Utilizing a large language model to generate an automated communication flow

1 . A system, comprising:

a processor configured to:

analyze a natural language description of a desired function to be achieved;

automatically generate a prompt for a large language model based on the natural language description, including by inserting at least a portion of a selected prompt template in the automatically generated prompt, wherein the selected prompt template is selected specifically for a communication channel based on an analysis of the natural language description of the desired function to be achieved;

provide the automatically generated prompt to the large language model; and

based on an output of the large language model, automatically generate an automated communication flow to be implemented for the communication channel; and

a memory coupled to the processor and configured to provide the processor with instructions.

2 . The system of claim 1 , wherein the communication channel is selected via a user interface.

3 . The system of claim 2 , wherein the selected communication channel is selected among a plurality of different communication channel options via a drop down menu associated with the user interface.

4 . The system of claim 1 , wherein the natural language description of the desired function to be achieved indicates a type of automated communication flow to be generated.

5 . The system of claim 4 , wherein the type of automated communication flow to be generated is an email collection flow, a link to site flow, an appointment booking flow, a quiz flow, or a specific message flow.

6 . The system of claim 1 , wherein the analysis of the natural language description of the desired function to be achieved includes performing natural language processing on the natural language description to determine a type of automated communication flow to be generated.

7 . The system of claim 6 , wherein the selected prompt template specifically for the communication channel corresponds to the determined automated communication flow type.

8 . The system of claim 1 , wherein the automated communication flow includes one or more content nodes.

9 . The system of claim 8 , wherein the selected prompt template indicates the one or more content nodes to be included in the automated communication flow.

10 . The system of claim 9 , wherein the selected prompt template includes at least one placeholder message for one of the one or more content nodes.

11 . The system of claim 9 , wherein for a first content node of the one or more content nodes, the selected prompt template includes at least one identifier of a second content node as a target identifier associated with the first content node.

12 . The system of claim 9 , wherein the selected prompt template indicates at least one reply message for one of the one or more content nodes.

13 . The system of claim 12 , wherein the selected prompt template indicates a placeholder title for the at least one reply message.

14 . The system of claim 1 , wherein the automatically generated prompt for the large language model includes one or more examples of an automated communication flow format that match a type of the automated communication flow.

15 . The system of claim 1 , wherein the automatically generated prompt for the large language model includes at least one trigger for the automated communication flow.

16 . The system of claim 1 , where the processor is further configured to receive the output of the large language model.

17 . The system of claim 1 , wherein the output of the large language model is a structure description of the automated communication flow.

18 . The system of claim 17 , wherein automatically generating the automated communication flow to be implemented for the communication channel includes validating the structure description of the automated communication flow.

19 . A method, comprising:

analyzing a natural language description of a desired function to be achieved;

automatically generating a prompt for a large language model based on the natural language description, including by inserting at least a portion of a selected prompt template in the automatically generated prompt, wherein the selected prompt template is selected specifically for a communication channel based on an analysis of the natural language description of the desired function to be achieved;

providing the automatically generated prompt to the large language model; and

based on an output of the large language model, automatically generating an automated communication flow to be implemented for the communication channel.

20 . A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:

analyzing a natural language description of a desired function to be achieved;

automatically generating a prompt for a large language model based on the natural language description, including by inserting at least a portion of a selected prompt template in the automatically generated prompt, wherein the selected prompt template is selected specifically for a communication channel based on an analysis of the natural language description of the desired function to be achieved;

providing the automatically generated prompt to the large language model; and

based on an output of the large language model, automatically generating an automated communication flow to be implemented for the communication channel.