This is an overview of domain separation and the Agent Intelligence application. Domain
separation enables you to separate data, processes, and administrative tasks into logical
groupings called domains. You can then control several aspects of this separation, including
which users can see and access data.
Support: Level 2
Agent Intelligence enables the creation
of supervised machine learning solutions using historic datasets. A machine learning solution
definition can be configured in Agent Intelligence per domain, which ensures
that the data used by the solution is domain-specific data. After a solution is trained for a
domain, the solution calls for a prediction to be made for resolution, depending on what that
domain belongs to. For example, the solution might be an incident or case.
How domain separation works in Agent Intelligence
An instance owner can train a machine learning (ML) solution for each domain by creating a
solution definition for each domain and training those solutions. In this way each solution uses
data specific to the corresponding domain.
- Data can be domain separated
- Domain column is present for base system application tables
- Domain-specific configuration is managed by instance owner
- Tenant domains can manage their own application data
- Application properties are domain-aware when needed