Generating synthetic messages for training an artificial intelligence model of a communications services platform

A system, comprising:

• a memory;
• and
• a processing device, coupled with the memory, configured to perform operations comprising:
• generating, by a communication services platform, one or more example messages simulating communications of a customer of the communication services platform with a user associated with the customer, wherein each example message of the example messages is associated with a first message category,
• generating a prompt that includes a command to generate a synthetic message based on the example messages,
• causing a first artificial intelligence (AI) model, in response to receiving the prompt, to generate a plurality of synthetic messages,
• generating a training dataset comprising the plurality of synthetic messages, wherein each item of the training dataset includes the first message category as a target output label, and
• training, using the training dataset, a second AI model to classify input messages into a plurality of message categories reflecting respective use cases associated with the input messages, wherein the plurality of message categories includes the first message category.

A computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

• generating, by a communication services platform, one or more example messages simulating communications of a customer of the communication services platform with a user associated with the customer, wherein each example message of the example messages is associated with a first message category;
• generating a prompt that includes a command to generate a synthetic message based on the example messages;
• causing a first artificial intelligence (AI) model, in response to receiving the prompt, to generate a plurality of synthetic messages;
• generating a training dataset comprising the plurality of synthetic messages, wherein each item of the training dataset includes the first message category as a target output label;
• and
• training, using the training dataset, a second AI model to classify input messages into a plurality of message categories reflecting respective use cases associated with the input messages, wherein the plurality of message categories includes the first message category.