Iterative communication plan generation using large language models

A method, comprising:

• receiving, by a device and via a user interface, one or more natural language inputs that indicate one or more desired characteristics for a communication plan, wherein the communication plan is defined by a plurality of plan parameters;
• generating, by the device and using a large language model (LLM), one or more plan parameters of the plurality of plan parameters based on the one or more desired characteristics;
• generating, by the device and using a prediction model that is distinct from the LLM, a predicted outcome to result from execution of the communication plan based on the one or more plan parameters, wherein the predicted outcome indicates a predicted effect on one or more user engagement metrics;
• and
• providing, by the device and via the user interface, an indication of the predicted outcome in association with the one or more plan parameters.

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

• one or more instructions that, when executed by one or more processors of a device, cause the device to:
• obtain structured data representing a plurality of plan parameters of a communication plan, wherein the structured data was generated based on one or more natural language inputs received via a user interface and processed using a large language model (LLM);
• identify, based on the structured data, two or more communication channels via which to provide a plurality of communications associated with the communication plan to a plurality of individuals;
• and
• cause execution of the communication plan, including causing the plurality of communications to be provided to the plurality of individuals via the two or more communication channels in accordance with the plurality of plan parameters.