Abstract: In one embodiment, a method for providing assets from an asset origin to client devices includes receiving, by a computing system, a request to access a frontend asset from a first client device of the client devices. The method includes determining, by the computing system, an asset selection criteria. The method includes modifying, by the computing system through a dynamic function based on the asset selection criteria, a request for the asset origin to select a particular asset from multiple assets that are responsive to the request to access the frontend asset. The method includes causing, by the computing system, the asset origin to provide the particular asset to the first client device by providing the modified request to the asset origin.

Abstract: A system dynamically routes queries from an organization for processing. An incoming query is classified using a base model to determine a canonical group. The query is routed based on the canonical group. Responsive to the query, response data is then provided to the user device. Event data about the query, the routing, and the response data is used to train a first model that is used to determine subsequent routing. When a threshold is reached with respect to the available event data, a second model is trained using the event data. Processing of subsequent queries using the second model results in reduced demand for computer resources and reduces response times. The second model may be retrained on a schedule, or upon occurrence of a trigger event, such as an addition or removal of a canonical group.