I think we should consider introducing the concept of AI agents as additional users in the workspace, potentially each under control of a human user.
In other words, admins/architects can define what access each (human) user is allowed, and then any user can create ‘delegate AI’ users.
By default, the AI users get the the same permissions as their human master, but the user also has the option of restricting them, e.g. making one of their AI delegates a read-only agent, making another limited to certain spaces/dbs, another limited to certain entities etc.
Hopefully, the AI providers (openai, anthropic etc.) will make it easy for users to interact with external tools (like Fibery) via multiple ‘personas’ instead of always granting the same permission level for every interaction