Product — Control

Let the agent work inside explicit operational boundaries.

Roles and permissions, agent policy, rules for reaching private systems, preview and approve, secrets and credentials, audit and cost.

Owner, admin, member, and viewer roles govern the single instance — the whole access-control model.

Control tool behavior and approval requirements at the agent layer.

Allow, deny, or require-approval rules for anything touching private infrastructure, tested before you rely on them.

See the proposed action and decide in the console or through a time-limited public action link.

Stored as references, decrypted only at call time — never embedded in a task or config.

A scrubbed audit history, retention controls, security settings, and daily model-spend ceilings.