# US 2026/0140499 A1 · Computer-assisted test plan creation using generative ai

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

- Number: US 2026/0140499 A1
- Document ID: US20260140499A1
- Status: Published application
- Kind: A1
- Application number: 19/358,933
- Filed: 2025-10-15
- Published: 2026-05-21
- Earliest claimed: 2023-04-16
- Assignees: Tulip Interfaces, Inc.
- Applicants: Tulip Interfaces, Inc.
- Inventors: Natan Linder; Rony Kubat; Roy Shilkrot; Mason Guy Glidden
- Web page: https://patentgrep.com/patent/US20260140499A1

## CPC

- G06F 16/345: {Summarisation for human users}
- G06Q 50/04: Manufacturing
- G05B 19/0426: {Programming the control sequence}
- G05B 19/41845: {characterised by system universality, reconfigurability, modularity}
- G05B 23/0248: {Causal models, e.g. fault tree; digraphs; qualitative physics}
- G05B 23/0272: {Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user}
- G06F 9/4887: {involving deadlines, e.g. rate based, periodic}
- G06F 16/383: using metadata automatically derived from the content
- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 40/30: Semantic analysis
- G06F 40/56: Natural language generation
- G06N 3/0475: Generative networks
- G06N 20/00: Machine learning
- G06Q 10/0639: Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06V 10/82: using neural networks
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G05B 2219/23249: Using audio and or video playback
- G06V 2201/06: Recognition of objects for industrial automation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Generative artificial intelligence is applied to a manufacturing process to create a test plan for validation, including proof of execution of various test, process steps, and the like.

## Claims

### Claim 1

A computer program product comprising computer executable code embodied in a non-transitory computer readable medium that, when executing on one or more computing devices, performs the steps of:
converting an application for a manufacturing process into an intermediate representation in near natural language form;
requesting a description of the application from a first large language model based on the intermediate representation;
receiving one or more validation rules for the manufacturing process based on at least one of a regulation, an industry standard, and a customer requirement;
presenting the description of the application and the one or more validation rules to a second large language model along with a request for an evaluation of whether the manufacturing process consistently satisfies the one or more validation rules; and
presenting a result for the evaluation as a validation report in human readable form.

### Claim 2 (depends on 1)

The computer program product of claim 1, wherein requesting the description of the application includes requesting a classification of the application from a classification engine.

### Claim 3 (depends on 1)

The computer program product of claim 1, wherein receiving the one or more validation rules includes providing the one or more validation rules to a second large language model with a request for a natural language description.

### Claim 4 (depends on 3)

The computer program product of claim 3, further comprising code that performs the step of prompting the second large language model to specify one or more additional sensors recommended for the manufacturing process to satisfy the one or more validation rules.

### Claim 5 (depends on 1)

The computer program product of claim 1, further comprising code that performs the step of prompting the second large language model to specify one or more human touch points for inspection recommended for the manufacturing process to satisfy the one or more validation rules.

### Claim 6 (depends on 1)

The computer program product of claim 1, wherein requesting the description of the application includes providing the first large language model with supplemental descriptive data for the application.

### Claim 7 (depends on 6)

The computer program product of claim 6, wherein the supplemental descriptive data includes a screenshot of a user interface acquired during execution of the application.

### Claim 8 (depends on 6)

The computer program product of claim 6, wherein the supplemental descriptive data includes one or more of a user interface for the application, a user manual for the application, a video captured during the manufacturing process, and a text summary of the application.

### Claim 9

A method comprising:
receiving a description of an application for a manufacturing process;
receiving one or more validation rules for the manufacturing process; and
requesting a validation report from an inference engine by presenting the description of the application and the one or more validation rules to the inference engine along with a request for an evaluation of whether the manufacturing process consistently satisfies the one or more validation rules.

### Claim 10 (depends on 9)

The method of claim 9, further comprising presenting the validation report to a user.

### Claim 11 (depends on 9)

The method of claim 9, wherein requesting the description of the application includes requesting a classification of the application from a classification engine.

### Claim 12 (depends on 9)

The method of claim 9, requesting the validation report includes requesting documentation from the inference engine of how the application satisfies each of the one or more validation rules.

### Claim 13 (depends on 9)

The method of claim 9, wherein receiving the one or more validation rules includes receiving validation documentation including at least one of a regulation applicable to the manufacturing process, an industry standard applicable to the manufacturing process, and a customer requirement applicable to the manufacturing process, and requesting a summary of the validation documentation from an inference engine.

### Claim 14 (depends on 9)

The method of claim 9, wherein requesting the validation report includes requesting machine readable code to modify the application to satisfy the one or more validation rules.

### Claim 15 (depends on 9)

The method of claim 9, wherein requesting the validation report includes providing the inference engine with a sensor description characterizing one or more sensors available to the application during the manufacturing process, and requesting a description of how the one or more sensors can be used to satisfy the one or more validation rules.

### Claim 16 (depends on 9)

The method of claim 9, wherein requesting the validation report includes prompting the inference engine to specify one or more sensors recommended for the application to satisfy the one or more validation rules.

### Claim 17 (depends on 9)

The method of claim 9, wherein the one or more validation rules include one or more steps to be required during the manufacturing process.

### Claim 18 (depends on 9)

The method of claim 9, wherein receiving the description of the application includes providing a second inference engine with supplemental descriptive data for the application along with a request for the description in a near natural language form.

### Claim 19 (depends on 18)

The method of claim 18, wherein the supplemental descriptive data includes one or more of a user interface for the application, a user manual for the application, a video captured during the manufacturing process, a screen shot captured while the application is executing, a user interface layout for the application, a code segment for the application, and a text summary of the application.

### Claim 20

A system comprising:
a manufacturing process controlled by an application;
a text description of one or more validation requirements for the manufacturing process; and
a test plan generation module configured to perform the steps of:
requesting a description of the application from a first large language model, and
requesting a validation report from a second inference engine, the validation report including a human readable description of how the application satisfies the one or more validation requirements for the manufacturing process based on the description of the application and the text description of the one or more validation requirements.