# US 2025/0061404 A1 · Digital processing systems and methods for implementing and managing artificial intelligence functionalities in applications

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

- Number: US 2025/0061404 A1
- Document ID: US20250061404A1
- Status: Published application
- Kind: A1
- Application number: 18/400,816
- Filed: 2023-12-29
- Published: 2025-02-20
- Earliest claimed: 2023-08-14
- Assignees: Monday.Com Ltd.
- Applicants: Monday.Com Ltd.
- Inventors: Nadav GRINBERG; Etay LIBERMAN; Vlad MYSTETSKYI
- Web page: https://patentgrep.com/patent/US20250061404A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 8/30: Creation or generation of source code
- G06F 8/36: Software reuse
- G06F 9/44526: {Plug-ins; Add-ons}
- G06F 9/453: {Help systems}
- G06F 16/9035: Filtering based on additional data, e.g. user or group profiles
- G06N 20/00: Machine learning
- G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis}
- H04L 67/1001: for accessing one among a plurality of replicated servers
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods are disclosed for selection operations for a plurality of distinct Artificial Intelligence (AI) agents. The operations comprise accessing an application that employs AI functionality, sending, via the application, a common prompt to a plurality of distinct AI agents, receiving from each of the plurality of distinct AI agents a response to the common prompt, comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents based on the comparison.

## Claims

### Claim 1

A non-transitory computer-readable medium containing instructions that when executed by at least one processor cause the at least one processor to perform selection operations for a plurality of distinct Artificial Intelligence (AI) agents, the operations comprising:
accessing an application that employs AI functionality;
sending, via the application, a common prompt to a plurality of distinct AI agents, wherein the common prompt is associated with a query received via a user interface;
receiving from each of the plurality of distinct AI agents a response to the common prompt;
determining a level of applicability for each of the distinct AI agents for addressing the query by analyzing information associated with each of the received responses;
comparing the level of applicability for each of the distinct AI agents;
selecting at least one AI agent from the plurality of distinct AI agents based on the comparison of the level of applicability, wherein the at least one AI agent with a high level of applicability is selected from the plurality of distinct AI agents; and
providing, by the selected AI agent, the response associated with the selected AI agent to a user device.

### Claim 2 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein receiving from each of the plurality of distinct AI agents a response to the common prompt includes receiving from each of the plurality of distinct AI agents at least a portion of a response to the common prompt.

### Claim 3 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein information associated with each of the received responses includes content of the response and a response time.

### Claim 4 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the comparison of the level of applicability for each of the distinct AI agents is performed by a predetermined AI agent.

### Claim 5 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein comparing the level of applicability for each of the distinct AI agents includes determining a score for each of the received responses by analyzing information associated with each of the received responses and ranking the plurality of AI agents according to the determined scores.

### Claim 6 (depends on 5)

The non-transitory computer-readable medium of claim 5, wherein analyzing information associated with each of the received responses includes at least one of evaluating quality of content of each of the received responses, determining a response time for each of the received responses, or a combination thereof.

### Claim 7 (depends on 5)

The non-transitory computer-readable medium of claim 5, wherein selecting the at least one selected AI agent from the plurality of AI agents is based on the determined scores.

### Claim 8 (depends on 5)

The non-transitory computer-readable medium of claim 5, wherein following ranking of the plurality of AI agents according to the determined scores, the operations further include saving the determined scores in a database for influencing future comparisons.

### Claim 9 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein selecting at least one AI agent from the plurality of distinct AI agents includes selecting at least two AI agents from the plurality of distinct AI agents, and merging responses of the at least two selected AI agents to generate a merged response.

### Claim 10 (depends on 9)

The non-transitory computer-readable medium of claim 9, wherein merging responses of the at least two selected AI agents is performed by using a preestablished AI agent.

### Claim 11 (depends on 9)

The non-transitory computer-readable medium of claim 9, wherein merging responses of the at least two selected AI agents includes balancing responses of the at least two selected AI agents.

### Claim 12 (depends on 9)

The non-transitory computer-readable medium of claim 9, wherein the operations further include outputting the merged response.

### Claim 13 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the operations further include outputting the response of the at least one selected AI agent.

### Claim 14 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the operations further include:
receiving a feedback signal on the outputted response, wherein the feedback signal is either positive or negative;
if the feedback signal is negative, selecting at least one other AI agent from the plurality of distinct AI agents; and
outputting the response of the at least one other selected AI agent.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the feedback signal is received from a user via a user interface.

### Claim 16 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the operations further include analyzing a context associated with the common prompt.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, selecting at least one AI agent from the plurality of distinct AI agents based on the comparison, includes selecting at least one AI agent from the plurality of distinct AI agents based on the comparison and the analysis of the context associated with the common prompt.

### Claim 18 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the operation further includes storing in a database a record of the common prompt and the at least one selected AI agent.

### Claim 19

A method using at least one processor for selecting at least one AI agent from a plurality of distinct AI agents, the method comprising:
accessing, an application that employs AI functionality;
sending, via the application, a common prompt to a plurality of distinct AI agents, wherein the common prompt is associated with a query received via a user interface;
determining a level of applicability for each of the distinct AI agents for addressing the query by analyzing information associated with each of the received responses;
comparing the level of applicability for each of the distinct AI agents;
selecting at least one AI agent from the plurality of distinct AI agents based on the comparison of the level of applicability, wherein the at least one AI agent with a high level of applicability is selected from the plurality of distinct AI agents; and
providing, by the selected AI agent, the response associated with the selected AI agent to a user device.

### Claim 20

A system for selecting at least one AI agent from a plurality of distinct AI agents, the system comprising:
at least one processor configured to:
access an application that employs AI functionality;
send, via the application, a common prompt to a plurality of distinct AI agents, wherein the common prompt is associated with a query received via a user interface;
receive from each of the plurality of distinct AI agents a response to the common prompt;
determine a level of applicability for each of the distinct AI agents for addressing the query by analyzing information associated with each of the received responses;
compare the level of applicability for each of the distinct AI agents
compare information associated with each of the received responses; and
select at least one AI agent from the plurality of distinct AI agents based on the comparison of the level of applicability, wherein the at least one AI agent with a high level of applicability is selected from the plurality of distinct AI agents; and
provide, by the selected AI agent, the response associated with the selected AI agent to a user device.

### Claim 21 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the response is modified or processed by the at least one processor before providing the response to the user device.

### Claim 22 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein at least a portion of the response indicates applicability or non-applicability to the query.
