At step 406, process 400 (e.g., using one or more components in system 200 (FIG. 2)) generates a dynamic conversational response based on the intent of the user. For example, by using the two-tier machine learning model, the system may ensure that at least a conversational response is generated based on an intent in the correct cluster. The system may also increase the likelihood that it determines a correct specific intent of the user. For example, as the initial determination of the intent cluster has been made, the second machine learning model can be trained to optimize the precision of the selection of the specific intent. That is, the output of the second machine learning model, and the response generated based on that output, will only be selected from responses from the intent cluster.

For example, the system may generate a dynamic conversational response (e.g., response 102 (FIG. 1)) and present the response in a user interface (e.g., user interface 100 (FIG. 1)). The response may appear with one or more likely responses (e.g., as shown in FIG. 1)). In some embodiments, the system may receive a user action selecting (or not selecting) a response (e.g., response 102 (FIG. 1)) from a user interface.