Abstract: Dynamically evolving cognitive architecture system planning is described. A system forms an intent based on a user input, and creates a plan based on the intent. The plan includes a first action object that transforms a first concept object associated with the intent into a second concept object and also includes a second action object that transforms the second concept object into a third concept object associated with a goal of the intent. The first action object and the second action object are selected from multiple action objects. The system executes the plan, and outputs a value associated with the third concept object.

Abstract: A dynamically evolving cognitive architecture system based on third-party developers is described. A system forms an intent based on a user input, and creates a plan based on the intent. The plan includes a first action object that transforms a first concept object associated with the intent into a second concept object and also includes a second action object that transforms the second concept object into a third concept object associated with a goal of the intent. The first action object and the second action object are selected from multiple action objects. The system executes the plan, and outputs a value associated with the third concept object.

Abstract: A dynamically evolving cognitive architecture system based on contributions from third-party developers is described. A system receives a span of natural language annotated with an object from a first third-party developer. The system forms an intent based on a user input, which includes a natural language span which corresponds to an action object, a first concept object, and/or a second concept object. The action object, the first concept object, and/or the second concept object is provided by a second third-party developer. The annotating object is the action object, the first concept object, or the second concept object. Forming the intent enables executing the action object to transform the first concept object into the second concept object based on the annotated span of natural language, and also enables outputting a value associated with the second concept object associated with a goal of the intent.