DETAILED ACTION
This is Final Office Action in response to amendment filed on July 27, 2026. Claim 8 has been cancelled. Claim 21 is newly added. Claims 1-7 and 9-21 are pending.
Information Disclosure Statement
The references listed in the IDS filed on August 2, 2026 has been considered and entered into record. A copy of the signed or initialed IDS is hereby attached.
Response to Arguments
Applicant's arguments regarding the “system-level agent connecting a user to various abilities of installed applications within the context and interface of an application” (response 7/27/2026, pages 2-3) have been fully considered but they are not persuasive. The examiner respectfully disagrees. The recitations that the “system-level agent connects a user to various abilities of installed applications within the interface of an application” amounts to an abstract idea and fail to integrate it into a practical application under Step 2A, prong 2 and Step 2B Merely using a computer as a tool to perform an abstract idea does not integrate the abstract idea into a practical application (see MPEP 2106.05(f)). Likewise, using a large language model to perform the recited functions does not provide an inventive concept or amount to significantly more than the abstract idea (see Recentive Analytics V. Fox Broadcasting Corp. (134 F.4th 1205, 2025 U.S.P.Q.2d 628). The claimed use of well-known machine learning or large language model techniques such as supervised training within an interface, represents the use of conventional computing techniques. Accordingly, these limitations, individually or in combination, do not amount to significantly more than an abstract idea. For these reasons, the rejection under §101 is maintained.
Applicant’s arguments regarding the amended limitations “generating an application agent, wherein the application agent is a system-level large language model service of an operating system of the device and is instantiated by the operating system within an interface of the application; wherein the action output comprises a first executable instruction to be executed by the application and a second executable instruction to be executed by another application accessible by the operating system” (response 7/27/2026, pages 2-3) with respect to the rejections of claims 1-20 under 35 USC § 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of Visoky et al. (US 20250291327 A1).
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. The claims recite accessing, by one or more processors, an application running on a device; generating, by the one or more processors and based on one or more parameters of the application, an application agent, wherein the application agent is instantiated within the application, the instantiation comprising an interface within the application; receiving, by the one or more processors via the application agent, an input prompt, the input prompt comprising a plurality of words in a natural-language format; providing, by the one or more processors, the input prompt as an input for one or more large language models (LLMs); receiving, by the one or more processors, an inference output of the one or more LLMs, the inference output indicative of an intent of the input prompt; and causing, by the one or more processors and based on the intent of the input prompt, the device to perform an action output. This judicial exception is not integrated into a practical application because the steps can be performed manually in human mind. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claim here merely uses the processor as a tool to perform the otherwise mental processes. See October Update at Section I(C)(ii). Thus, the limitations recite concepts that fall into the “mental process” grouping of abstract ideas.
ANALYSIS under Revised Guidance of 2019 PEG:
Statutory Category:
The claims 1-20 are directed to one of the four statutory category (claims 1-13 a method or a process, claims 14-19 a device or apparatus and claim 20 a non-transitory computer readable media).
Step 2A – Prong 1: Judicial Exception Recited?
The claim 1 recites the limitations of accessing an application, generating an application agent, receiving natural-language input, processing it with LLMs, determining intent and causing an action based on that intent. These operations can be characterized as abstract idea “mental processes” (interpreting language, determining intent, and information processing). The claim also recites the advanced models like LLMs that are used to perform the mental processes. However, using the large language model is applying it and is not significantly more than a mental process per Recentive Analytics V. Fox Broadcasting Corp. (134 F.4th 1205, 2025 U.S.P.Q.2d 628). Thus, the claim recite abstract idea under Step 2A, Prong 1.
Step 2A – Prong 2: integrated into a practical application?
The claim 1 recites limitations or elements “application agent, interface withing the application and device performs an action” are recited at a high level of generality, wherein the application agent is described only functionally (no architecture or technical mechanism), the interface is generic computer component and the device action is result-oriented such as “perform an action output”. There is no recitation of specific technological improvement and no constraint on how LLMs are implemented or integrated. Therefore, the claim does not integrate the abstract idea into a practical application.
Step 2B: The claim recites potential additional elements such as one or more processors, application agent, interface, LLMs and device action. However, these recited as generic components “processor”, “device”, “interface” that are well-understood, routine and conventional and therefor do not provide an inventive concept (see MPEP 2106.05(d)(II)). The claim does not integrate the abstract idea into a practical application because the additional elements (processor, device, interface) merely implement the abstract idea using generic computer technology. Furthermore, the claim does not include additional elements that amount to significantly more than the judicial exception.
The claim does not include additional elements sufficient to amount to significantly more than the judicial exception, nor does it recite and inventive concept. Although the claim recites LLM models. However, there is no specific architecture, training method, or technical improvement. There is nothing here appears to improve computer performance, solve a specific technical problem in networking, storage, and introduce a novel data structure or algorithm. Instead, it is mere instructions to apply a judicial exception, it cannot integrate a judicial exception into a practical application at step 2A or provide an inventive concept in step 2B. Accordingly, these recitations do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to the abstract idea.
Dependent claim 2 recites “input prompt is generated at least in part by the one or more LLMs” abstract idea under step 2A(ii). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 3 recites “generating action output, wherein the second output is provided through the application agent” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 4 recites “accessing a second application and generating a second application agent” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 5 recites “determining one or more limitations of the action” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 6 recites “accessing the one or more LLMs through an application programming interface (API) of the application” abstract idea under step 2A(ii). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 7 recites “the action output performs at least one functionality of the application” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 8 recites “wherein the action output comprises at least one functionality of at least one outside application, the outside application being different than the application in which the application agent is instantiated” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 9 recites “wherein the input prompt is generated at least in part by the application agent” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 10 recites “determining a user intent, wherein the input prompt is based on the user intent” abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 11 recites “receiving, by the one or more LLMs, a plurality of training input prompts; generating, by the one or more LLMs, a plurality of training action outputs, each of the plurality of training action outputs associated with a corresponding one of the plurality of training input prompts” abstract idea under step 2A(ii) and “comparing each of the plurality of training action outputs with a threshold value; and selecting, based on the comparison of each of the plurality of training action outputs with the threshold value, one of the plurality of training input prompts as the optimized input prompt “abstract idea under step 2A(i). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 12 recites “causing the device to perform the action output comprises using a functionality of one or more applications accessible to the device” abstract idea under step 2A(ii). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Dependent claim 13 recites “wherein the action output is generated at least in part by the one or more LLMs” abstract idea under step 2A(ii). Therefore, the claimed elements fail to integrate the judicial exception into a practical application.
Claim 14 and 20 are rejected due to the similar analysis of claim 1. Claims 15-19 are similar analysis of claims 2-13 and do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element in claims 15-19 represent a further mental process step. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer component, then it falls within the “mental processes” group of abstract ideas. Each additional step is considered an abstract idea (mental process step) and does not integrate the judicial exception into a practical application. An additional abstract idea (mental process step) is not sufficient to amount to significantly more than the judicial exception. Therefore, claims 1-20 are not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-7 and 9-21 are rejected under 35 U.S.C. 103 as being unpatentable over Salomons et al. (US 20250278287 A1) in view of Visoky et al. (US 20250291327 A1).
Regarding claim 1, similar claim 14 and claim 20, Salomons discloses a method comprising:
accessing, by one or more processors (Fig.1, Salomons, computing device includes processor), an application running on a device (¶[0032] and [0034], Salomons, i.e., computing device accessing the software application via a web browser or dedicated mobile app);
generating, by the one or more processors and based on one or more parameters of the application (¶[0026]-[0027], Salomons), an application agent (¶[0026] and [0033]-[0034], Salomons), wherein the application agent is instantiated within the application, the instantiation comprising an interface within the application (¶[0033]-[0034], Salomons, i.e., generates a set of user interface actions, wherein, user interface actions refer to steps that can be programmatically performed with respect to software application “applicant agent”);
receiving, by the one or more processors via the application agent, an input prompt, the input prompt comprising a plurality of words in a natural-language format (¶[0033]-[0034], Salomons, i.e., receiving input as natural language);
providing, by the one or more processors, the input prompt as an input for one or more large language models (¶[0033]-[0034] and [0087]-[0088], Salomons, i.e., inputting the LLM prompt into an LLM);
receiving, by the one or more processors, an inference output of the one or more LLMs, the inference output indicative of an intent of the input prompt (¶[0087]-[0088], Salomons, i.e., the LLM will return one or more UI actions that are responsive to the input prompt); and
causing, by the one or more processors and based on the intent of the input prompt, the device to perform an action output (¶[0087]-[0088], [0090] and [0098], Salomons, i.e., returning UI actions output).
To clarify the language of “generating an application agent, wherein the application agent is instantiated within the application,” although as stated above Salomons discloses generating, by the one or more processors and based on one or more parameters of the application (¶[0026]-[0027], Salomons), an application agent (¶[0026] and [0033]-[0034], Salomons), wherein the application agent is instantiated within the application, the instantiation comprising an interface within the application (¶[0033]-[0034], Salomons).
However, Visoky discloses generating an application agent (¶[0082] and [0084]-[0085], Visoky)3, wherein the application agent is instantiated within the application (Figs.6-7 and ¶[0084]-[0085], Visoky, i.e., LLM-based OT network assistant within an enterprise corresponding the claimed application agent,) wherein the application agent is a system-level large language model service of an operating system of the device and is instantiated by the operating system within an interface of the application (Fig. 7 and ¶[0084]-[0085], Visoky); wherein the action output comprises a first executable instruction to be executed by the application and a second executable instruction to be executed by another application accessible by the operating system (Fig. 7 and ¶[0084]-[0085], Visoky).
It would have been obvious to a person having ordinary skill in the art before the effective filing date, to substitute the artificial intelligent agent taught by Visoky for the artificial intelligence agent of Salomons to enhance interaction with the virtual environment of Salomons. In view of the teaching of Salomons and Visoky, one of ordinary skill in the art would have been motivated to make such a substitution because both refences teach methods for managing artificial intelligence agents and applications. The substitution would merely involve using one known method in place of another to achieve plurality of outputs based on the use of AI across different domains.
Regarding claim 2 and similar claim 15, Salomons/Visoky combination discloses wherein the input prompt is generated at least in part by the one or more LLMs (¶[0087]-[0088], Salomons).
Regarding claim 3 and similar claim 16, Salomons/Visoky combination discloses generating a second output based on the action output, wherein the second output is provided through the application agent (¶[0105]-[0106], Salomons).
Regarding claim 4 and similar claim 17, Salomons/Visoky combination discloses accessing a second application; and generating, by the one or more processors and based on one or more parameters of the second application, a second application agent, wherein: the second application agent is instantiated within the second application, the instantiation comprising an interface within the second application; and the interface within the second application includes the application agent (¶[0058],[0087]-[0088] and [0098], Salomons).
Regarding claim 5 and similar claim 18, Salomons/Visoky combination discloses determining one or more limitations of the action output, the one or more limitations based on: a plurality of available functions of the application (¶[0058],[0087]-[0088] and [0098], Salomons); and a permission set of the application comprising a list of allowed resources of the device available for access by the application (¶[0054],[0087]-[0088] and [0098], Salomons, i.e., administrator define UI actions for a given prompt “permission set…”).
Regarding claim 6 and similar claim 19, Salomons/Visoky combination discloses accessing the one or more LLMs through an application programming interface of the application (¶[0058] and [0087]-[0088], Salomons); and limiting a functionality of the one or more LLMs based on one or more permissions of the application (¶[0058] and [0087]-[0088], Salomons).
Regarding claim 7, Salomons/Visoky combination discloses wherein the action output performs at least one functionality of the application (¶[0058] and [0105]-[0106], Salomons).
Regarding claim 9, Salomons/Visoky combination discloses wherein the input prompt is generated at least in part by the application agent (¶[0087]-[0088], Salomons).
Regarding claim 10, Salomons/Visoky combination discloses determining a user intent, wherein the input prompt is based on the user intent (¶[0033], [0041]and [0087]-[0088], Salomons).
Regarding claim 11, Salomons/Visoky combination discloses wherein the input prompt is a product of prompt engineering, the prompt engineering comprising generation of an optimized input prompt based on: receiving, by the one or more LLMs, a plurality of training input prompts (¶[0087]-[0088], Salomons); generating, by the one or more LLMs, a plurality of training action outputs (¶[0087]-[0088], [0090] and [0098], Salomons), each of the plurality of training action outputs associated with a corresponding one of the plurality of training input prompts (¶[0087]-[0088], [0090] and [0098], Salomons); comparing each of the plurality of training action outputs with a threshold value (¶[0085], Salomons); and selecting, based on the comparison of each of the plurality of training action outputs with the threshold value, one of the plurality of training input prompts as the optimized input prompt (¶[0085] and [0087]-[0088], Salomons).
Regarding claim 12, Salomons/Visoky combination discloses wherein causing the device to perform the action output comprises using a functionality of one or more applications accessible to the device (¶[0058] and [0105]-[0106], Salomons).
Regarding claim 13, Salomons/Visoky combination discloses wherein the action output is generated at least in part by the one or more LLMs (¶[0087]-[0088], Salomons).
Regarding claim 21, Salomons/Visoky combination discloses wherein the input prompt is generated at least in part by the one or more LLMs (¶[0087]-[0088], Salomons).
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 HANH B THAI whose telephone number is (571)272-4029. The examiner can normally be reached Mon-Friday 7-4:30.
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, Tony Mahmoudi can be reached at 571-272-4078. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
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.
/HANH B THAI/Primary Examiner, Art Unit 2163 October 1, 2026
