# US 2026/0087303 A1 · Method and system for automating chat-based interactions

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087303 A1
- Document ID: US20260087303A1
- Status: Published application
- Kind: A1
- Application number: 18/892,601
- Filed: 2024-09-23
- Published: 2026-03-26
- Earliest claimed: 2024-09-23
- Assignees: Honeywell International Inc.
- Applicants: Honeywell International Inc.
- Inventors: Vijay Kumar Ravi; Pavan Ravindra Chhatpar; Jan Zirnstein; Sumanth Chitikireddy; Alpesh Desai; Brian Lau
- Web page: https://patentgrep.com/patent/US20260087303A1

## CPC

- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/0475: Generative networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system and method for automating chat-based interactions utilizing a large language model (LLM) is disclosed. The method involves receiving one or more requests from a user through an apparatus designed to automate various tasks, including data collection from multiple sources. Upon receiving the user's request, a query message is sent to the LLM, which determines whether to collect additional data from one or more Application Programming Interfaces (APIs) or to generate a final response based on the existing message history. If additional data is needed, it is collected from the APIs and incorporated into the LLM's message history. Subsequently, the LLM generates a final response based on either the updated message history or the newly collected data. This final response is then communicated back to the user, ensuring accurate and contextually relevant interactions.

## Claims

### Claim 1

A method for automating chat-based interactions using a large language model (LLM), comprising:
receiving, by an apparatus, one or more requests from a user, wherein the apparatus is configured to automate one or more tasks including collecting data from one or more sources;
sending a query message to the LLM based on the user's request, wherein the LLM provides information on either collecting data from one or more Application Programming Interfaces (APIs) or returning a final response to the query message based on available history of messages with the LLM;
collecting data from the one or more APIs or sending a final response to the query message based on LLM's information;
based on collecting, updating the collected data from the APIs to the available message history with the LLM;
receiving a final response from the LLM based on at least one of the available message history with the LLM and the collected data from the one or more APIs; and
sending the final response to the user.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the one or more sources include at least one of:
Search API;
Structured Query Language (SQL) API; and
Graph API.

### Claim 3 (depends on 1)

The method as claimed in claim 1, further comprising using an API interaction toolkit including functions comprising one or more of list_api_servers, requests_get, and requests_post for collecting data from the one or more sources.

### Claim 4 (depends on 1)

The method as claimed in claim 1, further comprising storing history in a vector format for semantically relevant retrieval in a conversation vector database.

### Claim 5 (depends on 1)

The method as claimed in claim 1, further comprising accessing the LLM via endpoints including one or more of open weight LLM Endpoint and proprietary LLM Endpoint.

### Claim 6 (depends on 1)

The method as claimed in claim 1, further comprising deploying an automated agentic Generative Artificial Intelligence (GenAI) template.

### Claim 7 (depends on 6)

The method as claimed in claim 6, wherein deploying the agentic GenAI template comprises:
automatically setting up the necessary infrastructure for the chat-based interactions;
utilizing one or more curated tools tailored to the chat-based interactions; and
employing pre-built Extract Transform Load (ETL) pipelines for data processing.

### Claim 8 (depends on 1)

The method as claimed in claim 1, further comprising vectorizing and mapping the stored data.

### Claim 9 (depends on 8)

The method as claimed in claim 8, wherein vectorizing and mapping the stored data comprises at least one of:
converting unstructured data into a usable format;
preparing structured data using SQL; and
creating time series data from telemetry.

### Claim 10 (depends on 1)

The method as claimed in claim 1, wherein the LLM provides the information on collecting the data from the one or more APIs when the LLM lacks sufficient data corresponding to the query message.

### Claim 11

An apparatus for automating chat-based interactions using a large language model (LLM), wherein the apparatus automates one or more tasks including collecting data from one or more sources, and the apparatus is configured to:
receive one or more requests from a user;
send a query message to the LLM based on the user's request, wherein the LLM provides information on either collecting data from one or more Application Programming Interfaces (APIs) or returning a final response to the query message based on available history of messages with the LLM;
collect data from the one or more APIs or send a final response to the query message based on LLM's information;
based on collection, update the collected data from the APIs to the available message history with the LLM;
receive a final response from the LLM based on at least one of the available message history with the LLM and the collected data from the one or more APIs; and
send the final response to the user.

### Claim 12 (depends on 11)

The apparatus as claimed in claim 11, wherein the one or more sources include at least one of:
search API;
Structured Query Language (SQL) API; and
graph API.

### Claim 13 (depends on 11)

The apparatus as claimed in claim 11, wherein the apparatus further configured to use an API interaction toolkit including functions comprising one or more of list_api_servers, requests_get, and requests_post for collecting data from the one or more sources.

### Claim 14 (depends on 11)

The apparatus as claimed in claim 11, wherein the apparatus further configured to store history in a vector format for semantically relevant retrieval in a conversation vector database.

### Claim 15 (depends on 11)

The apparatus as claimed in claim 11, wherein the apparatus further configured to access the LLM via endpoints including one or more of open weight LLM Endpoint and proprietary LLM Endpoint.

### Claim 16 (depends on 11)

The apparatus as claimed in claim 11, wherein the apparatus further configured to deploy an automated agentic Generative Artificial Intelligence (GenAI) template.

### Claim 17 (depends on 16)

The apparatus as claimed in claim 16, wherein the apparatus is configured to deploy the agentic GenAI template by:
automatically setting up the necessary infrastructure for the chat-based interactions;
utilizing one or more curated tools tailored to the chat-based interactions; and
employing pre-built Extract Transform Load (ETL) pipelines for the data processing.

### Claim 18 (depends on 11)

The apparatus as claimed in claim 11, wherein the apparatus further configured to vector and map the stored data by:
converting unstructured data into a usable format;
preparing structured data using SQL; and
creating time series data from telemetry.

### Claim 19 (depends on 11)

The apparatus as claimed in claim 11, wherein the LLM provides the information on collecting the data from the one or more APIs when the LLM lacks sufficient data corresponding to the query message.

### Claim 20

A non-transitory computer-readable medium having stored thereon computer-readable instructions that, when executed by a processor, cause the processor to execute a method for automating chat-based interactions using a large language model (LLM), comprising:
receiving, by an apparatus, one or more requests from a user, wherein the apparatus is configured to automate one or more tasks including collecting data from one or more sources;
sending a query message to the LLM based on the user's request, wherein the LLM provides information on either collecting data from one or more Application Programming Interfaces (APIs) or returning a final response to the query message based on available history of messages with the LLM;
collecting data from the one or more APIs or sending a final response to the query message based on LLM's information;
based on collecting, updating the collected data from the APIs to the available message history with the LLM;
receiving a final response from the LLM based on at least one of the available message history with the LLM and the collected data from the one or more APIs; and
sending the final response to the user.
