# US 12,602,504 B2 · Integrated agent-driven data framework > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,504 B2 - Document ID: US12602504B2 - Status: Granted - Kind: B2 - Application number: 19/340,698 - Filed: 2025-09-25 - Published: 2026-01-22 - Granted: 2026-04-14 - Earliest claimed: 2023-01-19 - Assignees: Citibank, N.A. - Applicants: Citibank, N.A. - Inventors: William Franklin Cameron; Prithvi Narayana Rao - Web page: https://patentgrep.com/patent/US12602504B2 ## CPC - G06F 21/552: {involving long-term monitoring or reporting} - G06F 21/6218: {to a system of files or objects, e.g. local or distributed file system or database} - G06F 16/2358: {Change logging, detection, and notification (replication G06F16/27)} - G06F 21/577: {Assessing vulnerabilities and evaluating computer system security} - G06F 2221/034: Test or assess a computer or a system - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The present disclosure relates to systems, methods, and devices for providing a centralized data store that receives and transmits data via agents that operate independently of one another. In some implementations, the agents transform data prior to transmission to the centralized data store. In some implementations, the centralized data store is configured to transform data. The centralized data store can evaluate, route, score, and otherwise manipulate and select received data. The centralized data store can respond to data requests based at least in part on its evaluation of received data. ## Claims ### Claim 1 A computer-implemented method for centralized data management, the method comprising: receiving, from a first agent, a data request for data stored by a central hub, wherein the first agent is configured to receive one or more inputs and to perform one or more actions autonomously or semi-autonomously in response to the one or more inputs; determining that the first agent is authorized to issue the data request; identifying a dataset in a data store of the central hub that is responsive to the data request; determining if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: transmitting the dataset to the first agent; when the dataset is a restricted dataset: identifying a second dataset in the data store that is responsive to the data request and is different from the restricted dataset; and transmitting the second dataset to the first agent, wherein the second dataset is not a restricted dataset, wherein the first agent has permission to access the second dataset, wherein the transmitted dataset is transmitted to the data store from a second agent different from the first agent, wherein the first agent does not communicate with the second agent, wherein transmitting the transmitted dataset comprises transmitting an identifier of the second agent, and wherein transmitted the transmitted dataset comprises transmitting an expiration date of the transmitted dataset. ### Claim 2 A computer-implemented method for centralized data management, the method comprising: receiving, from a first agent, a data request, wherein the first agent is configured to access one or more inputs and to perform one or more actions in response to the one or more inputs; determining that the first agent is authorized to issue the data request; identifying a dataset in a data store that is responsive to the data request; determining if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: determining that a second agent is providing information for updating the dataset, wherein the second agent is different from the first agent; updating the dataset; and transmitting the dataset to the first agent upon completion of the update, wherein the first agent does not communicate with the second agent. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, further comprising: transmitting at least one of an identifier of the second agent, an expiration date of the dataset, or a confidence level associated with the dataset to the first agent. ### Claim 4 (depends on 2) The computer-implemented method of claim 2, further comprising, when the dataset is a restricted dataset: identifying a second dataset responsive to the data request; and transmitting the second dataset to the first agent, wherein the second dataset is not a restricted dataset, wherein the second dataset is different from the first dataset, and wherein the first agent has access permissions for the second dataset. ### Claim 5 (depends on 2) The computer-implemented method of claim 2, wherein the request comprises a subscription request. ### Claim 6 (depends on 2) The computer-implemented method of claim 2, further comprising: determining an addition of new data responsive to the data request; and transmitting the new data to the first agent. ### Claim 7 (depends on 2) The computer-implemented method of claim 2, wherein the updating is done as one or more atomic transactions. ### Claim 8 (depends on 2) The computer-implemented method of claim 2, further comprising: determining, using the provided information, an updated confidence level for the second agent, wherein the updated confidence level is based on one or more of: a size of the provided information, a frequency of updates by the second agent, or a security measure taken by the second agent. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, wherein the security measure includes an attestation signed by a hardware module of a system on which the second agent is operating. ### Claim 10 (depends on 2) The computer-implemented method of claim 2, further comprising: applying a transformation to the provided information. ### Claim 11 (depends on 2) The computer-implemented method of claim 2, further comprising: receiving, from a third agent, data that conflicts with the dataset from the second agent; and resolving the conflict by preferring the dataset from the second agent based on a preference configuration, wherein the third agent acts as a fallback agent when the second agent has not submitted data within a threshold period of time. ### Claim 12 A system for centralized data management, the system comprising: at least one hardware processor; and at least one non-transitory, computer-readable storage medium having instructions thereon that, when executed by the at least one hardware processor, cause the system to: receive, from a first agent, a data request, wherein the first agent is configured to access one or more inputs and to perform one or more actions in response to the one or more inputs; determine that the first agent is authorized to issue the data request; identify a dataset in a data store that is responsive to the data request; determine if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: determine that a second agent is providing information for updating the dataset, wherein the second agent is different from the first agent; update the dataset; and transmit the dataset to the first agent upon completion of the update, wherein the first agent does not communicate with the second agent. ### Claim 13 (depends on 12) The system of claim 12, wherein the instructions are further configured to cause the system to: transmit at least one of an identifier of the second agent, an expiration date of the dataset, or a confidence level associated with the dataset to the first agent. ### Claim 14 (depends on 12) The system of claim 12, wherein the instructions are further configured to cause the system to, when the dataset is a restricted dataset: identify a second dataset responsive to the data request; and transmit the second dataset to the first agent, wherein the second dataset is not a restricted dataset, wherein the second dataset is different from the first dataset, and wherein the first agent has access permissions for the second dataset. ### Claim 15 (depends on 12) The system of claim 12, wherein the request comprises a subscription request. ### Claim 16 (depends on 12) The system of claim 12, wherein the instructions are further configured to cause the system to: determine an addition of new data responsive to the data request; and transmit the new data to the first agent. ### Claim 17 (depends on 12) The system of claim 12, wherein the updating is done as one or more atomic transactions. ### Claim 18 (depends on 12) The system of claim 12, wherein the instructions are further configured to cause the system to: determine, using the provided information, an updated confidence level for the second agent, wherein the updated confidence level is based on one or more of: a size of the provided information, a frequency of updates by the second agent, or a security measure taken by the second agent. ### Claim 19 (depends on 18) The system of claim 18, wherein the security measure includes an attestation signed by a hardware module of a system on which the second agent is operating. ### Claim 20 (depends on 12) The system of claim 12, wherein the instructions are further configured to cause the system to: receive, from a third agent, data that conflicts with the dataset from the second agent; and resolve the conflict by preferring the dataset from the second agent based on a preference configuration, wherein the third agent acts as a fallback agent when the second agent has not submitted data within a threshold period of time. ### Claim 21 A computer-implemented method for centralized data management, the method comprising: receiving, from a first agent, a data request, wherein the first agent is configured to access one or more inputs and to perform one or more actions in response to the one or more inputs; determining that the first agent is authorized to issue the data request; identifying a dataset in a data store that is responsive to the data request; determining if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: determining that the second agent is providing information for updating the dataset; updating the dataset, wherein the updating is done as one or more atomic transactions; and transmitting the dataset to the first agent, wherein the dataset is transmitted to the data store from a second agent different from the first agent, wherein the first agent does not communicate with the second agent. ### Claim 22 A computer-implemented method for centralized data management, the method comprising: receiving, from a first agent, a data request, wherein the first agent is configured to access one or more inputs and to perform one or more actions in response to the one or more inputs; determining that the first agent is authorized to issue the data request; identifying a dataset in a data store that is responsive to the data request; determining if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: determining that the second agent is providing information for updating the dataset; updating the dataset; determining, using the provided information, an updated confidence level for the second agent; and transmitting the dataset to the first agent, wherein the dataset is transmitted to the data store from a second agent different from the first agent, wherein the first agent does not communicate with the second agent. ### Claim 23 A system for centralized data management, the system comprising: at least one hardware processor; and at least one non-transitory, computer-readable storage medium having instructions thereon that, when executed by the at least one hardware processor, cause the system to: receive, from a first agent, a data request, wherein the first agent is configured to access one or more inputs and to perform one or more actions in response to the one or more inputs; determine that the first agent is authorized to issue the data request; identify a dataset in a data store that is responsive to the data request; determine if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: determine that the second agent is providing information for updating the dataset; update the dataset, wherein the updating is done as one or more atomic transactions; and transmit the dataset to the first agent, wherein the dataset is transmitted to the data store from a second agent different from the first agent, wherein the first agent does not communicate with the second agent. ### Claim 24 A system for centralized data management, the system comprising: at least one hardware processor; and at least one non-transitory, computer-readable storage medium having instructions thereon that, when executed by the at least one hardware processor, cause the system to: receive, from a first agent, a data request, wherein the first agent is configured to access one or more inputs and to perform one or more actions in response to the one or more inputs; determine that the first agent is authorized to issue the data request; identify a dataset in a data store that is responsive to the data request; determine if the dataset is not a restricted dataset; and when the dataset is not a restricted dataset: determine that the second agent is providing information for updating the dataset; update the dataset; determine, using the provided information, an updated confidence level for the second agent; and transmit the dataset to the first agent, wherein the dataset is transmitted to the data store from a second agent different from the first agent, wherein the first agent does not communicate with the second agent.