System and method for generating dynamic conversational AI experiences using large language models and decisioning systems

A non-transitory computer-readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining steps of:

• receiving a natural language question from a user;
• determining, using a large language model, whether the natural language question is a transactional question or an informational question;
• generating, using a first generative artificial intelligence (AI) model, a first response to the natural language question when the natural language question is an informational question;
• generating, using a transaction generative AI model that interfaces with a decisioning system based on contracts of the decisioning system, a second response to the natural language question when the natural language question is a transactional question, wherein the decisioning system contracts define business logic, rules, and decision-making processes for handling transactional requests;
• generating, using a sentiment-based response generator, a third response based on one of the first response or the second response and a sentiment of the natural language question;
• presenting the third response to the user;
• and
• training the transaction generative AI model using a reinforcement learning approach based on a source of knowledge containing chat logs, transcripts, and transaction records, the reinforcement learning approach including providing model prompts generated from the source of knowledge to a reinforcement learning agent, and updating a behavior of the reinforcement learning agent based on feedback from an evaluator that assesses actions of the reinforcement learning agent.

A device comprising:

• a processor;
• and
• a storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
• logic, executed by the processor, for receiving a natural language question from a user;
• logic, executed by the processor, for determining, using a large language model, whether the natural language question is a transactional question or an informational question;
• logic, executed by the processor, for generating, using a first generative artificial intelligence (AI) model, a first response to the natural language question when the natural language question is an informational question;
• logic, executed by the processor, for generating, using a transaction generative AI model that interfaces with a decisioning system based on contracts of the decisioning system, a second response to the natural language question when the natural language question is a transactional question, wherein the decisioning system contracts define business logic, rules, and decision-making processes for handling transactional requests;
• logic, executed by the processor, for generating, using a sentiment-based response generator, a third response based on one of the first response or the second response and a sentiment of the natural language question;
• logic, executed by the processor, for presenting the third response to the user;
• and
• logic, executed by the processor, for training the transaction generative AI model using a reinforcement learning approach based on a source of knowledge containing chat logs, transcripts, and transaction records, the reinforcement learning approach including providing model prompts generated from the source of knowledge to a reinforcement learning agent, and updating a behavior of the reinforcement learning agent based on feedback from an evaluator that assesses actions of the reinforcement learning agent.