Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

What does an agent first IDE look like? Our Head of Product Engineering breaks down the unique interaction surfaces that make Antigravity work: the Editor, the Browser, and the Agent Manager.

Google Antigravity

174,360 subscribers

144,331 views • 7 months ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

What are the core primitives powering Antigravity in 2026? Kevin Hou breaks down why we’re investing in dynamic agent teams, active sidecars, and generative UI to build the future of autonomous engineering.

What are the core primitives powering Antigravity in 2026? Kevin Hou breaks down why we’re investing in dynamic agent teams, active sidecars, and generative UI to build the future of autonomous engineering.

Google Antigravity

57,666 views • 16 days ago

Antigravity is unapologetically agent first. [1/9] Welcome to the "Age of Artifacts": multi-modal agents across your IDE and browser. It's more than just a code editor. Here's what I had to say at AI Engineer summit nyc a couple weeks ago 🧵

Antigravity is unapologetically agent first. [1/9] Welcome to the "Age of Artifacts": multi-modal agents across your IDE and browser. It's more than just a code editor. Here's what I had to say at AI Engineer summit nyc a couple weeks ago 🧵

Kevin Hou

53,341 views • 7 months ago

Granular code control or prompt-driven development? In Antigravity, you exist in both worlds. Dive into the Editor for deep work. Pull back to the Agent Manager to manage multiple agents across workspaces. Switch between them instantly. Watch the Manager and Editor in sync 👇

Granular code control or prompt-driven development? In Antigravity, you exist in both worlds. Dive into the Editor for deep work. Pull back to the Agent Manager to manage multiple agents across workspaces. Switch between them instantly. Watch the Manager and Editor in sync 👇

Google Antigravity

70,384 views • 7 months ago

This week we introduced Google Antigravity, a new agentic development platform where agents operate across the editor, terminal, and browser. Check out this tutorial to get started. Highlights: 00:00 Overview 00:44 Agent Manager, editor, browser 01:48 Agent-assisted development 02:15 Initial prompt and implementation 03:30 Artifacts for agent accountability 05:09 Antigravity browser extension 06:12 Parallel tasks via the Inbox 06:40 Nano Banana image generation integration 08:08 Artifact review 11:18 Testing application 12:47 Walkthrough

This week we introduced Google Antigravity, a new agentic development platform where agents operate across the editor, terminal, and browser. Check out this tutorial to get started. Highlights: 00:00 Overview 00:44 Agent Manager, editor, browser 01:48 Agent-assisted development 02:15 Initial prompt and implementation 03:30 Artifacts for agent accountability 05:09 Antigravity browser extension 06:12 Parallel tasks via the Inbox 06:40 Nano Banana image generation integration 08:08 Artifact review 11:18 Testing application 12:47 Walkthrough

Google AI Developers

42,550 views • 8 months ago

Google just showed the part of the agent stack most people are still underestimating. Not the model. Not the chat UI. The memory substrate around the agent. In this Antigravity segment, Google describes an agent-first environment built around: - agent conversations - agent-produced artifacts - multi-agent orchestration - subagents - hooks - asynchronous task management That is not a nicer IDE. It is what happens when software stops being a sequence of chats and starts becoming a persistent workforce. Karl's article explains why the winning agents will not just be the ones with the smartest rented model. They will be the ones that remember what they did, what they learned, what changed, and what can be trusted. Full breakdown below.

Google just showed the part of the agent stack most people are still underestimating. Not the model. Not the chat UI. The memory substrate around the agent. In this Antigravity segment, Google describes an agent-first environment built around: - agent conversations - agent-produced artifacts - multi-agent orchestration - subagents - hooks - asynchronous task management That is not a nicer IDE. It is what happens when software stops being a sequence of chats and starts becoming a persistent workforce. Karl's article explains why the winning agents will not just be the ones with the smartest rented model. They will be the ones that remember what they did, what they learned, what changed, and what can be trusted. Full breakdown below.

Karl Mehta

13,930 views • 1 month ago

The future of software development is here. Our Agent Manager serves as your primary surface for orchestration, while the Editor is your tool for precision debugging and manual refinement. Seamlessly move between the big picture and the fine details without losing context.

The future of software development is here. Our Agent Manager serves as your primary surface for orchestration, while the Editor is your tool for precision debugging and manual refinement. Seamlessly move between the big picture and the fine details without losing context.

Google Antigravity

122,770 views • 6 months ago

Google just launched a new Agentic IDE called Antigravity. Of course it's a VS Code fork, but they have some interesting moves around the built in browser, puppeteer, planning + tasks and an agent inbox. Full video →

Google just launched a new Agentic IDE called Antigravity. Of course it's a VS Code fork, but they have some interesting moves around the built in browser, puppeteer, planning + tasks and an agent inbox. Full video →

Wes Bos

50,194 views • 8 months ago

Instead of a browser in your IDE, what if you brought your IDE to the browser? I’ve been Warping a chrome extension that brings your local agent session to your browser’s sidecar, lets you check on your cloud agent runs at a glance, and kick off agent runs. what do we think? using Aiden Bai’s react-grab library here 🙏

Instead of a browser in your IDE, what if you brought your IDE to the browser? I’ve been Warping a chrome extension that brings your local agent session to your browser’s sidecar, lets you check on your cloud agent runs at a glance, and kick off agent runs. what do we think? using Aiden Bai’s react-grab library here 🙏

sathvik

13,195 views • 1 month ago

"You'll see this in a big way with the software engineering agent." He points to SWE agents, where 50¢ of compute can yield "$500 / $5,000 of work." The SWE agent will be the first major impact that will make people think about the economy with shock.

"You'll see this in a big way with the software engineering agent." He points to SWE agents, where 50¢ of compute can yield "$500 / $5,000 of work." The SWE agent will be the first major impact that will make people think about the economy with shock.

Chubby♨️

111,704 views • 1 year ago

We built Artifacts so you don’t have to guess what the agent is doing. They are dynamic intermediates, the shared source of truth between you and the agent.

We built Artifacts so you don’t have to guess what the agent is doing. They are dynamic intermediates, the shared source of truth between you and the agent.

Google Antigravity

138,919 views • 6 months ago

Introducing Design System Agents. Turn your repos, npm packages and docs into an agent that builds prototypes engineering can actually ship. The Prototype is t̶h̶r̶o̶w̶n̶ ̶a̶w̶a̶y̶ the Product.

Introducing Design System Agents. Turn your repos, npm packages and docs into an agent that builds prototypes engineering can actually ship. The Prototype is t̶h̶r̶o̶w̶n̶ ̶a̶w̶a̶y̶ the Product.

bolt.new

116,955 views • 3 months ago

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

80,428 views • 11 days ago

We asked Antigravity to onboard a new designer. It crawled our site for our fonts, logo, and color palette, compiled the specs into a walkthrough, and drafted the email in Gmail. From the agent manager to website to inbox. Back to building. 💻

Google Antigravity

133,412 views • 6 months ago

Does Byron Buxton fit the Dodgers need for an outfielder? 👀 @AlannaRizzo breaks down why it could make sense and what a hypothetical deal might look like.

Does Byron Buxton fit the Dodgers need for an outfielder? 👀 @AlannaRizzo breaks down why it could make sense and what a hypothetical deal might look like.

Dodgers Territory

99,779 views • 8 months ago

Orchids is rebranding to Bud: the first agent with a full computer. Since our launch in September of last year, we’ve grown to well over 7 figures ARR in record time. We’ve simultaneously come to realize that an agent that builds apps is just the first step in a future where an agent does the majority of human work. Comment below to get early access or go to bud [dot] app.

Orchids is rebranding to Bud: the first agent with a full computer. Since our launch in September of last year, we’ve grown to well over 7 figures ARR in record time. We’ve simultaneously come to realize that an agent that builds apps is just the first step in a future where an agent does the majority of human work. Comment below to get early access or go to bud [dot] app.

Bud

123,558 views • 3 months ago

Deep Research Combined With Powerpoint Our PowerPoint agent - gathers requirements - does deep research and gathers content - creates an outline for each slide - lets you make edits and upload a template and presents the final result in the form of a finished product!!

Deep Research Combined With Powerpoint Our PowerPoint agent - gathers requirements - does deep research and gathers content - creates an outline for each slide - lets you make edits and upload a template and presents the final result in the form of a finished product!!

Bindu Reddy

23,520 views • 1 year ago

Demis Hassabis reveals Google's three-stage stack rewrite: AI first, model first, agent first. Bolting agents onto normal software does not scale to billions. "We've got to, we've done a lot of engineering work under the hood in the last year, which you'll see, you see the surface of when we announced things like this." "But actually, you can almost think that whole stack had to be rewritten to be sort of AI first, model first, and now agent first." "So that's quite a big change from like normal software." "And obviously there's all this huge infrastructure that serves billions of users every day at lightning speed and that's all gonna work." "And I think we've made massive improvements on that over the past year. And that's why you can see all the goodness of the AI models flowing through into our product surfaces so quickly and in such compelling ways." Most companies are adding an agent interface to yesterday's software. Demis says Google changed the substrate itself. The moat may not be the model. It may be the infrastructure that lets the model reach billions of users every day without breaking. - Demis Hassabis (Demis Hassabis), CEO of Google DeepMind, with Rowan Cheung at Google I/O 2026

Demis Hassabis reveals Google's three-stage stack rewrite: AI first, model first, agent first. Bolting agents onto normal software does not scale to billions. "We've got to, we've done a lot of engineering work under the hood in the last year, which you'll see, you see the surface of when we announced things like this." "But actually, you can almost think that whole stack had to be rewritten to be sort of AI first, model first, and now agent first." "So that's quite a big change from like normal software." "And obviously there's all this huge infrastructure that serves billions of users every day at lightning speed and that's all gonna work." "And I think we've made massive improvements on that over the past year. And that's why you can see all the goodness of the AI models flowing through into our product surfaces so quickly and in such compelling ways." Most companies are adding an agent interface to yesterday's software. Demis says Google changed the substrate itself. The moat may not be the model. It may be the infrastructure that lets the model reach billions of users every day without breaking. - Demis Hassabis (Demis Hassabis), CEO of Google DeepMind, with Rowan Cheung at Google I/O 2026

Karl Mehta

35,821 views • 7 days ago

What could the future of human-agent interaction look like in your browser? 🌐 Project Mariner is a research prototype built with Gemini 2.0 that’s able to research information and carry out tasks directed by you through an experimental Chrome extension. See it in action ↓

What could the future of human-agent interaction look like in your browser? 🌐 Project Mariner is a research prototype built with Gemini 2.0 that’s able to research information and carry out tasks directed by you through an experimental Chrome extension. See it in action ↓

Google DeepMind

71,263 views • 1 year ago

Introducing the new dev-browser cli. The fastest way for an agent to use a browser is to let it write code. Just `npm i -g dev-browser` and tell your agent to "use dev-browser"

Introducing the new dev-browser cli. The fastest way for an agent to use a browser is to let it write code. Just `npm i -g dev-browser` and tell your agent to "use dev-browser"

Sawyer Hood

866,903 views • 4 months ago

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

119,783 views • 1 month ago