Run many agents at once: the Manager Surface
Goal. Stop working one agent at a time — spawn and watch several in parallel from the Manager Surface.
Agent 1: refactor this analysis script into modules with type hints. Agent 2: write pytest tests for the normalisation step. Run both now.
Open the Manager Surface, spawn two agents on these two independent tasks, and watch them work side by side.
- 1Open the Manager Surface — the control room where you spawn, orchestrate and observe multiple agents running in parallel across workspaces.
- 2Give each agent an independent task (no shared file, no 'do A then B'), so they can run at the same time without stepping on each other.
- 3A big job can also be split across subagents that each take a piece — useful when one task naturally breaks into parallel parts.
You'll see. Two or more agents running concurrently in the Manager Surface, each making progress on its own task while you watch.
Cost. Parallel agents draw from the same weekly rate-limit pool on the free plan, so they finish a multi-part job faster but don't make it cheaper — for heavy parallel use, Google AI Pro raises the limits (see antigravity.google/pricing for current plan pricing).
Takeaway. The Manager Surface is the whole point of Antigravity: orchestrate many agents at once instead of babysitting one.