Course contents
Autonomy: Permission Presets and Review Policies
Decide what an agent may do without asking: the App's four permission presets, the Plan Review Policy, your own allow, ask and deny rules, and the CLI's execution modes.
Every agent tool has to answer one question: what can the agent do without asking you? Too little autonomy and you become a click-to-approve machine. Too much and one bad instruction runs unchecked. Antigravity answers it with settings that stack: a permission preset, a plan review policy, and your own allow, ask and deny rules on top.
Four presets in the App
As of November 2026 the App offers four permission presets, and Default is selected out of the box. You change the preset in Settings > General > Global Permissions > Permission Preset, or override it for one project in Settings > Projects.
| Preset | Terminal sandbox | Terminal commands | Files | MCP and web |
|---|---|---|---|---|
| Request Review | Off | Always ask | Project only | Ask |
| Default | On | Run in the sandbox; ask outside it | Project and temp folders | Ask |
| Auto | On | Run in the sandbox; outside it, safe reversible commands run and risky ones ask | Project and temp folders | Ask |
| Turbo | Off | Allowed, unrestricted | Full filesystem | Allowed |
The sandbox is an operating-system boundary (Seatbelt on macOS, kernel namespaces on Linux, AppContainer on Windows) that limits commands to the project and temp folders, with no network by default. Auto isn't available on business or enterprise accounts. Explore what each preset does to the same set of actions.
Simplified from Antigravity's permissions docs as of November 2026. Your own Allow and Ask rules move individual actions; Deny rules block under every preset.
Move the controls and watch what changes.
Switch the widget to Turbo. One action is still blocked. Why?
Plan Review Policy
The preset governs actions. The Plan Review Policy in Settings > General governs whether the agent stops after planning. Request review, shown in Settings as Always Ask, means the agent halts and asks for your approval before it acts on proposed changes; Google labels it recommended. Always proceed removes that mandatory stop. Under either policy, asking for a plan with /plan stops for your approval.
Your rules sit on top
Presets are starting points. You add rules in three lists: Allow runs without asking, Ask pauses for you, and Deny blocks immediately. Rules always take precedence over the preset, and among themselves Deny beats Ask, which beats Allow. Each rule targets an action: read_file and write_file take paths, read_url, execute_url and download_url take domains, command takes command prefixes, and mcp takes a server or a tool. The docs' own example Deny rules safeguard Git history (.git/) and SSH keys (~/.ssh). In the CLI the same rules live in a settings file:
{
"agentMode": "accept-edits",
"permissions": {
"allow": ["command(npm test)", "command(npm run lint)"],
"ask": ["command(git push)"],
"deny": ["command(rm -rf)"]
}
}Configure the CLI so file edits in the workspace apply without asking, other terminal commands still ask unless a rule allows them, and every git push waits for you.
The CLI's execution modes
| Mode | File edits | Terminal commands |
|---|---|---|
default | Shows a diff and waits for you | Asks first |
accept-edits | Applied automatically inside the workspace | Asks first |
auto | Applied automatically | Run in the sandbox; outside it, safe reversible ones run and risky ones ask |
plan | None until you approve a plan | Reads and proposes first |
Shift+Tab cycles the modes, agy --mode=auto sets one for a single run, and agentMode in settings.json saves your default. In the CLI the terminal sandbox is a separate setting and it's off by default: turn it on with agy --sandbox or Sandbox Mode in /config. auto needs the sandbox and a personal account. --dangerously-skip-permissions approves every request without asking, and the name is accurate.
Earn each loosening
Start every new project on Default with plan review on. Loosen per project, not globally, and only after the agent has a track record there: a repo with a solid test suite and a run of clean reviews might move to Auto. Keep Turbo for throwaway sandboxes, never a machine that holds production credentials. Two checkpoints are worth keeping at any level: plan review before edits, which catches wrong scope while it's free, and your review of the walkthrough and diff before merge, which catches wrong outcomes while they're cheap.
Loosening autonomy on a real repo
You've used the Default preset on your team's API repo for two weeks. Its test suite is solid and the last eight agent runs passed review cleanly. You're tired of approving the same install prompts.
What do you change?
Plain-English definitions from the AI Coding Dictionary.