Agent governance
Developer control plane for policies, metering, and activity history.
Workspace: Local workspaceRole: AdminWelcome Preview
research-crew-policy

Edit policy

Change the live rules. Publishing creates a new version and leaves activation to you on the next screen — or activate from History when ready.

Tools shown below are collected from all registered agents in your workspace. A policy's scope (agent selector + environment) controls which agents it applies to — only set access for tools used by the agents this policy will govern.

01 · Pre-flight

Can this agent run? Checked before execution begins.

Tools

2 allow · 1 review · 4 deny

Everything not marked Allow or Review is denied by default. Review tools pause for a human before they run.

Tool
Allow
Review
Deny
Remove
arxiv_search
delete_research_data
draft_outreach_email
read_customer_profile
score_icp_fit
send_outreach_email
web_search

Models

Which LLMs this policy permits
1 of 7 models allowed▼
Select which models this policy permits. Leaving all unchecked denies every model request.
02 · In-flight

Is this action safe and worth it? Checked on every tool call.

Guardrails

Prompt and payload checks on every governed call
03 · Post-flight

Can we explain and improve it? Tracks behavior and feeds back into pre-flight.

Privilege de-escalation

Auto-tighten access when an agent misbehaves
After this many token-overage strikes, all tools require human review until an operator resets the agent.
Cancel