Gemini 3.5 Flash 🤝 Google Antigravity Watch how the model deploys multiple subagents to design and build an entire city.

Find out more →

@antigravity Everyone's eyeing the city layout, but the real win's the subagent orchestration. If it can't handle conflicting constraints between agents, it's just a fancy simulation.

Used subagents to design our entire go-to-market structure last quarter. Main agent assigned territories, built the comp plan, hired 6 SDRs, and allocated budget. Our CFO found out when payroll ran. She said 'none of these people are real.' They are not real. The quota attainment is still impressive.

@antigravity watching subagents coordinate to design and build an entire city in real time is the kind of demo that makes you put your phone down and just stare. this is the Google that people kept saying was sleeping. turns out they were just loading 🤭

@antigravity The coordination layer is kinda the whole bet. I'm curious how it handles rollback when one subagent's output breaks another agent's constraints.

@antigravity To actually achieve this how much token usage is needed really ? I mean I assume you would hit limits fast with all these sub agents ?

@antigravity New UI is 🤮

@antigravity wow, this is cool af.

@antigravity The interesting part isn’t even the benchmark jump anymore. It’s that models are starting to behave less like “chatbots” and more like operating systems coordinating specialized agents in parallel. We’re slowly moving from prompting intelligence → directing intelligence.

@antigravity

@antigravity hey ， like this

@antigravity im sorry but this example is so bad, no? like its generating almost nonsense. im sure the tool is usefull for something ... but this?

@antigravity Gemini 3.5 flash+ code execution tools = god tier , in ai studio it auto test and do auto benchmark its amazing and efficient

@antigravity Love google

@antigravity Was hopeful for antigravity but lack of extensions (like giving me access to Claude code) make it useless for my needs. Downloaded update, struggled as the help gave outdated advice, then deleted.

@antigravity Incrível de verdade! Muitos ainda não se deram conta da grandiosidade e poder do Gemini 3.5 Flash.

@antigravity

@antigravity "What if we shoved AI into every aspect of your fucking lives!"

@antigravity Please resolve the limits issue. The project can't be completed in three hours. Tokens are disappearing faster than people expect. Compare this to the Codex. @GoogleDeepMind

@antigravity AI is moving WAY faster than most people expected.

@antigravity We went from autocomplete to building cities. The jump in capability this year alone is hard to process

@antigravity Sick multi subagents demo

@antigravity can’t wait for the subagents to start unionizing

@antigravity hmmm? nie ogarnia

@antigravity Antigravity is cool

@antigravity The subagent orchestration is the real story here — specialised agents with scoped contexts beat one monolithic prompt for spatial planning. Curious how they handle inter-agent state sync and failure recovery at scale. Agentic architecture > raw parameter count.

@antigravity The multi-agent city build is a strong demo because it shows planning, delegation and execution together. That is where these models start feeling useful for real projects.

@antigravity multi-agent orchestration at this fidelity is the real unlock — single-model bottlenecks are the bigger constraint than raw parameter count.

@antigravity Subagents are where the demo starts to resemble real work. The operator question becomes coordination: who owns the plan, how conflicts get resolved, what evidence each subagent returns, and how the final result is judged before anything hits production.

@antigravity Sorry, but splitting the old application into two separate ones wasn't a great move. Installing both Antigravity 2.0 and Antigravity IDE now just gives me exactly what we had before in a single application.

@antigravity Looks like Google fixed housing problem.

@antigravity Please retain Gemini CLI

@antigravity 3.5 flash it's impressive but, hey! I was never reaching the limit for the previous model. Now I did it in record time. (Plus user)

@antigravity Subagent orchestration for complex spatial tasks is where things get genuinely interesting. Not "AI writes code" interesting, but "AI models understand dependencies and parallel workstreams" interesting. That's a different level of reasoning.