Prosecution Insights
Last updated: May 29, 2026
Application No. 18/633,227

TOOLS FOR LARGE LANGUAGE MODEL AGENTS

Final Rejection §101§112
Filed
Apr 11, 2024
Examiner
ALLADIN, AMBREEN A
Art Unit
3691
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Wells Fargo Bank N A
OA Round
2 (Final)
24%
Grant Probability
At Risk
3-4
OA Rounds
1y 6m
Est. Remaining
50%
With Interview

Examiner Intelligence

Grants only 24% of cases
24%
Career Allowance Rate
79 granted / 333 resolved
-28.3% vs TC avg
Strong +26% interview lift
Without
With
+25.8%
Interview Lift
resolved cases with interview
Typical timeline
3y 7m
Avg Prosecution
31 currently pending
Career history
368
Total Applications
across all art units

Statute-Specific Performance

§101
21.9%
-18.1% vs TC avg
§103
67.3%
+27.3% vs TC avg
§102
3.0%
-37.0% vs TC avg
§112
6.7%
-33.3% vs TC avg
Black line = Tech Center average estimate • Based on career data from 333 resolved cases

Office Action

§101 §112
DETAILED ACTION Status of the Claims 1. This action is in response to the Request for Reconsideration dated September 2, 2025. 2. Claims 1-6, 8, 11-16 and 18 are currently pending and have been examined. 3. Claims 1, 4, 8, 11, 14 and 18 have been amended. 4. Claims 7, 9-10, 17 and 19-20 have been canceled. Notice of Pre-AIA or AIA Status 5. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Claim Interpretation – Broadest Reasonable Interpretation 6. In determining patentability of an invention over the prior art, all claim limitations have been considered and interpreted using the “broadest reasonable interpretation consistent with the specification during the examination of a patent application since the applicant may then amend his claims.” See In re Prater and Wei, 162 USPQ 541, 550 (CCPA 1969); MPEP § 2111. Applicant always has the opportunity to amend the claims during prosecution, and broad interpretation by the examiner reduces the possibility that the claim, once issued, will be interpreted more broadly than is justified. See In re Prater, 162 USPQ 541, 550-51 (CCPA 1969); MPEP § 2111. Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 26 USPQ2d 1057 (Fed. Cir. 1993). See also MPEP 2173.05(q) All claim limitations have been considered. Additionally, all words in the claims have been considered in judging the patentability of the claims against the prior art. See MPEP 2143.03. Claim limitations that contain statement(s) such as “if, may, might, can, could”, are treated as containing optional language. As matter of linguistic precision, optional claim elements do not narrow claim limitations, since they can always be omitted. Claim limitations that contain statement(s) such as “wherein, whereby”, that fail to further define the steps or acts to be performed in method claims or the discrete physical structure required of system claims. Similarly, a method step exercised or triggered upon the satisfaction of a condition, where there remains the possibility that the condition was not satisfied under the broadest reasonable interpretation, is an optional claim limitation. see MPEP § 2103(I)(C); In re Johnson, 77 USPQ2d 1788 (Fed Cir 2006). As the Applicant does not address what happens should the optional claim limitations fail, Examiner assumes that nothing happens (i.e. the method stops). An alternate interpretation is that merely the claim limitations based upon the condition are not triggered or performed. The subject matter of a properly construed claim is defined by the terms that limit its scope. It is this subject matter that must be examined. As a general matter, grammar and the plain meaning of terms as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. see MPEP §2013(I)(C). Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. see MPEP §2013(I)(C). Claim scope is not limited by claim language that suggests or makes optional but does not require steps to be performed, or by claim language that does not limit a claim to a particular structure. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298 (Fed. Cir. 2009). See MPEP 2111.04, 2143.03. Language in a method or system claim that states only the intended use or intended result, but does not result in a manipulative difference in the steps of the method claim nor a structural difference between the system claim and the prior art, fails to distinguish the claims from the prior art. In other words, if the prior art structure is capable of performing the intended use, then it meets the claim. The following types of claim language may raise a question as to its limiting effect (this list is not exhaustive): Statements of intended use or field of use, including statements of purpose or intended use in the preamble (MPEP 2111.02); Clauses such as “adapted to”, “adapted for”, “wherein”, and “whereby” (MPEP 2111.04) Contingent limitations (MPEP 2111.04) Printed matter (MPEP 2111.05) and Functional language associated with a claim term (MPEP 2181) Examiner notes that during examination, “claims … are to be given their broadest reasonable interpretation consistent with the specification, and … claim language should be read in light of the specification as it would be interpreted by one of ordinary skill in the art.” See In re Bond, 15 USPQ 1566, 1568 (Fed. Cir. 1990), citing In re Sneed, 218 USPQ 385, 388 (Fed. Cir. 1983). However, "in examining the specification for proper context, [the examiner] will not at any time import limitations from the specification into the claims". See CollegeNet, Inc. v. ApplyYourself, Inc., 75 USPQ2d 1733, 1738 (Fed. Cir. 2005). Construing claims broadly during prosecution is not unfair to the applicant, because the applicant has the opportunity to amend the claims to obtain more precise claim coverage. See In re Yamamoto, 222 USPQ 934, 936 (Fed. Cir. 1984), citing In re Prater, 162 USPQ 541, 550 (CCPA 1969). As such, while all claim limitations have been considered and all words in the claims have been considered in judging the patentability of the claimed invention, the following language is interpreted as not further limiting the scope of the claimed invention. The preamble of the instant claim 1 recites "[a] computer system for providing one or more tools for large language model agents, the computer system comprising:” The preamble of the instant claim 11 recites “A method for providing one or more tools for large language model agents, the method comprising:” In general, a preamble limits the invention if it recites essential structure or steps, or if it is "necessary to give life, meaning, and vitality" to the claims. Pitney Bowes, Inc. v. Hewlett-Packard Co. 51 USPQ2d 1161 (Fed. Cir. 1999), Catalina Marketing International Inc. v. Coolsavings.com Inc., 62 USPQ2d 1781 (Fed. Cir. 2002). Conversely, where a patentee defines a structurally complete invention in the claim body and uses the preamble only to state a purpose or an intended use for the invention, the preamble is not a claim limitation given patentable weight. Rowe v. Dror, 42 USPQ2d 1550 (Fed. Cir. 1997); Catalina Marketing International Inc. v. Coolsavings.com Inc., 62 USPQ2d 1781 (Fed. Cir. 2002); Bell Communications Research, Inc. v. Vitalink Communications Corp., 34 USPQ2d 1816 (Fed. Cir. 1995) If a prior art structure is capable of performing the intended use as recited in the preamble, then it meets the claim. See, e.g., In re Schreiber, 128 F.3d 1473, 1477, 44 USPQ2d 1429, 1431 (Fed. Cir. 1997) See MPEP 2111.02 In the instant case, “for providing one or more tools for large language model agents” as recited in the preambles of Claims 1 and 11 only state a purpose and/or the intended use of the invention and accordingly is not being assigned any patentable weight. Similarly in the instant case, the following italicized limitations are expressing the intended result of a process step positively recited and are not given weight: As in Claim 1: provide a description of the one or more tools available for use by the large language model agents in response to a query from the large language model agents through the application programming interface, wherein the description includes a list of the one or more tools in a structured format having parameter names, data types, and usage examples; intercept a request from the large language model agents by injecting additional behavior that is consumed by the large language model agents, wherein the additional behavior requires manual approval; generate a user interface control that details the request and allows for the manual approval before the large language model agents are allowed to proceed with the request; execute, upon receipt of the manual approval, the one or more tools upon receipt of a request from the large language model agents through the application programming interface, wherein the request conforms to the structured format; As in Claim 11: providing an application programming interface to interface with the large language model agents; providing a description of the one or more tools available for use by the large language model agents in response to a query from the large language model agents through the application programming interface, wherein the description includes a list of the one or more tools in a structured format having parameter names, data types, and usage examples; intercepting a request from the large language model agents by injecting additional behavior that is consumed by the large language model agents, wherein the additional behavior requires manual approval; generating a user interface control that details the request and allows for the manual approval before the large language model agents are allowed to proceed with the request; executing, upon receipt of the manual approval, the one or more tools upon receipt of a request from the large language model agents through the application programming interface, wherein the request conforms to the structured format; As in Claims 5 and 15: wherein the one or more tools are related to financial accounts. As in Claims 6 and 16: wherein the one or more tools include a tool to obtain balances for the financial accounts. As in Claims 8 and 18: wherein the application programming interface requires the user to be authenticated before providing the information to the large language model agents. Additional behavior: Applicant uses the term “additional behavior” in the independent claims. Applicant’s specification discloses the following: “In this example, the approval engine 304 intercepts all key input and output calls by the LLM-based agent engine 302 and injects additional behavior (“middleware”) or wholly replaces functionality with appropriate error messages that are then consumed by the LLM-based agent engine 302.” (See Applicant Spec para 44) “For example, assume the example above where the customer wishes to align the credit card payment due date with the mortgage payment due date. The LLM-based agent engine 302 accesses the tools on the server device 112 to request the payment due dates and calculate the change to the credit card payment due date. However, before the LLM-based agent engine 302 is allowed to request the modification of the credit card payment due date, the approval engine 304 intercepts the request by the LLM-based agent engine 302 and requires approval by the customer.” (See Applicant Spec para 45) “In one example, this may include generation of a “pop-up” approval dialog (or other control mechanism) listing details about the potential change to the credit card payment due date: Your agent proposes to change your credit card payment due date to January 1 to align with your mortgage payment due date. Do you wish to make this change?” (See Applicant Spec para 46) “The customer can then approve or disapprove of the change before the LLM-based agent engine 302 is allowed to proceed with then [sic] change. If approved by the customer, the LLM-based agent engine 302 continues to use the tools provided by the server device 112 to effectuate the change. If not approved by the customer, the LLM-based agent engine 302 generates an error indicating that the change cannot be made.” (See Applicant Spec para 47) The ”additional behavior” is thus being interpreted as affirming or disapproving a change as noted by the specification. Claim Rejections - 35 USC § 112 The following is a quotation of the first paragraph of 35 U.S.C. 112(a): (a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112: The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention. 7. Claims 1-6, 8, 11-16 and 18 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. The amendment filed September 2, 2025 is objected to under 35 U.S.C. 132(a) because it introduces new matter into the disclosure. 35 U.S.C. 132(a) states that no amendment shall introduce new matter into the disclosure of the invention. The added material which is not supported by the original disclosure is as follows: As in Claim 1 and substantially similarly in Claim 11: provide a description of the one or more tools available for use by the large language model agents, in response to a query from the large language model agents through the application programming interface, wherein the description includes a list of the one or more tools in a structured format having parameter names, data types, and usage examples; execute, upon receipt of the manual approval, the one or more tools upon receipt of a request from the large language model agents through the application programming interface, wherein the request conforms to the structured format; intercept a request from the large language model agents by injecting additional behavior that is consumed by the large language model agents, wherein the additional behavior requires manual approval; The first two limitations are broader than the specification discloses. There is no reference to parameter names, data types and usage examples in a structured format. Rather, it appears that Applicant has attempted to claim a “structured format” that is alleging to be what is provided. There is no disclosure of a structured format, parameter names, data types and usage examples per se. There is no figure that discloses alleged format with parameter names, data types and usage examples. Applicant’s specification discloses that the “…client device 102 can access a series of tools available from the server device 112” and in one example “…the client device 102 can query the tools engine 204 of the server device 112 to request a list of the tools available to the client device 102…” (See Applicant Spec para 28) The specification then describes the computer code, while further disclosing that the client device is provided a List of Accounts tool that provides a list of all accounts and an Account Balance Tool that provides a present or past balance for a financial account. (See Applicant Spec para 29) The specification continues, indicating that the client device can use the information about the tools available from the server device to request details about one or more of the desired tools. (See Applicant Spec para 30) “For instance, the client device 102 can request additional information about the AccountBalanceTool from the server device 112.” (See Applicant Spec para 30) The tool engine 204 then provides additional details about the AccountBalanceTool, including the fields associated therewith, including an “account_name” field that is the account name (e.g., “Checking Account”) and a “context” field that allows for the definition of a point in time. (See Applicant Spec paras 30-31) While the computer coding presented in the specification, the terms used to describe the coding are broader than the specification discloses and also appear to be not what the system would be displaying to a user when providing a description of the tools to a user to interact with. Further, the description list itself does not provide the other categories of information, rather the specification indicates that a client would need to further interact with the requested list in order to arrive at the option to request details about one or more of the desired tools. (See Applicant Spec para 30) As to the “intercept” limitation, as claimed it appears to the be the approval engine of the customer’s device that is programmed to set limits on the processes initiated by the LLM-based agent. (See Applicant Spec paras 42-43) The specification indicates use of an approval engine and a LLM-based agent engine which appear to be separately housed elements operating on separate devices in order to have the approval engine intercept a request from the LLM model agents. The claim limitation does not appear to function in the manner disclosed in the specification or without the systemization to perform in the manner claimed. Examiner suggests using the terminology of the specification, while also limiting the claim to present the invention from either the view of the user utilizing the interface via a computer system or the back end system instead of attempting to recite both front end and back end functionality without distinguishing the steps and systemization is utilized. Here, Applicant has attempted to claim some steps from the description of Figure 2 related to the server device and other steps related to Figure 3 which is related to the client device together without indicating the systemization distinctions from the server versus a client device between the steps. Dependent Claims 2-6, 8, 12-16 and 18 are further rejected as based on a rejected base claim. Applicant is required to cancel the new matter in the reply to this Office Action. 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. 8. Claims 1-6, 8, 11-16 and 18 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more. ANALYSIS: STEP 1: Does the claimed invention fall within one of the four statutory categories of invention (process, machine, manufacture or composition matter? Yes and No. Claim 1 recites a system claim. Claim 11 recites a method claim. Currently, the method has a separate rejection as being non-statutory, however Examiner assumes that Applicant will rectify the claims to properly claim the invention as within statutory categories. STEP 2A: Prong One: Does the Claim Recite A Judicial Exception (An Abstract Idea, Law of Nature or Natural Phenomenon)? (If Yes, Proceed to Prong Two, If No, the claim is not directed to a judicial exception and qualifies as subject matter patent eligible material) Claim 1 recites the abstract idea of providing tools in response to requests. The idea is described by the following limitations: authenticate a user; provide a description of the one or more tools available for use…wherein the description includes a list of the one or more tools in a structured format having parameter names, data types and usage examples; wherein the additional behavior requires manual approval; generate the request and allows for the manual approval before allowing the request to proceed; execute, upon receipt of the manual approval, the one or more tools upon receipt of a request wherein the request conforms to the structured format; provide information in response to the request Claim 11 recites the abstract idea of providing tools in response to requests. The idea is described by the following limitations: authenticating a user; providing a description of the one or more tools available for use…wherein the description includes a list of the one or more tools in a structure format having parameter names, data types and usage examples; wherein the additional behavior requires manual approval; generate the request and allows for the manual approval before allowing the request to proceed; executing, upon receipt of the manual approval, the one or more tools upon receipt of a request wherein the request conforms to the structured format; providing information in response to the request The abstract ideas describe mental processes and certain methods of organizing human activity. As to the mental processes, the steps describe concepts performed in the human mind including an observation, evaluation, judgment and/or opinion as noted above. The steps are performing a mental process in a computer environment that recites limitations receiving, observing and evaluating information and with the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being practically performed by a human mentally. As to certain methods of organizing human activity, the steps involve managing personal behavior or relationships or interactions between people (including following rules or instructions) (Step 2A – Prong 1: Yes, the claims are abstract) Prong Two: Does the Claim Recite Additional Elements That Integrate The Judicial Exception Into A Practical Application of the Exception? (If Yes, the claim is not directed to a judicial exception and qualifies as subject matter patent eligible material. If No, Proceed to Step 2B) The claims do not include additional elements that integrate the judicial exception into a practical application of the exception because the claims do not provide improvements to another technology or technical field, improvements to the functioning of the computer itself, are not applying or using a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition, are not applying the judicial exception with, or by use of a particular machine, are not effecting a transformation or reduction of a particular article to a different state or thing, and are not applying the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment. Claim 1 recites one or more processors, non-transitory computer-readable storage media encoding instructions, an API to interface with large language model agents; large language model agents, intercept a request from the large language model agents by injecting additional behavior that is consumed by large language model agents, and a user interface control. Claim 11 recites an API to interface with large language model agents, large language model agents, intercepting a request from the large language model agents by injecting additional behavior that is consumed by large language model agents, and a user interface control. Further, the method outlined in Claim 11 does not sufficiently tie the method steps to a particular machine within the body of the claim. As such, the recitations are further failing to integrate the judicial exception into a practical application on this basis. In particular, the claims only recite one or more processors, non-transitory computer-readable storage media encoding instructions, an API to interface with large language model agents, large language model agents, intercepting a request from the large language model agents by injecting additional behavior that is consumed by large language model agents, and a user interface control which are recited at a high level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts to no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, Claims 1 and 11 are directed to an abstract idea without a practical application. (Step 2A – Prong 2: No, the additional claimed elements are not integrated into a practical application) STEP 2B: If there is an exception, determine if the claim as a whole recites significantly more than the judicial exception itself. The courts have recognized the following computer functions as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity: i) receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)); ii) performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values); Bancorp Services v. Sun Life, 687 F.3d 1266, 1278, 103 USPQ2d 1425, 1433 (Fed. Cir. 2012) ("The computer required by some of Bancorp’s claims is employed only for its most basic function, the performance of repetitive calculations, and as such does not impose meaningful limits on the scope of those claims."); iii) electronic recordkeeping, Alice Corp., 134 S. Ct. at 2359, 110 USPQ2d at 1984 (creating and maintaining "shadow accounts"); Ultramercial, 772 F.3d at 716, 112 USPQ2d at 1755 (updating an activity log); iv) storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93; v) electronically scanning or extracting data from a physical document, Content Extraction and Transmission, LLC v. Wells Fargo Bank, 776 F.3d 1343, 1348, 113 USPQ2d 1354, 1358 (Fed. Cir. 2014) (optical character recognition); and vi) a web browser’s back and forward button functionality, Internet Patent Corp. v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1418 (Fed. Cir. 2015). (MPEP §2106.05(d)(II)) This listing is not meant to imply that all computer functions are well‐understood, routine, conventional activities, or that a claim reciting a generic computer component performing a generic computer function is necessarily ineligible. Courts have held computer‐implemented processes not to be significantly more than an abstract idea (and thus ineligible) where the claim as a whole amounts to nothing more than generic computer functions merely used to implement an abstract idea, such as an idea that could be done by a human analog (i.e., by hand or by merely thinking). On the other hand, courts have held computer-implemented processes to be significantly more than an abstract idea (and thus eligible), where generic computer components are able in combination to perform functions that are not merely generic. (MPEP §2106.05(d)(II) – emphasis added) Below are examples of other types of activity that the courts have found to be well-understood, routine, conventional activity when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity: recording a customer’s order, Apple, Inc. v. Ameranth, Inc., 842 F.3d 1229, 1244, 120 USPQ2d 1844, 1856 (Fed. Cir. 2016); shuffling and dealing a standard deck of cards, In re Smith, 815 F.3d 816, 819, 118 USPQ2d 1245, 1247 (Fed. Cir. 2016); restricting public access to media by requiring a consumer to view an advertisement, Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 716-17, 112 USPQ2d 1750, 1755-56 (Fed. Cir. 2014); identifying undeliverable mail items, decoding data on those mail items, and creating output data, Return Mail, Inc. v. U.S. Postal Service, -- F.3d --, -- USPQ2d --, slip op. at 32 (Fed. Cir. August 28, 2017); presenting offers and gathering statistics, OIP Techs., 788 F.3d at 1362-63, 115 USPQ2d at 1092-93; determining an estimated outcome and setting a price, OIP Techs., 788 F.3d at 1362-63, 115 USPQ2d at 1092-93; and arranging a hierarchy of groups, sorting information, eliminating less restrictive pricing information and determining the price, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1331, 115 USPQ2d 1681, 1699 (Fed. Cir. 2015) (MPEP 2106.05(d)) Here, the steps are receiving or transmitting data over a network (Symantec, TLI, OIP Techs – MPEP 2106.05(d)(II); storing and retrieving information in memory (Versata, OIP Techs – MPEP 2106.05(d)(II) and electronically scanning or extracting data (Content Extraction – MPEP 2106.05(d)(II)– all of which have been recognized by the courts as well-understood, routine and conventional functions. The claims are directed to an abstract idea with additional generic computer elements that do not add meaningful limitations to the abstract idea because they require no more than a generic computer to perform generic computer functions that are well-understood, routine, and conventional activities previously known in the industry. For the next step of the analysis, it must be determined whether the limitations present in the claims represent a patent-eligible application of the abstract idea. A claim directed to a judicial exception must be analyzed to determine whether the elements of the claim, considered both individually and as an ordered combination are sufficient to ensure that the claim as a whole amounts to significantly more than the exception itself. For the role of a computer in a computer implemented invention to be deemed meaningful in the context of this analysis, it must involve more than performance of “well-understood, routine, [and] conventional activities previously known to the industry.” Further, “the mere recitation of a generic computer cannot transform a patent ineligible abstract idea into a patent-eligible invention.” Applicant’s specification discloses the following: “Figure 1 schematically shows aspects of one example system 100 programmed to provide LLM agents. In this example, the system 100 can be a computing environment that includes a plurality of client and server devices. In this instance, the system 100 includes client devices 102, 104, a server device 112, and a database 114. The client devices 102, 104 and communicate with the server device 112 through a network 110 and associated application programming interface (API) 106 to accomplish the functionality described herein.” (See Applicant Specification para 11) “Each of the devices may be implemented as one or more computing devices with at least one processor and memory. Example computing devices include a mobile computer, a desktop computer, a server computer, or other computing device or devices such as a server farm or cloud computing used to generate or receive data.” (See Applicant Specification para 12) “As illustrated in the embodiment of Figure 4, example server device 112 which provides the functionality described herein, can include at least one central processing unit (“CPU”) 402, a system memory 408, and a system bus 422 that couples the system memory 408 to the CPU 402. The system memory 408 includes a random-access memory (“RAM”) for 10 and a read-only memory (“ROM”) 412. A basic input/output system containing the basic routines that help transfer information between elements within the server device 112, such as during startup, is stored in the ROM 412. The server device 112 further includes a mass storage device 414. The mass storage device 414 can store software instructions and data. A central processing unit, system memory, and mass storage device similar to that shown can also be included in the other computing devices disclosed herein.” (See Applicant Specification para 51) “The mass storage device 414 is connected to the CPU 402 through a mass storage controller (not shown) connected to the system bus 422. The mass storage device 414 and its associated computer-readable data storage media provide non-volatile, non-transitory storage for the server device 112. Although the description of computer-readable data storage media contained herein refers to a mass storage device, such as a hard disk or a solid-state disk, it should be appreciated by those skilled in the art that computer-readable data storage media can be any available non-transitory, physical device, or article of manufacture from which the central display station can read data and/or instructions.” (See Applicant Specification para 52) “Computer-readable data storage media include volatile and non-volatile, removable, and non-removable media implemented in any method or technology for storage of information such as computer-readable software instructions, data structures, program modules, or other data. Example types of computer-readable data storage media include, but are not limited to, RAM, ROM, EPROM, EEPROM, flash memory, or other solid-state memory technology, CD-ROMs, digital versatile discs (“DVDs”), other optical storage media, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the server device 112.” (See Applicant Specification para 53) “According to various embodiments of the invention, the server device 112 may operate in a networked environment using logical connections to remote network devices through network 110, such as a wireless network, the Internet, or another type of network. The server device 112 may connect to network 110 through a network interface unit 404 connected to the system bus 422. It should be appreciated that the network interface unit 404 may also be utilized to connect to other types of networks and remote computing systems. The server device 112 also includes an input/output controller 406 for receiving and processing input from a number of other devices, including a touch user interface display screen or another type of input device. Similarly, the input/output controller 406 may provide output to a touch user interface display screen or other output devices.” (See Applicant Specification para 54) Generic computer components recited as performing generic computer functions that are well-understood, routine and conventional activities amount to no more than implementing the abstract idea with a computerized system. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. The collective functions appear to be implemented using conventional computer systemization. The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Upon reconsideration of the indicia noted under Step 2A in concert with the Step 2B considerations, the additional claim element(s) amounts to no more than mere instructions to apply the exception using generic computer components. The same analysis applies in Step 2B, i.e., mere instructions to apply an exception using a generic computer component cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B. The claim does not provide an inventive concept significantly more than the abstract idea. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The independent claims 1 and 11 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more) Dependent Claims 2-6, 8, 12-16 and 18 further define the abstract idea that is presented in the respective independent Claims 1 and 11 and are further grouped as certain methods of organizing human activity and are abstract for the same reasons and basis as presented above. Dependent Claims 2 and 12 provide further details as to the user being authenticated by a third party. This still describes mental processes and certain methods of organizing human activity. Dependent Claims 3 and 13 provide further details as to the description of the one or more tools noting that the description includes a name and a user for each of the tools. This still describes mental processes and certain methods of organizing human activity. Dependent Claims 4 and 14 further recite wherein the request [is] generated through a prompt executed by the large language model agents. The prompt is described at a high level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts to mere instructions to apply the exception using a generic computer component. This step is still describing mental processes and certain methods of organizing human activity. Dependent Claims 5 and 15 further recite wherein the one or more tools are related to financial accounts. This still describes mental processes and certain methods of organizing human activity. Dependent Claims 6 and 16 further recite wherein the one or more tools include a tool to obtain balances for the financial accounts. This still describes mental processes and certain methods of organizing human activity. Dependent Claims 8 and 18 further recite wherein the application programming interface requires the user to be authenticated before providing the information to the large language model agents. The authentication is described at a high level of generality (i.e., as a generic processor performing generic computer functions) such that it amounts to mere instructions to apply the exception using a generic computer component. This step is still describing mental processes and certain methods of organizing human activity. No further additional hardware components other than those found in the respective independent claims is recited, thus it is presumed that the claim is further utilizing the same generic systemization as presented above. The dependent claims do not include any additional elements that integrate the abstract idea into a practical application of the exception or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the dependent claims are also directed to an abstract idea. Thus, Claims 1-6, 8, 11-16 and 18 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter. Regarding Claims 11-16 and 18, Examiner notes that the method of Claims 11-16 and 18 would also have been rejected under the earlier §101 standards based upon In re Bilski, which have been superseded by the current §101 standards based upon the Alice-Mayo test. Specifically, Claim 11 contains an insufficient recitation of a machine or transformation as the involvement of the machine. As recited, the machine is merely nominally, insignificantly or tangentially related to the performance of the steps. Examiner notes that there is no explicit reference to a machine in Independent Claim 11. There is no direct tie between a machine and the limitations of the independent claim, nor to the subsequent dependent claims. Examiner is only noting this as §101 under the Alice-Mayo test is considered a substantially higher bar than under In re Bilski. Examiner suggests Applicant incorporate language into the body of the claim reciting the machine elements performing the recited process. Relevant Prior Art of Record Kolchin (US PG Pub 2024/0202687) – discloses a method for preventing and analyzing fraud in financial services that incudes the steps of continuously collecting multimodal data from a plurality of independent channels, including visual, auditory, and tactile data; analyzing the multimodal data using a Large Language Model (LLM) based operating system and fraud prevention modules to detect and prevent fraudulent activities; integrating third-party data from external sources to enhance contextual understanding and improve fraud detection accuracy; and communicating with users through any of the modalities to address potential fraud concerns or obtain additional verification. Bhasin (US PG Pub. 2025/0124275) – discloses methods and systems for determining suitable products and operating parameters for performing a task. (See Bhasin Abstract) The method includes generating and transmitting, via large language machine learning model, a query response message based on product-specific data, entity-specific data, and predefined rules such that the query response message indicates task-specific information that includes a list of the one or more suitable products and operating parameters corresponding to each suitable product for performing the task. (See Bhasin Abstract) Hockey et al. (US PG Pub. 2019/0318122) – discloses a system and method for secure permissioning of access to user accounts, functions as a technology-driven solution for securing and automating the process of reporting financial information. (See Hockey para 48) The system and method may be implemented in connection with a financial institution system such as a digital platform of a bank, a payment service, a credit card system, an investment system, and/or any type of financial institution. (See Hockey para 56) The system and method is preferably implemented within multitenant computing systems wherein multiple users and entities are served by shared computing resources and infrastructures. (See Hockey para 57) Some variations may relate to systems and techniques for securely and efficiently obtaining user account data via instantiation of virtualized or simulated instances of first-party software applications, for example generation of proxy, virtualized, or simulated instances of software applications that are configured to interface with external systems via public or non-public (e.g proprietary) application programming interfaces (APIs). (See Hockey para 68) Response to Arguments Applicant's arguments filed September 2, 2025 have been fully considered as further detailed below: Regarding the Claim Objections: Applicant is thanked for the corrections made to Claims 4 and 14 to address the claim objections of record. (See Applicant’s Arguments dated 09/02/2025, page 7) The claim objections have accordingly been withdrawn. Regarding the 101 Rejections: Applicant traverse the rejection. (Id. at page 7) While Examiner appreciates Applicant’s efforts in rolling up some limitations from former dependent claims 7, 9 and 10 and adding material to the recitations, there is a gap between the recitations and the inventive concept. As currently argued, the technical problem is that of hallucinations, however the solution is solved in the claims by a business solution, namely manual approval. (Id. at pages 7-8) The mental processes are as a result of the claims using generic systemization being used to perform processes that were ordinarily been conducted by financial services personnel or IVR services. There is no indication of creation of novel APIs, LLMs or a specialized algorithm in the specification. This is coupled with the lack of systemization in the claims and the “additional behavior” being equated to manual approval. While Examiner agrees that AI is clearly involved in the envisioned invention and that the claims could be claimed outside of a mental process, at the moment the systemization contours and invocation of manual approval without the systemization and processes being clearly recited does not clearly rule it out. (Id. at page 9) Similarly, as to Applicant’s assertions that the claims being integrated into a practical application or significantly more is disclosed, the issues mentioned under the 112(a) and the lack of proper systemization in claiming the inventive concept prevent Examiner from making such a finding at this time. (Id. at pages 9-10) Regarding the Prior Art: While there is no prior art being applied at this time, Examiner notes that this is in part predicated on limitations that do not have proper support in the specification. (Id. at pages 10-11) Accordingly, this will be reevaluated based on Applicant’s response. 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 AMBREEN A. ALLADIN whose telephone number is (571)270-3533. The examiner can normally be reached Monday - Friday 9-5. 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, Abhishek Vyas can be reached at 571-270-1836. 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. /AMBREEN A. ALLADIN/Primary Examiner, Art Unit 3691 December 20, 2025
Read full office action

Prosecution Timeline

Apr 11, 2024
Application Filed
Jun 03, 2025
Non-Final Rejection mailed — §101, §112
Aug 17, 2025
Interview Requested
Aug 26, 2025
Examiner Interview Summary
Aug 26, 2025
Applicant Interview (Telephonic)
Sep 02, 2025
Response Filed
Dec 23, 2025
Final Rejection mailed — §101, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12614429
LOCATION-BASED ACCOUNT MANAGEMENT AND FRAUD-DETECTION SYSTEM FOR USE WITH MOBILE GAMBLING APPLICATIONS
1y 10m to grant Granted Apr 28, 2026
Patent 12608693
System, Method, and Computer Program Product for a Contactless ATM Experience
3y 4m to grant Granted Apr 21, 2026
Patent 12572977
AUTOMATED AND RELIABLE DETERMINATION OF A FORWARD VALUE ASSOCIATED WITH A FUTURE TIME PERIOD BASED ON OBJECTIVELY DETERMINED EXPECTATIONS RELATED THERETO
3y 8m to grant Granted Mar 10, 2026
Patent 12505417
ALERTING USERS OF A PHYSICAL PICKUP POINT
4y 1m to grant Granted Dec 23, 2025
Patent 12417497
Dynamic Generation of Order Entry Fields on a Trading Interface
3y 5m to grant Granted Sep 16, 2025
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
24%
Grant Probability
50%
With Interview (+25.8%)
3y 7m (~1y 6m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 333 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month