Chat interface with chatbot agent supported by language models for placing group orders

A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform steps comprising:

• receiving, via a chat interface of a computer system, input data with information about a conversation between a plurality of users of the computer system about a group order for the plurality of users;
• applying, by a chatbot agent module of the computer system, a chatbot prediction model to the input data to generate a score that is indicative of a confidence that the information provided by the conversation passes a threshold for generating a list of ingredients for the group order, wherein the chatbot prediction model is a machine-learning model trained to continually predict whether the conversation has given enough information for generating the list of ingredients;
• responsive to the score being greater than a threshold score, invoking, by the chatbot agent module, a participation of a chatbot agent in the conversation at the chat interface;
• responsive to the score being greater than a threshold score, generating a first prompt for input into an ingredient generation large language model (LLM), the first prompt including the received input data and a request for generating the list of ingredients for the group order;
• requesting the ingredient generation LLM to generate, based on the first prompt input into the ingredient generation LLM, the list of ingredients and metadata associated with the plurality of users;
• generating a second prompt for input into an item generation LLM, the second prompt including the list of ingredients, the metadata and a request for generating a list of items for the group order;
• requesting the item generation LLM to generate, based on the second prompt input into the item generation LLM, the list of items;
• causing, by the chatbot agent, the chat interface to display content prompting approval by the plurality of users for conversion of the list of items;
• and
• responsive to the approval, placing the group order comprising the list of items at the computer system for delivery to a user of the plurality of users.

A computer system comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium having instructions that, when executed by the processor, cause the computer system to perform steps comprising:
• receiving, via a chat interface of the computer system, input data with information about a conversation between a plurality of users of the computer system about a group order for the plurality of users;
• applying, by a chatbot agent module of the computer system, a chatbot prediction model to the input data to generate a score that is indicative of a confidence that the information provided by the conversation passes a threshold for generating a list of ingredients for the group order, wherein the chatbot prediction model is a machine-learning model trained to continually predict whether the conversation has given enough information for generating the list of ingredients;
• responsive to the score being greater than a threshold score, invoking, by the chatbot agent module, a participation of a chatbot agent in the conversation at the chat interface;
• responsive to the score being greater than a threshold score, generating a first prompt for input into an ingredient generation large language model (LLM), the first prompt including the received input data and a request for generating the list of ingredients for the group order;
• requesting the ingredient generation LLM to generate, based on the first prompt input into the ingredient generation LLM, the list of ingredients and metadata associated with the plurality of users;
• generating a second prompt for input into an item generation LLM, the second prompt including the list of ingredients, the metadata and a request for generating a list of items for the group order;
• requesting the item generation LLM to generate, based on the second prompt input into the item generation LLM, the list of items;
• causing, by the chatbot agent, the chat interface to display content prompting approval by the plurality of users for conversion of the list of items;
• and
• responsive to the approval, placing the group order comprising the list of items at the computer system for delivery to a user of the plurality of users.