Prosecution Insights
Last updated: August 17, 2026
Application No. 18/525,505

MODIFYING SUBPORTIONS OF LARGE LANGUAGE MODEL OUTPUTS

Non-Final OA §102
Filed
Nov 30, 2023
Examiner
KELLS, ASHER
Art Unit
2171
Tech Center
2100 — Computer Architecture & Software
Assignee
Google LLC
OA Round
2 (Non-Final)
79%
Grant Probability
Favorable
2-3
OA Rounds
0m
Est. Remaining
90%
With Interview

Examiner Intelligence

Grants 79% — above average
79%
Career Allowance Rate
507 granted / 642 resolved
+24.0% vs TC avg
Moderate +11% lift
Without
With
+11.0%
Interview Lift
resolved cases with interview
Typical timeline
2y 6m
Avg Prosecution
28 currently pending
Career history
659
Total Applications
across all art units

Statute-Specific Performance

§101
12.8%
-27.2% vs TC avg
§103
40.0%
+0.0% vs TC avg
§102
19.8%
-20.2% vs TC avg
§112
22.3%
-17.7% vs TC avg
Black line = Tech Center average estimate • Based on career data from 642 resolved cases

Office Action

§102
DETAILED ACTION Status of the Claims Claims 1-20 are pending. Notice of AIA Status The present application, filed on or after 16 March 2013, is being examined under the first inventor to file provisions of the AIA . In the event the determination of the status of the application as subject to AIA 35 U.S.C. §§ 102 and 103 (or as subject to pre-AIA 35 U.S.C. §§ 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. § 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. Claims 1-6, 8-9, 13-18, and 20 are rejected under 35 U.S.C. § 102(a)(2) as being anticipated by Mansour et al., US 2025/0005528 A1. Regarding claim 1, Mansour discloses a method implemented using one or more processors, comprising: Processing a first large language model (LLM) prompt using an LLM to generate a first LLM response. Mansour ¶¶ 258-259. Providing the first LLM response to a client application, wherein the first LLM response is operable by the client application to provide first rendered LLM output. Mansour ¶¶ 259, 261, fig. 6B. Receiving, from the client application: an indication of a subportion of the first rendered LLM output that has been selected using one or more input devices, and a request for a modified version of the selected subportion of the first rendered LLM output. Mansour ¶ 285, fig. 10A. Extracting a subportion of the first LLM response that corresponds to the selected subportion of the first rendered LLM output. Mansour ¶ 286. Assembling, as a second LLM prompt, the selected subportion of the first LLM response with data indicative of the request to modify the selected subportion of the first rendered LLM output. Mansour ¶ 286. Processing the second LLM prompt using the same LLM or a different LLM to generate a second LLM response. Mansour ¶ 286. Providing the second LLM response to the client application, wherein the second LLM response is operable by the client application to provide second rendered LLM output that includes at least a part of the first rendered LLM output outside of the selected subportion of the first rendered LLM output and the modified version of the selected subportion of the first rendered LLM output. Mansour ¶ 287, fig. 10B. Regarding claim 2, which depends on claim 1, Mansour discloses wherein the first LLM response comprises a string of raw text that includes metadata instructions for formatting the first rendered LLM output at the client application. Mansour ¶ 268. Regarding claim 3, which depends on claim 2, Mansour discloses wherein the selecting comprises receiving, from the client application, a starting character position and an ending character position that identify a segment of the string of raw text outside of the metadata instructions. Mansour ¶ 285, fig. 10A (selected portion 1004). Regarding claim 4, which depends on claim 1, Mansour discloses wherein the request for a modified version of the selected subportion of the first rendered LLM output comprises a request to add one or more details to the selected subportion of the first rendered LLM output. Mansour teaches that displayed command controls may correspond to different content modification or content generation actions. Mansour ¶ 285. Mansour teaches the content modification action of expanding on a subtopic (i.e., adding details). Id. ¶ 262. Additionally, Mansour teaches the content modification action of adjusting the length of content (i.e., adding/removing details). Id. ¶ 255. Regarding claim 5, which depends on claim 1, Mansour discloses wherein the request for a modified version of the selected subportion of the first rendered LLM output comprises a request to modify or replace one or more details of the selected subportion of the first rendered LLM output. Mansour teaches that displayed command controls may correspond to different content modification or content generation actions, such as changing a tone of content. Mansour ¶ 285. Changing a tone of content implies the modification or replacement of details. Regarding claim 6, which depends on claim 1, Mansour discloses wherein the request for a modified version of the selected subportion of the first rendered LLM output comprises a request to add content to the selected subportion of the first rendered LLM output that supports one or more details of the selected subportion of the first rendered LLM output. Mansour teaches that displayed command controls may correspond to different content modification or content generation actions. Mansour ¶ 285. Mansour teaches the content modification action of expanding on a subtopic (i.e., adding content). Id. ¶ 262. Additionally, Mansour teaches the content modification action of adjusting the length of content (i.e., adding/removing content). Id. ¶ 255. Regarding claim 8, which depends on claim 1, Mansour discloses wherein the request for a modified version of the selected subportion of the first rendered LLM output comprises a natural language request. Mansour teaches receiving selection of predefined natural language command control (e.g., “SUMMARIZE”) from a command selection interface window. Mansour ¶ 285, fig. 10A. Regarding claim 9, which depends on claim 1, Mansour discloses wherein the first LLM response comprises metadata instructions for rendering one or more images, and the selected subportion of the first rendered LLM output comprises one or more rendered images. Mansour teaches that an LLM may generate images. Mansour ¶ 82. Claims 13-18 are drawn to a system that implements the methods recited in claims 1-6, respectively. Accordingly, these claims are rejected for substantially the same reasons as indicated in the above rejections of the corresponding claims. Claim 20 is drawn to instructions stored in a medium that implement the method recited in claim 1. Accordingly, this claim is rejected for substantially the same reasons as indicated in the above rejection of the corresponding claim. Allowable Subject Matter Claims 7, 10-12, and 19 contain allowable subject matter. Claims 7, 10-12, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. Conclusion Although particular portions of the prior art may have been cited in support of the rejections, the specified citations are merely representative of the teachings. Other passages and figures in the cited prior art may apply. Accordingly, Applicant should consider the entirety of the cited prior art for potentially teaching all or part of the claims. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Asher D Kells whose telephone number is (571)270-7729. The examiner can normally be reached Mon. - Fri., 8 a.m. - 4 p.m.. 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, Matt Ell can be reached at 571-270-3264. 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. Asher D. Kells Primary Examiner Art Unit 2171 /Asher D Kells/Primary Examiner, Art Unit 2171
Read full office action

Prosecution Timeline

Nov 30, 2023
Application Filed
Oct 03, 2025
Non-Final Rejection mailed — §102
Dec 15, 2025
Response Filed
Apr 22, 2026
Request for Continued Examination
Apr 27, 2026
Response after Non-Final Action
Aug 12, 2026
Non-Final Rejection mailed — §102 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12699921
SYSTEMS AND METHODS OF APPLYING MATRIX PRODUCT STATES TO MACHINE LEARNING
4y 1m to grant Granted Aug 04, 2026
Patent 12701110
USER INTERFACE AND NETWORK ELEMENTS OF INTEGRATION SYSTEM
2y 0m to grant Granted Aug 04, 2026
Patent 12693878
Application Onboarding Within Workload Protection Solutions
2y 8m to grant Granted Jul 28, 2026
Patent 12688212
AUTOMATED CONTENT CREATION AND CONTENT SERVICES FOR COLLABORATION PLATFORMS
3y 0m to grant Granted Jul 21, 2026
Patent 12688463
TIME-BOUND HYPERPARAMETER TUNING
2y 10m to grant Granted Jul 21, 2026
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

2-3
Expected OA Rounds
79%
Grant Probability
90%
With Interview (+11.0%)
2y 6m (~0m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 642 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