IP Library Granted Patent US 12,579,288
Granted Patent B1
US 12,579,288 · App. 19/287,102 · Granted Mar 17, 2026

System and method for utilizing an AI browser agent in identity discovery and management

Inventors: Amir Ben Ami (Nehalim, IL); Dror Hadas (Tel Aviv, IL); Matan Haimovitch (Tel Aviv, IL); Niv Goldenberg (Brooklyn, NY)
Assignee: Linx Ltd.
G06F21/62
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,579,288
App. No.
19/287,102
Granted
Mar 17, 2026
Kind
B1
Abstract

A system and method for utilizing an artificial intelligence (AI) browser agent to extract identity information for applying a cybersecurity control is presented. The method includes receiving access credentials to a software service, the software service including a plurality of associated identities; detecting in the software service each identity of the plurality of identities, and at least a metadata associated with each identity; generating for each detected identity a representation, the representation generated based on the associated at least a metadata; applying a control on the representation; and initiating an action in the software service, based on a result of applying the control on the representation.

Claims (59)

1 . A method for utilizing an artificial intelligence (AI) browser agent to extract identity information for applying a cybersecurity control, comprising:

receiving access credentials to a software service, the software service including a plurality of associated identities;

detecting in the software service each identity of the plurality of identities, and at least a metadata associated with each identity;

generating for each detected identity a representation, the representation generated based on the associated at least a metadata;

applying a control on the representation; and

initiating an action in the software service, based on a result of applying the control on the representation.

2 . The method of claim 1 , further comprising:

initiating the action in a computing environment configured to access the software service.

3 . The method of claim 1 , further comprising:

generating the representation further based on an associated permission.

4 . The method of claim 1 , further comprising:

configuring an AI agent client to detect in the software service each identity utilizing the access credentials.

5 . The method of claim 4 , further comprising:

configuring the AI agent to further interact with the software service, wherein interacting with the software service includes simulating a user interaction with the software service.

6 . The method of claim 4 , further comprising:

configuring a plurality of AI agent clients to each interact with the software service; and

generating the representation further based on a result of each interaction of the plurality of AI agent clients with the software service.

7 . The method of claim 1 , further comprising:

detecting in the metadata a permission; and

generating the representation for each identity further based on the detected permission.

8 . The method of claim 1 , further comprising:

initiating the action in a computing environment having access to the software service.

9 . The method of claim 1 , further comprising:

continuously applying controls on the representation; and

continuously updating the generated representation based on a result of applying the controls.

10 . A non-transitory computer-readable medium storing a set of instructions for utilizing an artificial intelligence (AI) browser agent to extract identity information for applying a cybersecurity control, the set of instructions comprising:

one or more instructions that, when executed by one or more processing circuitries of a device, cause the device to:

receive access credentials to a software service, the software service including a plurality of associated identities;

detect in the software service each identity of the plurality of identities, and at least a metadata associated with each identity;

generate for each detected identity a representation, the representation generated based on the associated at least a metadata;

apply a control on the representation; and

initiate an action in the software service, based on a result of applying the control on the representation.

11 . A system for utilizing an artificial intelligence (AI) browser agent to extract identity information for applying a cybersecurity control comprising:

a processing circuitry;

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

receive access credentials to a software service, the software service including a plurality of associated identities;

detect in the software service each identity of the plurality of identities, and at least a metadata associated with each identity;

generate for each detected identity a representation, the representation generated based on the associated at least a metadata;

apply a control on the representation; and

initiate an action in the software service, based on a result of applying the control on the representation.

12 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

initiate the action in a computing environment configured to access the software service.

13 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

generate the representation further based on an associated permission.

14 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

configure an AI agent client to detect in the software service each identity utilizing the access credentials.

15 . The system of claim 14 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

configure the AI agent to further interact with the software service, wherein interacting with the software service includes simulating a user interaction with the software service.

16 . The system of claim 14 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

configure a plurality of AI agent clients to each interact with the software service; and

generate the representation further based on a result of each interaction of the plurality of AI agent clients with the software service.

17 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

detect in the metadata a permission; and

generate the representation for each identity further based on the detected permission.

18 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

initiate the action in a computing environment having access to the software service.

19 . The system of claim 11 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:

continuously apply controls on the representation; and

continuously update the generated representation based on a result of applying the controls.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 25, 2025
From: BEN AMI, AMIR; HADAS, DROR; HAIMOVITCH, MATAN; GOLDENBERG, NIV
To: LINX LTD.
Reel/Frame 073033/0854 →
References Cited (14)
US 7146512B2 · Rothman · 2006 [cited by examiner]
US 7634800B2 · Ide · 2009 [cited by examiner]
US 8255594B2 · De · 2012 [cited by examiner]
US 8719838B1 · Oakes, III · 2014 [cited by examiner]
US 10063594B2 · Winn · 2018 [cited by examiner]
US 20090265708A1 · Nakajima · 2009 [cited by examiner]
US 20100077461A1 · Nguyen · 2010 [cited by examiner]
US 20120131138A1 · Swenson · 2012 [cited by examiner]
US 20140047532A1 · Sowatskey · 2014 [cited by examiner]
US 20160134620A1 · Morrison · 2016 [cited by examiner]
US 20170118214A1 · Vainstein · 2017 [cited by examiner]
US 20200374278A1 · Sundaram · 2020 [cited by examiner]
US 20220343010A1 · Ghafoor · 2022 [cited by examiner]
US 20250252184A1 · Ben-Noon · 2025 [cited by examiner]