Conversational Interface for Content Creation and Editing Using Large Language Models

A computing system, comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media storing instructions that are executable to cause the one or more processors to perform operations, the operations comprising:
• obtaining, via a conversational campaign assistant interface, by a custom trained machine-learned model, natural language input, wherein the natural language input comprises at least a website uniform resource locator (URL);
• accessing, via the custom machine-learned model, data associated with a website associated with the website URL;
• generating output comprising one or more suggested content item components based on the accessed data and natural language input;
• responsive to generating the output comprising the one or more suggested content item components, automatically populating one or more input fields with the one or more suggested content item components;
• and
• transmitting instructions that, when executed, cause a client device to provide the one or more suggested content item components for display via a user interface.

A computer-implemented method, performed by one or more processors, comprising:

• generating an initial user interface comprising a conversational campaign assistant interface;
• obtaining, via the conversational campaign assistant interface, by a custom trained machine-learned model, natural language input, wherein the natural language input comprises at least a website uniform resource locator (URL);
• accessing, via the custom machine-learned model, data associated with a website associated with the website URL;
• generating output comprising one or more suggested content item components based on the accessed data and natural language input;
• responsive to generating the output comprising the one or more suggested content item components, automatically populating one or more input fields with the one or more suggested content item components;
• and
• transmitting instructions that, when executed, cause a client device to provide the one or more suggested content item components for display via a user interface.

One or more non-transitory computer readable media storing instructions that are executable by one or more processors to perform operations comprising:

• generating an initial user interface comprising a conversational campaign assistant interface;
• obtaining, via the conversational campaign assistant interface, by a custom trained machine-learned model, natural language input, wherein the natural language input comprises at least a website uniform resource locator (URL);
• accessing, via the custom machine-learned model, data associated with a website associated with the website URL;
• generating output comprising one or more suggested content item components based on the accessed data and natural language input;
• responsive to generating the output comprising the one or more suggested content item components, automatically populating one or more input fields with the one or more suggested content item components;
• and
• transmitting instructions that, when executed, cause a client device to provide the one or more suggested content item components for display via a user interface.