Contextual resource completion

A computing system, comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media storing instructions that are executable by the one or more processors to cause the computing system to perform operations, the operations comprising:
• providing, to an endpoint device, an input interface configured for receiving natural language content;
• receiving, from the endpoint device, an initial input of natural language content associated with a document, wherein the initial input is based on user interactions with the input interface;
• receiving context data associated with the endpoint device;
• populating, based on the initial input and the context data, fields in a predetermined natural language instruction to generate a populated predetermined natural language instruction;
• generating, using a machine-learned content generation model to process the populated predetermined natural language instruction, a suggested portion of natural language content that completes a portion of the document;
• providing, to the endpoint device, the suggested portion;
• receiving, from the endpoint device, a response descriptive of a selection, via the input interface, for including the suggested portion in the document;
• and
• updating a state of the document based on the response.

One or more non-transitory computer-readable media storing instructions that are executable by one or more processors to cause a computing system to perform operations, the operations comprising:

• providing, to an endpoint device, an input interface configured for receiving natural language content;
• receiving, from the endpoint device, an initial input of natural language content associated with a document, wherein the initial input is based on user interactions with the input interface;
• receiving context data associated with the endpoint device;
• populating, based on the initial input and the context data, fields in a predetermined natural language instruction to generate a populated predetermined natural language instruction;
• generating, using a machine-learned content generation model to process the populated predetermined natural language instruction, a suggested portion of natural language content that completes a portion of the document;
• providing, to the endpoint device, the suggested portion;
• receiving, from the endpoint device, a response descriptive of a selection, via the input interface, for including the suggested portion in the document;
• and
• updating a state of the document based on the response.