DETAILED ACTION
This action is in response to the reply received 07/08/2026. After consideration of applicant's amendments and/or remarks:
Claims 1-20 rejected under 35 USC § 103.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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 1-4, 8-12, 15-17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Kumar, U.S. PG-Publication No. 2025/0110618 A1 (hereinafter KUMAR), in view of U.S. PG-Publication No. 2025/0110811 A1 (hereinafter MISHCHENKO).
Claim 1
KUMAR discloses a computer-implemented method. ¶ 0020: Automated content and API processing across collaboration platforms.
KUMAR discloses receiving, at the content management system via the content management system plugin integrated within the computing environment of the large language model a function call invoking one of the one or more content-management-system API operations on a content item stored in the content management system. ¶ 0177: Registered plugins access platform content and support model processing. ¶ 0188: A project inquiry plugin queries content associated with a named project.
KUMAR discloses executing, by the content management system, the content-management-system API operation on the content item stored in the content management system in response to the function call from the content management system plugin integrated within the computing environment of the large language model. ¶ 0188: The query extracts content from matching content items.
KUMAR disclose providing, via the content management system plugin, an output of the content-management-system API operation to the computing environment of the large language model. ¶ 0188: Extracted content supplies a prompt transmitted to the generative engine.
KUMAR does not expressly disclose integrating into a computing environment of a large language model, a content management system plugin comprising computer code that exposes, to the computing environment of the large language model, one or more content-management-system API operations executable by a content management system on content items stored in the content management system.
MISHCHENKO discloses integrating, into a computing environment of a large language model, a content management system plugin comprising computer code that exposes, to the computing environment of the large language model, one or more content-management-system API operations executable by a content management system on content items stored in the content management system. ¶ 0048: A generated plugin couples the model to exposed API functionality. ¶ 0063: Model generated function calls become external API requests. ¶ 0066: Function descriptions enable model selections of callable operations.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the CMS API integration of KUMAT to incorporate the generated plugin, API descriptions, and function call translation taught by MISHCHENKO. One of ordinary skill in the art would be motivated to integrate that functionality into KUMAR, with a reasonable expectation of success, in order to reduce integration and maintenance work by describing available operations through a reusable manifest and specification, as taught by MISHCHENKO at ¶ 0067.
Claim 2
MISHCHENKO discloses wherein integrating the content management system plugin comprises installing the computer code defining the content management system plugin on one or more network servers hosting the large language model to make the one or more content-management-system API operations available to the computing environment of the large language model. ¶ 0061: The integration system may occupy a single device. ¶ 0070: Computing devices may operate as networked servers. ¶ 0075: Executable instructions configure physical or virtual computing instances.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the plugin execution arrangement of KUMAR-MISHCHENKO to incorporate the consolidates server implementation taught by MISHCHENKO. One of ordinary skill the art would be motivated to integrate that implementation into JUMAR-MISHCHENKO, with a reasonable expectation of success, in order to avoid a separate network exchange between the model and its function call translator by executing them on the same server, as inferred from MISHCHENKO’s single device option and call translation arrangement at ¶¶ 0061, 0063.
Claim 3
MISHCHENKO discloses wherein the content management system is external to the computing environment of the large language model. ¶ 0168: The generative engine may occupy external hardware. ¶ 0180: The external generative service is accessed through APIs.
Claim 4
KUMAR discloses wherein executing the content-management-system API operation on the content item stored in the content management system comprises executing at least one of a search operation, a metadata access operation, a download operation, a copying operation, a moving operation, an editing operation, a content generation operation, a sharing operation, or an upload operation. ¶ 0188: The plugin searches stored project content.
Claim 8
Claim 8 is rejected utilizing the rationale for claim 1; the claim is directed to a system performing the method.
Claim 9
KUMAR discloses provide, for display via a user interface of a client device, a toggle element for initiating a large language model prompt. ¶ 0185: A displayed control invokes the generative service.
KUMAR discloses receive a user interaction with the toggle element. ¶ 0185: Selecting the control activates the service.
KUMAR discloses provide, to the large language model, the large language model prompt indicating operations associated with the content items stored in the content management system. ¶ 0186: Selectable commands specify content processing. ¶ 0188: The resulting prompt reaches the generative engine.
Claim 10
Claim 10 is rejected utilizing the rationale for Claim 3; the claim is directed to a system performing the method.
Claim 11
Claim 11 is rejected utilizing the rationale for claim 4; the claim is directed to a system performing the method.
Claim 12
KUMAR discloses receive, from at least one of the large language model or a third-party system, an additional function call requesting performance of an additional API operation on an additional content item modified by execution of a third-party API operation at the third-party system. ¶ 0146: API requests reach third party services with backend callback. ¶ 0031: Content can be recast for another platform. ¶ 0153: Modification results can pass to another system.
KUMAR discloses execute the additional API operation on the additional content item in response to the additional function call. ¶ 0152: An API request updates the stored document object.
Claim 15
Claim 15 is rejected utilizing the rationale for claim 1; the claim is directed to a medium storing instructions corresponding to the method.
Claim 16
KUMAR discloses provide, for display via a client device, a user interface element for initiating a large language model prompt. ¶ 0185: A graphical control invokes the generative service.
KUMAR discloses receive a user interaction with the user interface element. ¶ 0185: The service responds to control selection.
KUMAR discloses provide, to the large language model, the large language model prompt indicating operations for one or more of the content items stored in the content management system. ¶ 0188: A content inquiry produces a prompt for the model.
Claim 17
Claim 17 is rejected utilizing the aforementioned rationale for Claim 3; the claim is directed to a system performing the method.
Claim 20
KUMAR discloses receive, from the large language model via the content management system plugin, an additional function call requesting performance of an additional API operation on the content item after the content item is modified … wherein the third-party API operation uses relationship information indicating relationships between user accounts defined by the content management system and the content
items stored in the content management system. ¶ 0072: User references resolve to specific personal page identifiers. ¶ 0074: Graphs associate system objects with user identifiers. ¶ 0031: Content transformation supports exchange between platforms.
KUMAR discloses execute the additional API operation on the content item in response to the additional function call. ¶ 0152: The backend updates a document in response to an API request.
KUMAR does not expressly disclose wherein the content item is modified by execution of a third-party API operation at a third-party system.
MISHCHENKO discloses wherein the content item is modified by execution of a third-party API operation at a third-party system. ¶ 0054: Model controlled external applications can edit documents. ¶ 0052: External execution results can return to the model. ¶ 0063: Model function calls become API requests. ¶ 0068: The model selects functions and generates requests.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the third party content processing workflow of KUMAR to incorporate the external application editing, returned API results, and model generated follow on function calls taught by MISHCHENKO. One of ordinary skill in the art would be motivate to integrate that functionality into KUMAR, with a reasonable expectation of success, in order to reduce inaccuracies associated with multiple interfaces and API access points by controlling the external editing and subsequent CMS operations through the same model interface, as taught by MISHCHENKO at ¶ 0023.
Claims 5 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over KUMAR, in view of MISHCHENKO, further in view of Miller, U.S. Patent No. 9,807,073 B1.
Claim 5
Miller discloses wherein executing the content-management-system API operation on the content item stored in the content management system comprises executing a team-based API operation on a plurality of content items stored across a plurality of user accounts of the content management system. Miller discloses a “document management and collaboration system” enabling “multiple users belonging to a variety of organizations to share and collaborate on documents.” Miller, 2:6-19. A user of a first device 210 “requests that a document be shared with a second user …, whereby the request may be [an] application programming interface (API) function call.” Id. at 5:57-6:20. A first user may “grant the second user access to a document 316 retained by the document a management and collaboration system 302,” wherein the request is “an API function call” (i.e., team-based API operation). Id. at 7:1-18. The first user may “designate … a group of users with whom the document is to be shared” (group of users → team). Id. at 8:36-45.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the LLM configured to operate on content in a content management system of KUMAR-MISHCHENKO to incorporate a content management system API for sharing documents as taught by Miller. One of ordinary skill in the art would be motivated to integrate a content management system API for sharing documents into KUMAR-MISHCHENKO, with a reasonable expectation of success, in order to improve security, because “rather than share documents in an unsecure manner due to the fact that secure sharing is too cumbersome, users are more likely to adopt secure practices when enabled automatically by the document management and collaboration system.” Miller, 14:20-34.
Claim 19
Claim 19 is rejected utilizing the aforementioned rationale for Claim 5; the claim is directed to a medium storing instructions corresponding to the method.
Claims 6 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over KUMAR, in view of MISHCHENKO, further in view of Spagnolo et al., U.S. PG-Publication No. 2023/0418982 A1.
Claim 6
Spagnolo discloses generating, by executing a first API operation associated with the content management system plugin, a new content item comprising information from at least a portion of the content items stored in the content management system; and storing, by executing a second API operation associated with the content management system plugin, the new content item within the content management system. Spagnolo discloses a “content management system (CMS) … for providing integration between APPS configured for use with an editor application of the CMS.” Spagnolo, ¶ 6. The CMS “facilitates the creation, storage, editing, and delivery of digital content,” wherein the “creation, editing, federation and other management of content is mediated through a content management API 104” that is a “read-write API for managing content.” The content management API “enables one to pragmatically create or update content items.” Id. at ¶¶ 43, 46. The content management API is used “to generate new content items in the system, retrieve and edit existing content items, store changes to content items, etc.” Id. at ¶ 47. Back end APPs “can also call APIs directly … and may make scripted API calls to the CMS.” APPs can include “content actors enabling integration of services and custom logic, such as artificial intelligence (AI)” (e.g., the LLM system of Kumar). Id. at ¶¶ 84, 87; See Also ¶ 152 (“content infrastructure includes APIs for content management … to deliver content to any application”). For example, a translation logic 114 “enables translation … of the content into the local language,” and “may access the content management API 104 to retrieve, generate, and store translations of content in the CMS 100” (generate translation → new content item comprising information from at least a portion of content items stored); (store translation → store new content in CMS). Id. at ¶ 48.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the LLM configured to operate on content in a content management system of KUMAR-MISHCHENKO to incorporate API functions for accessing content in a content management system taught by Spagnolo. One of ordinary skill in the art would be motivated to integrate API functions for accessing content in a content management system into KUMAR-MISHCHENKO, with a reasonable expectation of success, in order to improve user experience, “by allowing users to flexibly structure and manage content, independent of the presentation of such content through various contexts” and to improve security by enabling “inter-app action triggering in a structured manner that is not open to potential exploitation or otherwise insecure.” Spagnolo, ¶¶ 2, 37.
Claim 13
Claim 13 is rejected utilizing the aforementioned rationale for Claim 6; the claim is directed to a system performing the method.
Claims 7, 14, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over KUMAR, in view of MISHCHENKO, further in view of Kapoor, U.S. PG-Publication No. 2016/0062839 A1.
Claim 7
Kapoor discloses executing a reverse version of the content-management-system API operation on the content item to undo a prior action associated with the function call. Kapoor discloses methods enabling “a user to store content items in a content library that can be access[ed] and modified from multiple client devices.” Changes made to the content library from a first device “can be synchronized such that the content library reflects the changes when accessed from a second device.” Kapoor, ¶¶ 19-20. The content management system 106 “can interact with other content and/or service providers … through an Application Programming Interface (API).” A user can “programmatically make calls directly to content management system 106 … to read, write, create, delete, share, or otherwise manipulate content.” Id. at ¶ 37. Kapoor discloses method 700 “for prompting a user to undo a content item operation at a client device.” After performing a move API operation, client device 102 “can determine if the client device has received an undo input … to return the moved content item to the origination directly.” Id. at ¶¶ 97-107; FIG. 7.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the LLM configured to operate on content in a content management system of KUMAR-MISHCHENKO to incorporate an API command to undo a content operation as taught by Kapoor. One of ordinary skill in the art would be motivated to integrate an API command to undo a content operation into KUMAR-MISHCHENKO, with a reasonable expectation of success, in order to improve user experience by enabling an undo operation to correct a user from a mistake such as “moving a shared content item” so that the “item will no longer be accessible to other users after the content has been moved.” See Kapoor, ¶ 103.
Claim 14
Claim 14 is rejected utilizing the aforementioned rationale for Claim 7; the claim is directed to a system performing the method.
Claim 18
Claim 18 is rejected utilizing the aforementioned rationale for Claim 7; the claim is directed to a medium storing instructions corresponding to the method.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. See Mishchenko et al., U.S. PG-Publication No. 2025/0110811 A1.
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 FRANK D MILLS whose telephone number is (571)270-3194. The examiner can normally be reached M-F 9-5:30 CT.
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, KEVIN YOUNG can be reached at (571)270-3180. 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.
/FRANK D MILLS/Primary Examiner, Art Unit 2194 September 30, 2026
Prosecution Insights