework, Prompt Suggestions, GitHub integration …)
- AI studio UI (Model Picker, Chat, Scrolling…)
and much more!
Get started with Gemini 2.0 Flash's native image generation 🖼️ + editing using @nextjs, by @_philschmid, try it for free with the Gemini API!
https://t.co/lbWIZAs8g0
Unfortunately, the question, "Why didn’t Russians rise up and do something as Putin was destroying their democracy?" is becoming much easier to answer. What say you, Americans? Does this look like Trump and his gang are waiting for 2026 or 2028?
One word: relentless. just in the past two weeks, we’ve shipped:
🌐 Genie 3 - the most advanced world simulator ever
🤔 Gemini 2.5 Pro Deep Think available to Ultra subs
🎓 Gemini Pro free for uni students & $1B for US ed
🌍 AlphaEarth - a geospatial model of the entire planet
🏛️ Aeneas - deciphering ancient text (in @Nature)
🥇 Gemini gold-medal level at the IMO
🧸 Storybook - books w/art & audio @GeminiApp
♛ New @Kaggle Game Arena benchmark for LLMs
🐙 Jules, our asynchronous coding agent, out of Beta
🇬🇧 AI Mode for Search available in the UK
📔 NotebookLM Video Overviews
🔥 Gemma passed 200m downloads
Now you know why I don't get much sleep 🛌 - too busy pushing the frontier!