Using chatbots to collect direct user feedback on application experience

An apparatus, comprising:

• one or more network interfaces;
• a processor coupled to the one or more network interfaces and configured to execute one or more processes;
• and
• a memory configured to store a process that is executable by the processor, the process when executed configured to:
• associate one or more performance metrics with a particular session of an online application;
• make, using machine learning model trained to predict whether users have perceived degraded experiences with the online application based on collected performance metrics, a prediction that a user of the online application associated with the particular session has perceived a degraded experience with the online application based on the one or more performance metrics;
• make, a determination that a the user of the online application associated with the particular session should be queried for feedback regarding their application experience, based on the prediction;
• obtain, based on the determination, feedback from the user regarding their application experience, by causing a chatbot integrated into the online application to be presented to the user and query the user for feedback regarding their application experience in real-time;
• and
• associate the feedback from the user regarding their application experience with the one or more performance metrics.

A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:

• associating, by the device, one or more performance metrics with a particular session of an online application;
• making, by the device and using machine learning model trained to predict whether users have perceived degraded experiences with the online application based on collected performance metrics, a prediction that a user of the online application associated with the particular session has perceived a degraded experience with the online application based on the one or more performance metrics;
• making, by the device, a determination that the user of the online application associated with particular session should be queried for feedback regarding their application experience based on the prediction;
• obtaining, by the device and based on the determination, feedback from the user regarding their application experience, by causing a chatbot integrated into the online application to be presented to the user and query the user for feedback regarding their application experience in real-time;
• and
• associating, by the device, the feedback from the user regarding their application experience with the one or more performance metrics.