# US 2026/0268252 A1 · Systems and methods for ai-driven workflow platform without moving data from closed data warehouse

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

- Number: US 2026/0268252 A1
- Document ID: US20260268252A1
- Status: Published application
- Kind: A1
- Application number: 19/354,627
- Filed: 2025-10-09
- Published: 2026-09-10
- Earliest claimed: 2025-03-10
- Assignees: Elementum, LLC
- Applicants: Elementum Ltd
- Inventors: David A. BLONSKI; Karen JENKINS; Nader MIKHAIL; Robert HUGHES; Porter HOSKINS; Josh WAITE
- Web page: https://patentgrep.com/patent/US20260268252A1

## CPC

- G06Q 10/06316: {Sequencing of tasks or work}
- G06F 3/0486: Drag-and-drop
- G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues}
- G06F 9/5072: {Grid computing}
- G06F 16/254: {Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses}
- G06Q 40/03055: {using artificial intelligence, machine learning or neural networks}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method is provided for an artificial intelligence (AI)-driven workflow platform. The method comprises: (a) executing a workflow, where at least a portion of the workflow is automated by an AI agent, the AI agent resides on a data cloud configuration that is operatively coupled to the AI-driven workflow platform; (b) storing, by an agent memory residing on the data cloud configuration, context data or workflow states generated during execution of the workflow; (b) generating, by an agent orchestrator residing on the AI-driven workflow platform, a structured prompt for the AI agent and one or more parameters for executing one or more tools provided by the AI-driven workflow platform. The structured prompt is generated based at least in part on the context data or workflow states stored on the data cloud configuration.

## Claims

### Claim 1

A computer-implemented method for an artificial intelligence (AI)-driven workflow platform, the method comprising:
(a) generating a workflow in the AI-driven workflow platform, wherein at least a portion of the workflow is automated by calling an AI agent, wherein the AI agent is executed natively within cloud data warehouse that is separate from and operatively coupled to the AI-driven workflow platform;
(b) maintaining, by a memory residing on the cloud data warehouse, context data or workflow states generated during an execution of the workflow;
(c) accessing, by an agent orchestrator residing on the AI-driven workflow platform, the context data or the workflow states stored in the memory on the cloud data warehouse without persisting the context data or the workflow states external to the cloud data warehouse:
(d) generating, by the agent orchestrator, a structured prompt for the AI agent and one or more parameters for executing one or more tools provided by the AI-driven workflow platform, wherein the structured prompt is generated based at least in part on the context data or the workflow states; and
(e) prompting the AI agent with the structured prompt and executing the workflow to perform an operation on one or more data objects within the cloud data warehouse without using an extract, transform and load (ETL) data integration process.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the structured prompt comprises context information and constraints injected by the agent orchestrator thereby limiting data to be accessed by the AI agent.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the agent orchestrator is configured to generate the context information by selecting one or more referential fields of the one or more data objects to be accessed by the AI agent.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the one or more referential fields of the one or more data objects are defined in a design-time configuration and are dynamically adjusted by the agent orchestrator in a run-time configuration.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the structured prompt is generated further based on an execution parameter or a data access policy.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein one or more tools comprise at least one of a workflow automation tool, a communication tool, a data retrieval tool, an integration application programming interface (API), and a decision support tool.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, further comprising storing one or more constraints associated with the one or more tools in a toolset registry residing on the AI-driven workflow platform.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein the toolset registry is configurable by a user via a graphical user interface (GUI) provided by the AI-driven workflow platform.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein executing the one or more tools comprises validating an input or output of the AI agent against the one or more constraints associated with the one or more tools.

### Claim 10

(canceled)

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, wherein the cloud data warehouse configuration comprises one or more data clouds storing the one or more data objects, and wherein the AI-driven workflow platform is granted permission to access, process, and edit the one or more data objects stored on the one or more data clouds.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, wherein executing the workflow comprises mapping selected one or more data objects stored on the one or more data clouds to a data storage model of the AI-driven workflow platform.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, further comprising defining a relationship between the selected one or more data objects and an element of the data storage model.

### Claim 14 (depends on 13)

The computer-implemented method of claim 13, wherein the relationship is defined by a user via a graphical user interface (GUI) provided by the AI-driven workflow platform.

### Claim 15 (depends on 14)

The computer-implemented method of claim 14, wherein the GUI permits the user to link one or more data fields of selected one or more data objects to one or more data fields or the element of the data storage model.

### Claim 16 (depends on 14)

The computer-implemented method of claim 14, wherein the workflow is an interactive workflow and is built via the GUI.

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, wherein the interactive workflow permits a user to add, remove or modify one or more components of a cloud application by dragging and dropping one or more graphical elements to the interactive workflow.

### Claim 18

A system for providing an artificial intelligence (AI)-driven workflow platform, the system comprising at least one processor and instructions executable to cause the at least one processor to perform operations comprising:
(a) generating a workflow in the AI-driven workflow platform, wherein at least a portion of the workflow is automated by calling an AI agent, wherein the AI agent is executed natively within a cloud data warehouse that is separate from and operatively coupled to the AI-driven workflow platform;
(b) maintaining, by a memory residing on the cloud data warehouse, context data or workflow states generated during an execution of the workflow;
(c) accessing, by an agent orchestrator residing on the AI-driven workflow platform, the context data or the workflow states stored in the memory on the cloud data warehouse without persisting the context data or the workflow states external to the cloud data warehouse;
(d) generating, by the agent orchestrator, a structured prompt for the AI agent and one or more parameters for executing one or more tools provided by the AI-driven workflow platform, wherein the structured prompt is generated based at least in part on the context data or the workflow states; and
(e) prompting the AI agent with the structured prompt and executing the workflow to perform an operation on one or more data objects within the cloud data warehouse without using an extract, transform and load (ETL) data integration process.

### Claim 19 (depends on 18)

The system of claim 18, wherein the structured prompt comprises context information and constraints injected by the agent orchestrator thereby limiting data to be accessed by the AI agent.

### Claim 20 (depends on 18)

The system of claim 18, wherein the agent orchestrator is configured to generate the context information by selecting one or more referential fields of the one or more data objects to be accessed by the AI agent.

### Claim 21 (depends on 20)

The system of claim 20, wherein the one or more referential fields of the one or more data objects are defined in a design-time configuration and are dynamically adjusted by the agent orchestrator in a run-time configuration.

### Claim 22 (depends on 18)

The system of claim 18, wherein the structured prompt is generated further based on an execution parameter or a data access policy.

### Claim 23 (depends on 18)

The system of claim 18, wherein the one or more tools comprise at least one of a workflow automation tool, a communication tool, a data retrieval tool, an integration application programming interface (API), and a decision support tool.

### Claim 24 (depends on 18)

The system of claim 18, wherein one or more constraints associated with the one or more tools are stored in a toolset registry residing on the AI-driven workflow platform.

### Claim 25 (depends on 24)

The system of claim 24, wherein the toolset registry is configurable by a user via a graphical user interface (GUI) provided by the AI-driven workflow platform and wherein executing the one or more tools comprises validating an input or output of the AI agent against the one or more constraints associated with the one or more tools.

### Claim 26 (depends on 18)

The system of claim 18, wherein the cloud data warehouse comprises one or more data clouds storing the one or more data objects, and wherein the AI-driven workflow platform is granted permission to access, process, and edit the one or more data objects stored on the one or more data clouds.

### Claim 27 (depends on 26)

The system of claim 26, wherein executing the one or more tools comprises mapping selected one or more data objects stored on the one or more data clouds to a data storage model of the AI-driven workflow platform.

### Claim 28 (depends on 27)

The system of claim 27, wherein the operations further comprise defining a relationship between the selected one or more data objects and an element of the data storage model.

### Claim 29 (depends on 28)

The system of claim 28, wherein the relationship is defined by a user via a graphical user interface (GUI) provided by the AI-driven workflow platform.

### Claim 30 (depends on 29)

The system of claim 29, wherein the GUI permits the user to link one or more data fields of selected one or more data objects to one or more data fields or the element of the data storage model.

### Claim 31 (depends on 29)

The system of claim 29, wherein the workflow is an interactive workflow and is built via the GUI and wherein the interactive workflow permits a user to add, remove or modify one or more components of a cloud application by dragging and dropping one or more graphical elements to the interactive flow.
