# US 2026/0087325 A1 · Artificial intelligence access layer for application control

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

- Number: US 2026/0087325 A1
- Document ID: US20260087325A1
- Status: Published application
- Kind: A1
- Application number: 18/894,246
- Filed: 2024-09-24
- Published: 2026-03-26
- Earliest claimed: 2024-09-24
- Assignees: Sap SE
- Applicants: Sap SE
- Inventors: Felipe Hernandez Plazas; Bernd Dittrich
- Web page: https://patentgrep.com/patent/US20260087325A1

## CPC

- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- G06N 3/0475: Generative networks
- G06F 9/4843: {by program, e.g. task dispatcher, supervisor, operating system}
- G06F 9/548: {Object oriented; Remote method invocation [RMI] (non-remote method invocation G06F9/449)}
- G06F 40/00: Handling natural language data (speech analysis or synthesis, speech recognition G10L)
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/216: using statistical methods
- G06F 40/279: Recognition of textual entities
- G06F 40/30: Semantic analysis
- G06F 40/35: Discourse or dialogue representation
- G06F 40/56: Natural language generation
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/10: Interfaces, programming languages or software development kits, e.g. for simulating neural networks
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- H04L 67/306: User profiles
- H04L 67/561: Adding application-functional data or data for application control, e.g. adding metadata
- G06F 9/4484: {Executing subprograms}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods described herein relate to a generative artificial intelligence (AI) access layer that is implemented for dynamic control of a software application. Input is received from the software application. A generative AI model is used to detect a relevant capability based on the input. Prompt data is generated based on generative AI scenario settings for the relevant capability. The prompt data includes at least some of the input and context data accessible to the software application. A capability result is generated by using the generative AI model to process the prompt data. The generation of the capability result is dynamically controlled using the generative AI scenario settings. The software application executes the relevant capability based on the capability result. Output is presented within a user interface of the software application.

## Claims

### Claim 1

A system comprising:
at least one memory that stores instructions; and
one or more processors configured by the instructions to perform operations comprising:
receiving input from a software application;
in response to receiving the input, transmitting a request to a generative artificial intelligence (AI) model to detect, based on first prompt data comprising the input, a relevant capability from among a plurality of supported capabilities of the software application;
automatically generating, based on generative AI scenario settings for the relevant capability, second prompt data comprising context data accessible to the software application and at least a subset of the input;
automatically generating a capability result for the relevant capability, the generating of the capability result being dynamically controlled using the generative AI scenario settings and comprising transmitting, to the generative AI model, at least one further request that includes the second prompt data; and
executing, by the software application, the relevant capability based on the capability result, the executing of the relevant capability causing presentation of output within a user interface of the software application.

### Claim 2 (depends on 1)

The system of claim 1, wherein the input comprises natural language user input, and the output comprises an execution result of the relevant capability, the operations further comprising:
generating the user interface of the software application to include a user input section;
causing presentation of the user interface at a user device during a user session;
receiving the natural language user input via the user input section;
in response to receiving the natural language user input, generating the generative AI scenario settings for the user session;
after presentation of the execution result within the user interface, receiving a user selection to confirm the execution result; and
in response to receiving the user selection, persisting the execution result in a database.

### Claim 3 (depends on 1)

The system of claim 1, the operations further comprising:
in response to receiving the input, accessing, from a database, a generative AI profile associated with the software application; and
instantiating, based on the generative AI profile, a scenario object to define the generative AI scenario settings.

### Claim 4 (depends on 3)

The system of claim 3, wherein the generative AI profile defines the plurality of supported capabilities of the software application, and further provides access to at least one of model settings or a plurality of prompt structures for dynamically interacting with the generative AI model.

### Claim 5 (depends on 1)

The system of claim 1, wherein the relevant capability is one of a plurality of relevant capabilities detected using the generative AI model, the operations comprising:
generating a respective capability result for each of the plurality of relevant capabilities, the respective capability results being generated at least partially in parallel.

### Claim 6 (depends on 5)

The system of claim 5, the operations further comprising, for each relevant capability of the plurality of relevant capabilities:
instantiating a capability-specific scenario object for the relevant capability, the capability-specific scenario object comprising capability-specific scenario settings to control the generating of the respective capability result for the relevant capability.

### Claim 7 (depends on 6)

The system of claim 6, wherein the generative AI model identifies, for each relevant capability of the plurality of relevant capabilities, the context data to be provided based on the capability-specific scenario settings, the operations further comprising:
instantiating a context handling object to retrieve the context data from a context dataset associated with the software application.

### Claim 8 (depends on 5)

The system of claim 5, the operations further comprising:
consolidating the respective capability results for the plurality of relevant capabilities into a structured set of capability results; and
processing, by the software application, the structured set of capability results to cause execution of the plurality of relevant capabilities.

### Claim 9 (depends on 1)

The system of claim 1, wherein the relevant capability is one of a plurality of relevant capabilities detected using the generative AI model, and the generative AI model processes the user input, based on the first prompt data, to detect a first portion of the user input that is associated with a first capability of the plurality of relevant capabilities and a second portion of the user input that is associated with a second capability of the plurality of relevant capabilities.

### Claim 10 (depends on 1)

The system of claim 1, wherein the capability result comprises structured data that provides, to the software application, one or more parameter values for executing the relevant capability.

### Claim 11 (depends on 1)

The system of claim 1, wherein the generative AI scenario settings comprise prompt settings for generating prompt data and function call settings for handling automated function calls, the operations further comprising:
executing at least one function call based on both the function call settings and a response received from the generative AI model.

### Claim 12 (depends on 11)

The system of claim 11, wherein the executing of the at least one function call comprises recursively executing function calls to finalize the generating of the capability result.

### Claim 13 (depends on 1)

The system of claim 1, wherein the input comprises at least one of natural language user input received from the software application via a user device or automated system input received from the software application.

### Claim 14 (depends on 1)

The system of claim 1, wherein the software application is a transportation management software application, the context data comprises information related to one or more transportation data objects, and the relevant capability comprises at least one of scheduling, assigning, updating, adapting, or augmenting the one or more transportation data objects within a context of the software application.

### Claim 15

A computer-implemented method performed by a computer system comprising a memory and at least one hardware processor, the computer-implemented method comprising:
receiving input from a software application;
in response to receiving the input, transmitting a request to a generative artificial intelligence (AI) model to detect, based on first prompt data comprising the input, a relevant capability from among a plurality of supported capabilities of the software application;
automatically generating, based on generative AI scenario settings for the relevant capability, second prompt data comprising context data accessible to the software application and at least a subset of the input;
automatically generating a capability result for the relevant capability, the generating of the capability result being dynamically controlled using the generative AI scenario settings and comprising transmitting, to the generative AI model, at least one further request that includes the second prompt data; and
executing, by the software application, the relevant capability based on the capability result, the executing of the relevant capability causing presentation of output within a user interface of the software application.

### Claim 16 (depends on 15)

The computer-implemented method of claim 15, wherein the input comprises natural language user input, and the output comprises an execution result of the relevant capability, the computer-implemented method further comprising:
generating the user interface of the software application to include a user input section;
causing presentation of the user interface at a user device during a user session;
receiving the natural language user input via the user input section;
in response to receiving the natural language user input, generating the generative AI scenario settings for the user session;
after presentation of the execution result within the user interface, receiving a user selection to confirm the execution result; and
in response to receiving the user selection, persisting the execution result in a database.

### Claim 17 (depends on 15)

The computer-implemented method of claim 15, further comprising:
in response to receiving the input, accessing, from a database, a generative AI profile associated with the software application; and
instantiating, based on the generative AI profile, a scenario object to define the generative AI scenario settings.

### Claim 18

One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by a computing system, cause the computing system to perform operations comprising:
receiving input from a software application;
in response to receiving the input, transmitting a request to a generative artificial intelligence (AI) model to detect, based on first prompt data comprising the input, a relevant capability from among a plurality of supported capabilities of the software application;
automatically generating, based on generative AI scenario settings for the relevant capability, second prompt data comprising context data accessible to the software application and at least a subset of the input;
automatically generating a capability result for the relevant capability, the generating of the capability result being dynamically controlled using the generative AI scenario settings and comprising transmitting, to the generative AI model, at least one further request that includes the second prompt data; and
executing, by the software application, the relevant capability based on the capability result, the executing of the relevant capability causing presentation of output within a user interface of the software application.

### Claim 19 (depends on 18)

The one or more non-transitory computer-readable media of claim 18, wherein the input comprises natural language user input, and the output comprises an execution result of the relevant capability, the operations further comprising:
generating the user interface of the software application to include a user input section;
causing presentation of the user interface at a user device during a user session;
receiving the natural language user input via the user input section;
in response to receiving the natural language user input, generating the generative AI scenario settings for the user session;
after presentation of the execution result within the user interface, receiving a user selection to confirm the execution result; and
in response to receiving the user selection, persisting the execution result in a database.

### Claim 20 (depends on 18)

The one or more non-transitory computer-readable media of claim 18, the operations further comprising:
in response to receiving the input, accessing, from a database, a generative AI profile associated with the software application; and
instantiating, based on the generative AI profile, a scenario object to define the generative AI scenario settings.
