NEW Antigravity Agent Teams Update is INSANE!

There's a brand new update from Antigravity. It's called Agent Teams in Antigravity. This is a new powerful system to build a dynamic team of specialized sub-agents. They can coordinate in the background, to plan, build and verify complex systems in the background of working parallel, which is really, really powerful.

So to do this, we've actually plugged in the Antigravity CLI into our Agent OS, as you can see right here. And just to test it out, I actually ran teamwork-preview for an SEO blog as a test over here, and you can see that it actually came up with the answer very quickly, so it creates a markdown file with a full plan for your agents, and then you can actually run it live, as you can see right here, and spin up the agentic sprint directly in the dashboard, which is pretty powerful. So you can just open it up and start running it straight away. And then the cool thing about this is the whole plan gets saved inside your workspace, so we can come back to it later.

So this is something I call the one command company. So Google's Antigravity can now spin up a whole team of AI specialists from one command, they plan, they build, they check in parallel and hand you the finished thing, actually testing it the day, and two of the builds are playable right inside the guide that I'm going to show you. Now you might wonder, okay, why is this useful? So I would talk about the Q of one problem, which is, you know, imagine running a company with a single employee, you know, brilliant, but it's still just one, they plan the project, they build the first part, then the second part, then they check it one thing at a time and aligned.

Now, if you double the amount of tasks they have to do, you double the weight and who splits the working pieces, who writes each job description, who remembers to check the result before it ships, what you do on every project, every single time. And that's what working with one AI agent is like. The model is brilliant, but the project management never stopped being your job. The one command company set up with Antigravity breaks that cycle because one command basically has a team, briefs the team and runs the team as well.

So what does agent teams actually do? Antigravity is Google's AI coding agent. It's the successor to their Gemini CLI and until now it was one worker. However, when you use a type and you type forward slash teamwork, hyphen preview, it becomes a hiring manager.

So you get a coordinator that reads your task, then drafts a team sheet, which specialists to hire, what each one owns and how they'll hand the work to each other, you say, yes, it spins the team up for real. So you literally just approve the plan and then it will build the whole thing out once, which is pretty incredible. So the way this works is you have a coordinator that drafts a team and reads the work, the plan and designs, builder A builds, builder B builds, and you get a verifier checker that works through it as well. So here's an example.

We actually created this plan for the team sheet, as I showed you a second ago. So inside our agent OS, we have Antigravity over here. And then inside the chat, we said, you know, teamwork preview, create that page, right? And so what it actually does is it creates an idea of team sheets here.

So we've got the SEO architects, the Next.js developer, SEO Ops, and the Lighthouse X, which is a QA developer as well, and actually plans out exactly how it's going to be built. And then the same run can actually be simulated live. And here's an example of what it can look like in real time. So we have the multi-agent collaborate preview, preview orchestrator, we can switch between sub-agents and the template presets, then it has the full project objective features.

And then it goes off and starts spinning up the full workspace with your team of agents working together, which is pretty awesome. Now, some people say you need to be technical to run an AI team of agents. Actually, no, because literally all you do is in one single command, you type forward slash teamwork hyphen preview, and you're good to go on that. Other people say, well, more agents must get more expensive, but actually you can use the CLI for free.

Or you can actually plug in your own custom APIs into there as well. You could even, for example, run this with like a local model like Jemma4, which comes from Google directly as well. And then other people say, well, it's a preview. I should wait.

I don't want to start using this system straight away. But honestly, the people start building right now are going to get ahead. The people wait are going to fall behind. And so you can see some examples of what our team actually built here in terms of how they've worked together.

So with the builder, the planner, the coordinator, and with the verifier too. And then we can see the tasks that are being worked on and everything else. We have another one here, which is team splitter. And so you can actually select the project of what you want to build, describe the project, and it assembles the team of agents as well.

And you might also say, this is great, but a solo agent could build this too. Why have multiple teams of agents? But the thing is here that when you're building this out, if you have one single agent, it's slower, it's unchecked, there's no quality control. And you also don't have specialist agents that are very focused on their role.

So for example, like if you have a quality control sub-agent in the team preview, well, that's just going to focus on making sure the quality is the best it could be. If you don't have a quality control agent in place, it's going to be super messy. Now you might wonder, okay, how do you run this out? You know, how do you set it up?

So make sure you have the agent anti-gravity CLI set up, or you can get our agent OS with it already plugged in. And then you run the update for AGY update. So that's anti-gravity update inside the terminal. Then you can just, inside your anti-gravity CLI, you run the preview.

So for example, forward slash teamwork preview to set up the task. Here's an example. So you can go inside here, teamwork preview, and then we'll just say draft, create a team for a new blog about Hermes agent and AI automation. And you actually just start coming up with the full plan right there.

That's how we can set it up. So that's really powerful. You might also wonder, okay, where do the files usually end up? So they just get saved locally, which is really cool.

And then you have, for example, the anti-gravity tab inside our agent OS ready to go with the same engine as the chat. And what I really like about this whole system, you know, this is, I think much better than using the terminal is that you have the workspace files, so everything is saved in one place and you can just come back to it later. Plus this can just run in the background whilst we're doing other stuff. So we can have teams running and setting up stuff in the background.

So how does it work? You've got one command, teamwork preview. Then you've got one approval. So you read the team shape and you can say, say, you just say go and, or you can pre-approve it as well.

And then you get the parallel work done, as we showed a second ago, and it actually builds cool stuff, which is fantastic. So really powerful update. I know a lot of people don't like anti-gravity since the new CLI came up. That's actually why we built it into the agent OS because we want to customize the look and the feel and the vibe of it as much as we want using this system instead, which I think is way better.

And so if you look at the old way versus the new way, before you were the org chat, right? So you have one worker that does everything step-by-step. There's a lot more time involved. So every step adds more time to the process because you didn't have parallel agents working together.

And then you would only have quality control if you were allowed to ask the agents to do it. And also you would split the tasks and write role prompts by hand. Now with this new update from anti-gravity with teams and anti-gravity agents, you've got a coordinator that drafts the right specialists per task. You have builders that work in parallel.

And then you also have a verifier that checks everything before delivery and you have roles, briefs, and team handoffs also written with the whole system. So it's just a new way to orchestrate your AI agents as a team so that you can move faster so that you can get more out of anti-gravity so that you can build agent teams without having to be technical as well. And this is great for building apps, websites, games, tools. You can see an example right here of how to run it.

And we actually have the full project code here. We've got the assembled agent team. So it comes back to us with like the Hermes tech specialists, the content lead, the SEO ops, the sandbox agent as well for quality controlling it. And we can just open the dashboard directly as well, which is pretty cool.

So if you want to get our full agent operating system with anti-gravity, the workspace system with the mission control, we've got paperclip for team orchestration as well. We have Hermes agent, Claude. We have Codex and GPT 516 built in there. This is just a really powerful system for orchestrating all of the agents instead of having to like click everywhere and manage all your different tabs and go into Claude and then Hermes agent and everything else.

You can get our agent OS system that's available inside the AI Profitable Boardroom, link in the comments description or go to the AI Profitable Boardroom.com. Inside the community, you can ask questions, get help and support in real time. I personally answer each of the questions inside the community with a video every single day. Inside the classroom, you can get access to all of our best trainings.

If you actually type in anti-gravity, you can actually get all of our best masterclasses inside the classroom for anti-gravity as well. We have loads of cool trainings on this stuff if you like it. Inside the new daily update section, you can get our agent OS system and we're always dropping like new tutorials. So this is like the new latest stuff that you can get the most out of.

So as soon as something new and useful comes out, we share it and we teach you exactly how to use it and get the most out of it. If you want to jump on coaching calls, you can get weekly coaching calls here. We have four of them. So you can share your screen, jump on a Zoom call, ask questions in real time.

And then inside the map, you can actually meet people in your local area who are building out with AI agents like you. So feel free to get that link in the comments description or go to the AI Profitable Boardroom.com. Thanks for watching.