Agent identification process

This article collects detailed information on how predictive routing works in specific scenarios. For more information about the data required to optimize predictive routing, see Data requirements for predictive routing

Predictive routing scores the agents who might handle an interaction using a machine learning model. Machine learning is effective at identifying patterns. In this case, patterns identify the agents who deal most effectively with certain types of interactions.

When predictive routing is activated on a queue, it creates a model using various data sources, including agent profile data, aggregated customer data (such as whether they are a repeat caller), and historic interaction data.  When an interaction is offered to the queue, it’s assigned in the following way:

  1. When an interaction arrives in that queue, predictive routing creates a list of all agents on the queue. It retrieves data about the customer and each available agent. Predictive routing does not consider the routing status at this point.
  2. Filters the list for required agent language skills and non-language ACD skills (if Skill matching is enabled). 
  3. It uses the model to process agent and customer data in real time and returns a ranking for each available agent. This ranking represents the agents predictive routing expects to have the most positive impact on the target KPI when handling that specific interaction. The highest scored agent ranks first.
    Note:  If the number of available agents on a queue is three or less, Genesys Cloud does not score the agents. It routes the interactions using the standard routing method.
  4. During the timeout period (configured in the Queue details page), agent identification happens based on the number of interactions waiting on the queue:
    1. When the number of interactions is lesser than the number of available agents – Predictive routing starts attempting to route to the highest ranked agents. If the highest ranked agents are not available, the system will gradually expand the target agent pool, adding lower ranked agents.  This process continues until an agent is found, or until the timeout expires. 
    2. When the number of interactions is higher than the number of available agents – When an agent becomes available, the system assigns the longest waiting interaction for which the agent currently qualifies.
    3. If Genesys Cloud finds no qualifying agent during the timeout period, it routes the interaction using standard routing, which is the fallback routing method.

      Related links:

      How the AI model scores agents for predictive routing