Skip to main content
AI. Policy Guardrails will let you author boundaries the AI agents must respect. Policy Binding then attaches a policy to specific pipelines and roles. It is Upcoming.

​
What it is designed to do

  • Define the rules and boundaries your agents must follow.
  • Review what a policy allows and disallows before it applies.
  • Bind the policy to the pipelines and roles it should govern.

​
What you can use today

Built-in guardrails already apply to every workspace. No AI system sets a candidate to hired, rejected or withdrawn; below-bar candidates stay visible for a person; every AI interview starts with a notice the candidate acknowledges; and AI employees ask for your approval before they create or publish a job or contact a candidate. See Configure safety settings.