Google Antigravity 上线 Dynamic Workflows，用 Python 脚本编排子智能体
做智能体编排的可以试试：Antigravity 现在让 agent 自己写 Python 脚本调度并行子任务，控制流确定、跑之前还能人工审一遍，比纯提示词链稳定。想取代 LangGraph 那类固定编排的团队值得动手测一下。
Google Antigravity 推出 Dynamic Workflows 功能：输入 /run-workflow 后，智能体会自动编写 Python 脚本来编排并行与串行运行的多个子智能体，并在子智能体之间做结构化交接。
其核心机制是用可审查、可复用的代码实现确定性控制流，替代纯提示词驱动的流程漂移。用户可以在脚本运行前先检查内容，运行后把脚本保存下来，随时重跑同一套流程。
官方透露团队内部大量使用该功能，让智能体自己写程序来编排 Hydrogen 和 Carbon，且无需手动调用 /run-workflow，模型可自主判断何时触发，类似 swarm 的调度方式。后续还有更多功能在路上。
Dynamic workflows are another extremely used feature internally. Very powerful to give agents the ability to write programs to orchestrate Hydrogen and Carbon. You don’t even need to /run-workflow, the model should be able to decide similar to swarms. Still more to come 👀 Google Antigravity @antigravity We're rolling out Dynamic Workflows in Google Antigravity. Use /run-workflow and the agent writes a Python script to orchestrate parallel and sequential subagents with structured handoffs, giving you deterministic control flow instead of prompt drift. Review the script before it runs, and save it to re-run the same flow anytime.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Google Antigravity, agents, coding assistants, workflow orchestration.
Source attribution: curated from Varun Mohan (@_mohansolo).
