Prerequisites to Getting Started

If you don't have the "Agents" option in the left navigation bar but are interested in trying out our AI Agents, then please contact your Customer Success Manager, Account Manager or [email protected] to request access.

Once your Organization has been given access to Agents, three user-level permission toggles become available in User Settings to manage who can do what with Agents. These toggles replace the previous all-or-nothing "Agents Access" toggle and give admins more granular control at the User level, before any Agent-level permission rules are applied:

  • Agents View/Chat — lets a user browse the agent library and chat with agents they have access to. No creation or editing controls are visible.
  • Agents Create/Edit — adds the ability to build new agents and edit or duplicate ones the user already has access to.
  • Agents Super Admin — extends Create/Edit with visibility into every agent (including private ones) and the ability to manage permissions across agents. Intended for team managers.

A user must have at least Agents View/Chat enabled to see Agents in the Main Menu and use them.

User-level permissions act as a hard cap: agent-level settings can never elevate a user above their assigned tier. This means admins can roll out the agent library broadly in View/Chat mode, give individual contributors the ability to build agents, and designate team managers as Super Admins — all without the previous all-or-nothing trade-off.

📘

Migration note

Any user who previously had the "Agents Access" toggle enabled automatically has Agents Create/Edit access after this release. Any user with a System Admin role (with access to ALL permissions) automatically has all three toggles enabled, including Agents Super Admin. Please review and adjust these permissions as needed for your users.

To use NinjaCat's AI Agents, you must have Datasets set up in NinjaCat's Data Cloud. If you're a first time user of NinjaCat's Data Cloud, follow these instructions to set up your first datasets: How to build a Native Provider Dataset in Data Cloud.