DETAILED ACTION
This action is in reply to the submission filed on 3/11/2026.
Status of Claims
Applicant’s amendments to claims 1-4 and 6-20 are acknowledged.
Claims 1-20 are currently pending and have been examined.
Response to Remarks
Applicant's remarks filed 3/11/2026 have been fully considered and have been found not persuasive in full. Regarding pages 8 and 9 of remarks, while the claims are not directed merely to the concept of “paying employees or organizing human activity”, they are not solving a technological problem, nor is there seen in the disclosure any such claim. The claims are using the combination of multiple differently trained large language models (LLMs) to perform a data analysis workflow. That is, the outputs of the first LLM are being used as the inputs for the second LLM. However, that is not seen as solving a technological problem, or improving the computing technology behind large language models. Therefore, the claims are seen as using LLM technology in its ordinary capacity to perform the payroll processing workflow, said workflow being fundamental economic concepts.
Regarding page 9 of remarks, the combination of the payroll processing workflow, anomaly detection, and corrective action routing are similarly seen as using trained LLMs to perform data analysis relating to payroll processing. In this case, the ordered combination of LLMs is seen as just one embodiment of the data analysis that could be accomplished by other technologies being used as tools to perform said analysis.
Claim Interpretation
Claim 1’s limitations concerning the first phase LLM processing payroll input data to generate structured payroll parameters is interpreted in light of paragraph 88 of the disclosed specification dated 8/21/2024. Said paragraph 88 teaches using an LLM output as input for the next payroll step, and the output can include rules and data. This language, “rules and data”, is within the scope of the claimed “structured payroll parameters”. Therefore, said claim language is interpreted to include the scope of “rules and data for a next step of the payroll process to be ingested by another LLM”. It is noted that any scope of the “structured payroll parameters” afforded by a broadest reasonable interpretation (BRI) not included in the disclosed rules and data is considered new matter and will not be afforded the application’s effective filing date. The Office will consider any supporting citations in present disclosure for purposes of determining the BRI.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: the claims fall under statutory categories of processes and/or machines.
Step 2A Prong 1: the claims recite: receive a request to perform payroll processing workflow for employees; extracting payroll information from data repositories; executing the workflow by processing payroll input data to generate structured payroll parameters, determining payroll calculations based on the parameters; and evaluating payroll outputs for compliance with jurisdiction-specific employment policies; monitoring workflow to detect anomalies including missing data or delayed phases; and updating a workflow state record to reflect completion. These limitations, as drafted, is a process that, under its broadest reasonable interpretation, covers certain methods of organizing human activity, specifically fundamental economic behavior, including paying employees. They are also directed to commercial or legal interactions, including legal obligations and business relations.
Step 2A Prong 2: Said judicial exception is not integrated into a practical application because the claims as a whole, looking at the additional elements: a non-transitory computer readable medium having instructions enabling a processor to perform, a cloud-based server with processor, memory and software, instantiating a plurality of phase-specific LLMs being configured to perform a different phase of the workflow, where the LLMs use LLM output as input, individually and in combination, merely use a computer (see MPEP 2106.05f.) The claims use these machines in their ordinary capacity for the purpose of applying the abstract idea(s). Therefore, these limitations are invoking computers or other machinery merely as a tool to perform an existing process, such that it amounts to no more than mere instructions to apply the exception. Then, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea, and the claim is directed to an abstract idea.
Step 2B: Said claims recite additional elements as listed above, which are not sufficient to amount to significantly more than the judicial exception because, as mentioned in Step 2A Prong 2, they use computers or other machinery to perform an abstract idea in such a way that amounts to no more than mere instructions to apply the exception using computers or other machinery. Mere instructions to apply an exception using computers or other machinery cannot provide an inventive concept. Therefore, the claim is not patent eligible.
Claims 2, 10 and 17 recite training the LLM with data specific to the payroll process. Office guidance suggests this is not more than “apply it” level of technology used in its ordinary capacity, as LLMs are inherently trained. Claims 3 and 11 recite LLMs adapted to operate with respect to a RACI framework, and invoking an additional LLM configured to generate corrective action instructions and route them to a stakeholder according the RACI. This, in combination with claim 1’s LLMs, is also seen as using LLMs in their ordinary capacity. That is, using LLMs with training data to perform a specific outcome after inputting data and receiving output. Using output data from one LLM as input data for another LLM to perform data transformation using LLMs is not seen as improving the functioning of LLM technology. Claims 4-8, 12-15 and 18-20 recite variations on the LLM training, as well as capability assessment of LLMs, and a cloud-based server in claim 5. This is seen as the same technology in above analysis.
For these reasons, the claims are not subject matter eligible.
Reasons why the Claims Would be Allowable over Prior Art
The following is a statement of reasons for the indication of allowable subject matter:
No prior art or non-patent literature has been found that teaches the claimed limitations regarding the claimed sequential usage of LLMs’ outputs as inputs, that are trained as claimed, in the context of payroll calculation, in combination with the other limitations found within the independent claim(s).
The closest prior art that reads on the claims are previously cited King, Skiles, (US 2023/0014904), and Schrage (US 2021/0004915). King teaches using machine learning to perform payroll analysis and predict recommended payroll activities, but not using multiple LLMs in step to output payroll calculations and monitor anomalies in payroll processing. Skiles uses multiple machine learning models in succession, one model’s output as another’s input, but not with machine learning models, and further does not teach a payroll process. Schrage teaches using neural networks in succession to detect payroll fraud, but not the claimed payroll process. In summation, Applicant' s claims are distinct from the closest prior art. For these reasons, the 103 rejections are overcome.
The examiner notes the cited limitations above in combination with the other limitations found within the independent claim(s) are found to be allowable over the prior art of record. Independent claims recite the quoted allowable subject matter or substantially similar language. Accordingly, the claims and their dependent claims are allowable over the prior art for the reasons identified.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, this action is made final. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Aaron Tutor, whose telephone number is 571-272-3662. The examiner can normally be reached Monday through Friday, 9 AM to 5 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Fahd Obeid, can be reached at 571-270-3324. The fax number for the organization where this application or proceeding is assigned is 571-273-5266.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AARON TUTOR/Primary Examiner, Art Unit 3627
Prosecution Insights