# US 2026/0093727 A1 · Ai-driven multi-agent system for comprehensive network, security and enterprise it operations

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

- Number: US 2026/0093727 A1
- Document ID: US20260093727A1
- Status: Published application
- Kind: A1
- Application number: 19/005,488
- Filed: 2024-12-30
- Published: 2026-04-02
- Earliest claimed: 2024-09-30
- Assignees: Extreme Networks, Inc.
- Applicants: Extreme Networks, Inc.
- Inventors: Maria Carolina BESSEGA; Markus NISPEL; Rosalia Stephany BRASSESCO; Sima SOLTANI; Jaime Rafael CAMACARO; Brendan FEE
- Web page: https://patentgrep.com/patent/US20260093727A1

## CPC

- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- G06F 9/453: {Help systems}
- G06F 9/5027: {the resource being a machine, e.g. CPUs, Servers, Terminals}
- G06F 9/54: Interprogram communication
- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- G06F 16/33295: {in dialogue systems}
- G06F 16/334: Query execution (filtering based on additional data G06F16/335)
- G06F 40/30: Semantic analysis
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06N 3/12: using genetic models
- H04L 41/16: using machine learning or artificial intelligence
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for generating a response to a user question. An example embodiment operates by querying a large language model (LLM) using a prompt associated with the user question and one or more available tools in a tool service. The embodiment then retrieves an endpoint from the tool service in which the endpoint is a digital location associated with a tool selected by the LLM. The embodiment then requests a database associated with the user question based on the endpoint meeting an endpoint requirement. The embodiment then executes a query at the database, thereby obtains data including the response to the user question. The embodiment then identifies an output format associated with the response. The embodiment then generates the response to the user question based on formatting the data using the output format.

## Claims

### Claim 1

A computer-implemented method for generating a response to a user question, comprising:
querying, by a structured data agent using at least one processor, a large language model (LLM), using a first prompt, wherein the first prompt is associated with the user question and one or more available tools in a tool service;
retrieving, in response to querying by the structured data agent, an endpoint from the tool service, wherein the endpoint is a digital location associated with a tool selected by the LLM;
requesting, by the structured data agent using an application programming interface (API), a database associated with the user question based on the endpoint meeting an endpoint requirement;
generating, by a query agent using the LLM and a second prompt associated with the database and the user question, a query for retrieving data from the database;
executing, by the query agent, the query at the database, thereby obtaining the data from the database, wherein the data comprises the response to the user question;
identifying, in response to the executing by a user experience agent using the LLM and a third prompt associated with the data and the user question, an output format associated with the response to the user question; and
generating, by the user experience agent, the response to the user question based on formatting the data using the output format.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
generating, by the structured data agent based on the endpoint failing to meeting the endpoint, one or more additional questions for obtaining missing information associated with the endpoint requirement.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising:
selecting, using the LLM and a fourth prompt, a new tool from the one or more available tools for addressing the one or more additional questions, wherein the fourth prompt is associated with the one or more additional questions and the one or more available tools.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
transmitting, by the structured data agent to a user device, a request for providing missing information associated with the endpoint requirement.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
in response to a chart or a table conforming to the output format, generating, by a text agent using the LLM and a fourth prompt, a description of the chart or the table, wherein the fourth prompt is associated with the data, the user question, and the chart or the table; and
displaying, by the text agent, the description of the chart or the table on a user device.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
requesting the database by accessing the API using a pagination, a rate throttling, and a rate limiting.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the database comprises an in-memory database.

### Claim 8

A system for generating a response to a user question, comprising:
one or more memories;
at least one processor each coupled to at least one of the memories and configured to perform operations comprising:
querying, by a structured data agent, a large language model (LLM), using a first prompt, wherein the first prompt is associated with the user question and one or more available tools in a tool service;
retrieving, in response to querying by the structured data agent, an endpoint from the tool service, wherein the endpoint is a digital location associated with a tool selected by the LLM;
requesting, by the structured data agent using an application programming interface (API), a database associated with the user question based on the endpoint meeting an endpoint requirement;
generating, by a query agent using the LLM and a second prompt associated with the database and the user question, a query for retrieving data from the database;
executing, by the query agent, the query at the database, thereby obtaining the data from the database, wherein the data comprises the response to the user question;
identifying, in response to the executing by a user experience agent using the LLM and a third prompt associated with the data and the user question, an output format associated with the response to the user question; and
generating, by the user experience agent, the response to the user question based on formatting the data using the output format.

### Claim 9 (depends on 8)

The system of claim 8, wherein the operations further comprise:
generating, by the structured data agent based on the endpoint failing to meeting the endpoint, one or more additional questions for obtaining missing information associated with the endpoint requirement.

### Claim 10 (depends on 9)

The system of claim 9, wherein the operations further comprise:
selecting, using the LLM and a fourth prompt, a new tool from the one or more available tools for addressing the one or more additional questions, wherein the fourth prompt is associated with the one or more additional questions and the one or more available tools.

### Claim 11 (depends on 8)

The system of claim 8, wherein the operations further comprise:
transmitting, by the structured data agent to a user device, a request for providing missing information associated with the endpoint requirement.

### Claim 12 (depends on 8)

The system of claim 8, wherein the operations further comprise:
in response to a chart or a table conforming to the output format, generating, by a text agent using the LLM and a fourth prompt, a description of the chart or the table, wherein the fourth prompt is associated with the data, the user question, and the chart or the table; and
displaying, by the text agent, the description of the chart or the table on a user device.

### Claim 13 (depends on 8)

The system of claim 8, wherein the operations further comprise:
requesting the database by accessing the API using a pagination, a rate throttling, and a rate limiting.

### Claim 14 (depends on 8)

The system of claim 8, wherein the database comprises an in-memory database.

### Claim 15

A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
querying, by a structured data agent, a large language model (LLM), using a first prompt, wherein the first prompt is associated with a user question and one or more available tools in a tool service;
retrieving, in response to querying by the structured data agent, an endpoint from the tool service, wherein the endpoint is a digital location associated with a tool selected by the LLM;
requesting, by the structured data agent using an application programming interface (API), a database associated with the user question based on the endpoint meeting an endpoint requirement;
generating, by a query agent using the LLM and a second prompt associated with the database and the user question, a query for retrieving data from the database;
executing, by the query agent, the query at the database, thereby obtaining the data from the database, wherein the data comprises the response to the user question;
identifying, in response to the executing by a user experience agent using the LLM and a third prompt associated with the data and the user question, an output format associated with the response to the user question; and
generating, by the user experience agent, the response to the user question based on formatting the data using the output format.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the operations further comprise:
generating, by the structured data agent based on the endpoint failing to meeting the endpoint, one or more additional questions for obtaining missing information associated with the endpoint requirement.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the operations further comprise:
selecting, using the LLM and a fourth prompt, a new tool from the one or more available tools for addressing the one or more additional questions, wherein the fourth prompt is associated with the one or more additional questions and the one or more available tools.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the operations further comprise:
transmitting, by the structured data agent to a user device, a request for providing missing information associated with the endpoint requirement.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the operations further comprise:
in response to a chart or a table conforming to the output format, generating, by a text agent using the LLM and a fourth prompt, a description of the chart or the table, wherein the fourth prompt is associated with the data, the user question, and the chart or the table; and
displaying, by the text agent, the description of the chart or the table on a user device.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the operations further comprise:
requesting the database by accessing the API using a pagination, a rate throttling, and a rate limiting.
