Action agent architecture in a scalable multi-service virtual assistant platform

A non-transitory, computer-readable medium storing program code for a multi-service virtual assistant platform which, when executed by a processor, cause the processor to perform computer-executable operations to implement:

• a natural language understanding (NLU) module to generate a parsed user input from one or more utterances received from a user;
• a plurality of information agents to obtain at least one information value from the parsed user input and/or contextual data;
• a plurality of action agents to perform two or more actions in response to the parsed user input, the contextual data, and/or the at least one information value, wherein the plurality of action agents are configured by specifying one or more triggering conditions, one or more action invocation parameters, one or more information agents as pre-requisites, and one or more responses;
• and
• a natural language generation (NLG) module to render a response back to the user after the two or more actions are performed.

A computer-implemented method for a multi-service virtual assistant platform which, when executed by a processor, causes the processor to perform steps comprising:

• generating a parsed user input from one or more utterances received from a user;
• obtaining at least one information value from the parsed user input and/or contextual data utilizing a plurality of information agents;
• performing two or more actions in response to the parsed user input, the contextual data, and/or the at least one information value utilizing a plurality of action agents, wherein the plurality of action agents are configured by specifying one or more triggering conditions, one or more action invocation parameters, one or more information agents as pre-requisites, and one or more responses;
• and
• rendering a response back to the user after the two or more actions are performed.