Policies

Write the rules that decide what an agent may do.

• Your first deny writes and activates a policy that denies one dangerous command and tells the agent why.
• Hold a call for a person holds one call until a named person approves it, with a bounded wait.
• Tickets gates a class of calls behind a ticket that an approver grants once and the agent consumes later.
• Classify sends a call to the inline classifier when a static rule cannot tell whether it is safe.
• Record a conversation turns recording on for one role, word for word or with secrets masked.
• Simulate a call tests a policy against a call before you activate it and shows which policies govern each role.