The present invention is an action agent architecture in a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. A plurality of information agents obtain at least one information value from a parsed user input and/or contextual data. A plurality of action agents perform one or more actions in response to the parsed user input, the contextual data, and/or an information value obtained from at least one of the information agents. The plurality of action agents are created through a declarative language 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. A natural language generation (NLG) module renders a response back to the user after the one or more actions are performed.