CPM Flow

This flow explains the steps that occur when a row is inserted in ChatAIPredictionInfo, which invokes the Custom Process Model (CPM) to evaluate the prediction results saved for each chat message.

1. Fetch all the messages present in the chat for which CPM is invoked
2. Skip ‘n’ number of configured chat messages from the evaluation
3. Check if the threshold number of negative messages are present in the chat
4. Once threshold is met, check for the following conditions:
   • Time between first and last negative customer response (configurable), then flag
   • Agent responded between first and last negative response then flag
   • Word length of the end user messages between first and last negative customer response (configurable) then flag
   • Time between the last negative response and last response

The following flowchart represents the CPM flow: