Abstract: Disclosed herein are, among other things, systems and methods that use machine learning models, such as large language models, for analysis (e.g., predictive analysis) of calls between an agent and caller and/or feedback generation for calls between an agent and caller. Such calls may be made by callers who are interested or potentially interested in an offering, such as a program, product, or service. Feedback may be presented (e.g., immediately) after a call completes and/or during a call, for example in near real-time. Systems and methods described herein may use and/or identify features and/or one or more predetermined (e.g., preferred or optimal) criteria (e.g., threshold(s), value(s), range(s), pattern(s), or a combination thereof) for analysis and/or feedback generation.