# US 2025/0094191 A1 · System and method for custom action creation in automation workflows

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

- Number: US 2025/0094191 A1
- Document ID: US20250094191A1
- Status: Published application
- Kind: A1
- Application number: 18/891,679
- Filed: 2024-09-20
- Published: 2025-03-20
- Earliest claimed: 2023-09-20
- Assignees: Zapier, Inc.
- Applicants: Zapier, Inc.
- Inventors: Bryan Helmig; Brian Corbin; Justin Deal; Vitor Balocco; Lisa Orr; Brady Skaurud
- Web page: https://patentgrep.com/patent/US20250094191A1

## CPC

- G06F 9/453: {Help systems}
- G06F 8/30: Creation or generation of source code
- G06F 9/541: {via adapters, e.g. between incompatible applications}
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and system for custom action creation in automation workflows is disclosed. In some embodiments, the method includes receiving a request for creating an application extension from a user, the application extension including at least one custom action. The method includes determining, using one or more trained artificial intelligence (AI) models, one or more existing application extensions and associated parameters from a plurality of connected applications. The method also includes generating one or more first graphical interfaces to present a recommendation to the user, the recommendation including the one or more existing application extensions and associated parameters. The method further includes receiving a selection of the recommendation from the user and, in response to receiving the selection, creating the application extension based at least on the recommended parameters.

## Claims

### Claim 1

A method for custom action creation in automation workflows comprising:
receiving a request for creating an application extension from a user, the application extension including at least one custom action;
determining, using one or more trained artificial intelligence (AI) models, one or more existing application extensions and associated parameters from a plurality of connected applications;
generating one or more first graphical interfaces to present a recommendation to the user, the recommendation including the one or more existing application extensions and associated parameters;
receiving a selection of the recommendation from the user; and
in response to receiving the selection, creating the application extension based at least on the recommended parameters.

### Claim 2 (depends on 1)

The method of claim 1, wherein creating the application extension based at least on the recommended parameters comprises:
in response to the user rejecting the recommended application extensions,
generating one or more second graphical interfaces to provide instructions for the user to create the at least one custom action;
populating values to one or more fields of the one or more second graphical interfaces based on the associated parameters; and
providing the populated values to the user to reduce user input in creating the at least one custom action.

### Claim 3 (depends on 1)

The method of claim 1, wherein creating the application extension based at least on the recommended parameters comprises:
in response to the user accepting a recommended application extension, using the accepted application extension to complete creating the application extension.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining the one or more existing application extensions and associated parameters comprises performing at least one of semantic search and AI prompting.

### Claim 5 (depends on 1)

The method of claim 1, further comprising generating one or more text responses to request additional information or to confirm user requirements, wherein determining the one or more existing application extensions and associated parameters is based at least on the user requirements.

### Claim 6 (depends on 1)

The method of claim 1, further comprising synchronizing information of the plurality of connected applications.

### Claim 7 (depends on 1)

The method of claim 1, wherein the request for creating the application extension comprises a natural language prompt describing the at least one custom action.

### Claim 8 (depends on 1)

The method of claim 1, further comprising generating one or more coding interfaces for a user to run a software program and create the application extension.

### Claim 9 (depends on 1)

The method of claim 1, further comprising sharing the application extension with one or more other users.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
training the one or more AI models using secured application programming interface (API) database.

### Claim 11

A system for custom action creation in automation workflows comprising:
a processor; and
a memory in communication with the processor and comprising instructions which, when executed by the processor, program the processor to:
receive a request for creating an application extension from a user, the application extension including at least one custom action;
determine, using one or more trained artificial intelligence (AI) models, one or more existing application extensions and associated parameters from a plurality of connected applications;
generate one or more first graphical interfaces to present a recommendation to the user, the recommendation including the one or more existing application extensions and associated parameters;
receive a selection of the recommendation from the user; and
in response to receiving the selection, create the application extension based at least on the recommended parameters.

### Claim 12 (depends on 11)

The system of claim 11, wherein, to create the application extension based at least on the recommended parameters, the instructions further program the processor to:
in response to the user rejecting the recommended application extensions,
generate one or more second graphical interfaces to provide instructions for the user to create the at least one custom action;
populate values to one or more fields of the one or more second graphical interfaces based on the associated parameters; and
provide the populated values to the user to reduce user input in creating the at least one custom action.

### Claim 13 (depends on 11)

The system of claim 11, wherein, to create the application extension based at least on the recommended parameters, the instructions further program the processor to:
in response to the user accepting a recommended application extension, use the accepted application extension to complete creating the application extension.

### Claim 14 (depends on 11)

The system of claim 11, wherein, to determine the one or more existing application extensions and associated parameters, the instructions further program the processor to perform at least one of semantic search and AI prompting.

### Claim 15 (depends on 11)

The system of claim 11, wherein the instructions further program the processor to generating one or more text responses to request additional information or to confirm user requirements, wherein determining the one or more existing application extensions and associated parameters is based at least on the user requirements.

### Claim 16 (depends on 11)

The system of claim 11, wherein the instructions further program the processor to synchronize information of the plurality of connected applications.

### Claim 17 (depends on 11)

The system of claim 11, wherein the request for creating the application extension comprises a natural language prompt describing the at least one custom action.

### Claim 18 (depends on 11)

The system of claim 11, wherein the instructions further program the processor to generate one or more coding interfaces for a user to run a software program and create the application extension.

### Claim 19 (depends on 11)

The system of claim 11, wherein the instructions further program the processor to share the application extension with one or more other users.

### Claim 20

A computer program product for custom action creation in automation workflows, the computer program product comprising a non-transitory computer-readable medium having computer readable program code stored thereon, the computer readable program code configured to:
receive a request for creating an application extension from a user, the application extension including at least one custom action;
determine, using one or more trained artificial intelligence (AI) models, one or more existing application extensions and associated parameters from a plurality of connected applications;
generate one or more first graphical interfaces to present a recommendation to the user, the recommendation including the one or more existing application extensions and associated parameters;
receive a selection of the recommendation from the user; and
in response to receiving the selection, create the application extension based at least on the recommended parameters.
