Hi Fibery team! I’d like to share a thought on how to make Fibery AI more “Management-friendly,” especially for larger organizations.
It would be great to have the ability to restrict Fibery AI access to specific Spaces.
For example, if a company has a Space with sensitive financial data and another one for general tasks, management would feel much more comfortable enabling AI for the entire account if they could simply ‘switch it off’ for the finance-related Space. This would give leadership peace of mind while still allowing the team to use AI for their daily work.
I wonder if there’s a way to segment AI usage for “global databases”. For example, a global documents database might be used for an organizational wiki, but it also might be used for some secure information. I don’t know if it would be possible to give AI access to the former but not for the latter.
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
