Driver monitoring with real time feedback

An apparatus comprising an interface and a processor. The interface may be configured to receive pixel data of a driver of a vehicle and an environment near the vehicle. The processor may be configured to process the pixel data arranged as video frames, generate a text description of the video frames, store the text description and a timestamp as metadata with the video frames, store triggers, compare the triggers to the text description, and generate a driver score in response to the comparison. A first AI model may perform video to text analysis to generate the text description. A second AI model may be configured to perform the comparison and generate the driver score in response to the triggers. The plurality of triggers may comprise a plain text description of driver behavior and an operation of the vehicle in the environment.