Systems and methods for intelligent call agent evaluations

A computer-implemented system for quantitative performance evaluation of a call agent, the computer-implemented system comprising a computing device having a memory for storing instructions, wherein the instructions, when executed, configure the computer-implemented system to provide:

• a transcript processing module configured to receive an audio recording of a call between the call agent and a customer and convert the audio recording to a text-based transcript;
• a preprocessing module configured to (i) identify at least one topic for categorizing the transcript by comparing the transcript to a list of historical call topics and (ii) retrieve from a database a set of criteria associated with the at least one topic, wherein each criterion correlates to a set of predefined questions for interrogating the transcript to evaluate the performance of the call agent with respect to the corresponding criterion, and wherein each question captures a sub-criterion under the corresponding criterion;
• a scoring module configured to:
• receive as inputs the predefined questions and the transcript and generate as outputs scores for respective ones of the predefined questions using a trained large language model (LLM), wherein each score measures a degree of satisfaction of the performance of the call agent during the call with respect to the sub-criterion captured by the corresponding predefined question;
• extract evidence from the transcript for each predefined question, wherein the evidence is a part of the transcript from which the LLM derived the score in response to the corresponding predefined question;
• compare the extracted evidence against the transcript to determine a degree of match;
• reject the score generated for the predefined question if the degree of match is below a predefined threshold;
• and
• a postprocessing module configured to:
• calculate a combined score for the call agent based on the scores for the predefined questions that are not rejected, the combined score representing an overall degree of satisfaction of the performance of the call agent with respect to the at least one topic identified for the call;
• and
• cause to display, via a graphical user interface, an identification of the call agent, a link to the audio recording of the call, the topic identified, and the combined score that quantitatively evaluates the performance of the call agent during the call.