Declarative agent with voice agent latency mitigation

A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform steps comprising:

• receiving, by an agent, a voice input from a user during a real-time conversation between the agent and the user;
• identifying, by an agent, one or more triggers based on the voice input and the real-time conversation, the one or more triggers comprising a set of foreground processing triggers and a set of background processing triggers;
• performing a foreground processing action based on the set of foreground processing triggers to generate a first response;
• performing a background processing action based on the set of background processing triggers to generate a second response;
• presenting the first response to the user in response to the received voice input;
• and
• in response to receiving the second response while the first response is presented to the user, modifying the first response in real-time to integrate the second response before finishing the presenting of the first response.

A system comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform steps comprising:
• receiving, by an agent, a voice input from a user during a real-time conversation between the agent and the user;
• identifying, by an agent, one or more triggers based on the voice input and the real-time conversation, the one or more triggers comprising a set of foreground processing triggers and a set of background processing triggers;
• performing a foreground processing action based on the set of foreground processing triggers to generate a first response;
• performing a background processing action based on the set of background processing triggers to generate a second response;
• presenting the first response to the user in response to the received voice input;
• and
• in response to receiving the second response while the first response is presented to the user, modifying the first response in real-time to integrate the second response before finishing the presenting of the first response.