Skip to main content
Policies are coming soon. Talk to us if you’d like early access.
Policies let you move beyond observing what agents do, to actively controlling them. Each policy defines conditions that detail what to watch for in a message, and an action to take when those conditions are met.

​
Conditions

Conditions are matching criteria for messages sent to and from an LLM, based on the tool being called, the integration it belongs to, the type of operation, and the agent invoking it.

​
Actions

When conditions match, Oso applies one of the following:
  • Alert — generate an alert and notify via Slack. For example, you can alert every time an agent makes a write call to GitHub rather than blocking it outright.
  • Block — prevent tool calls from executing, enforced centrally at the network level, regardless of what the agent or user has configured.
  • Require human approval — hold the agent’s request until a designated reviewer approves or denies it.

​
Get early access

Policies are in active development. Reach out to get involved in the early access program.