Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Agent approvals and governance

How Zerve's agents ask for approval, and the controls you have over what they do.

Zerve's agents can do real work: run code, deploy apps and use tools that reach other systems. This page explains when they ask for approval, and the controls you have over what they do.

What agents ask before doing

Action
What happens

Deploying

Before starting, updating or stopping a preview or production deployment, the agent asks you to confirm. Each user can turn this off with Don't ask before agent deployments in Preferences.

Using a tool that requires approval

For MCP servers marked Requires approval, the agent asks before using any of their tools

Irreversible changes

The agent always waits for you before doing something that can't be undone, whatever its other settings

Using a credential it doesn't have

The agent always waits for you to provide it

Controls for Workspace agents

Control
What it does

Ask mode can't change anything. Plan mode makes changes only after you approve its plan.

Whether Evolve Mode waits for your answers or carries on

The most a single Evolve Mode run can spend

Each custom subagent can only use the tools you give it

Which tools from each server the agent may use

People with view-only access to a notebook can only use Ask mode there.

Controls for superagents

Control
What it does

Rules the superagent follows strictly. They can't override Zerve's own safety rules.

Per objective: how freely the superagent decides, from Ask me first to Full autonomy

The superagent raises a decision instead of guessing, including before irreversible changes

Whether the superagent keeps working through its backlog on its own. Off by default.

The most its whole team can spend in a day

Who can message the superagent from outside Zerve. Closed by default.

Stops all of the superagent's work immediately

People with view-only access to a superagent can ask it questions, but can't start work or change anything.

Seeing what agents did

Every agent's work happens in a notebook, with real code and saved results, so you can check exactly what was done:

  • A superagent's Activity feed records what each team member did. See Monitor a superagent.

  • Every model call is recorded, with the model used and its cost. See Usage monitoring.

  • Superagents record their decisions and where each came from in their memory.

Organization-wide controls

Control
What it does

Which model providers and models anyone can use

Which features each member can use, including superagents and deployments

Lets admins restrict what blocks can do

Last updated

Was this helpful?