As noted by others, we already announced parts of /teamwork in Antigravity here: https://antigravity.google/blog/teamwork-when-ai-becomes-a-r... with more visualizations and more. Thi post was meant to report some advances in math/science/coding/engineering to show-case examples of tasks you can do with it.
We are constantly improving/evolving /teamwork and pushing those changes for external users. Will also post more about improvements and details for building teams of agents dynamically as Antigravity blog posts soon. Stay tuned!
Also I added a list of examples here: https://x.com/mirrokni/status/2121351383236436247?a=ma9UPZg_... and https://lnkd.in/p/esVTpR6p. I'll add a comment with examples as well.
When to use teamwork vs boost vs swarm?
Both take a long time. It used to be that antigravity was much faster than codex, but with recent releases it is substantially slower.
Inspecting the agents communication in teamwork, there seems to be an overwhelming amount of ceremony: BRIEF.md, specialized roles, multiple rounds of checking. Is all that necessary? Codex also uses agent âswarmsâ but unless theyâve hidden how the sausage is made, it doesnât seem so heavyweight.
Here is a short list of example results reported on the post; again we will have dedicated Antigravity posts for some of these.
* Math Open Problems & Formal Verification: Reporting 10+ open math and CS theory problems solved including 50M-line Lean 4 proof of CourtadeâKumar conjecture plus progress on several open problems in quantum query complexity, Tarjan's Deque Conjecture.
Also autonomous Lean formalizations of the Weil (1.8M lines), Birkhoff, and 3D BochnerâRiesz conjectures via Teamwork-LEAP, plus updates on Deep Review for STOCâ27.
* Several Systems, TPU Kernel, & Infra: * Clustering 1-Trillion-edge graphs on FarArray and RDMA (up to 180Ă faster), * 800K-line Zircon & 170K-line libgav1 safe Rust rewrites (20â30% faster than C++/ASM), * 4.09Ă JAXBench TPU kernel speedups with DuoDiscover, * Google internal examples: surpassing 1 PiB fleet memory savings, and 24% fewer Borg TPU preemptions for Borg Scheduling.
FWIW, since Argon 4 was launched I used Antigravity (without the /boost or the /teamwork flags) for "playground research" and had some discoveries in cryptography[1] and speeding up Python, removing the GIL, improving the JIT, and optimizing it for certain libraries (e.g. NetworkX) [2]. I don't know how stable is the Python one but it passes the included tests. I have spent some GC budget on it though.
Is CausalAnalyst the causal inference benchmark it talks about? Where are the results?
Related: I've been finding a lot of success (defined as more autonomy with less quality dropoff) with team-based workflows.
A lot of evidence for this.
- Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams (https://arxiv.org/abs/2606.01770) talks about multi-agent, role-based adaptive harnesses collaborating on non-homogeneous workstreams
- team-solve (https://github.com/guregodevo/memdoor/tree/main/examples/wor...) team of small models beats Fable on LiveCodeBench
- Agensh paper (https://arxiv.org/html/2609.26781v1) also talks about "role-playing agents to study autonomous cooperation"
All show that role-based, multi-agent setups improve performance.
It is not clear to me how or if /teamwork is any different than Claude dynamic workflows.
Antigravity as a harness feels very behind. There's not even any auto mode. And they announced /goal long after I ever felt the need to use it in CC or Codex.
Auto mode has been there for few versions, and recently (1-2 days ago?) became the default
This doesn't tell me how to use it.
The amount of breakthroughs this could deliver. Previously we shouldâve established R&D departments, prepare multi-cultural teams, all to work on a single project. Today? I can see a domain expert, guiding antigravity and delivering fast.
[flagged]
I think the authors also used Antigravity to write this article, because it sucks at communicating whatever point itâs trying to make. I think itâs something like âWe did the OpenAI 100 problems thing, but across many disciplines, and in collaboration with the experts instead of just dumping results on the world, and we also made the tooling feature available,â but Iâm not sure because it has that distinct Gemini flavor of packing in so many low-level details that the actual point becomes entirely obscured.
It is a shame that Gemini prose has become too detail dense in recent releases. Its prose was one of its distinct advantages over Claude with that annoying Claude speak...
It seems like they already announced /teamwork earlier [0], but now just announced that they got some scientific results out of it. They probably intentionally want to keep this low key, but in that case it's not clear why announce it at all.
[0]: https://antigravity.google/blog/teamwork-when-ai-becomes-a-r...
It sounds like they're saying they now offer an option, "/teamwork", that will throw more computer at a problem by choosing a team and a workflow that you the user don't have to (or get to?) know about.
> I think the authors also used Antigravity to write this article, because it sucks at communicating whatever point itâs trying to make.
The pattern seems to be pervasive at Google. Too much Ai, not enough human, top-down orders
Get a daily email with the the top stories from Hacker News. No spam, unsubscribe at any time.