Prosecution Insights
Last updated: April 19, 2026
Application No. 18/770,394

METHODS AND SYSTEMS FOR UPDATING A RETRIEVAL-AUGMENTED GENERATION FRAMEWORK

Non-Final OA §101§103
Filed
Jul 11, 2024
Examiner
PYO, MONICA M
Art Unit
2161
Tech Center
2100 — Computer Architecture & Software
Assignee
Shopify Inc.
OA Round
3 (Non-Final)
83%
Grant Probability
Favorable
3-4
OA Rounds
3y 4m
To Grant
99%
With Interview

Examiner Intelligence

Grants 83% — above average
83%
Career Allow Rate
511 granted / 616 resolved
+28.0% vs TC avg
Strong +36% interview lift
Without
With
+35.6%
Interview Lift
resolved cases with interview
Typical timeline
3y 4m
Avg Prosecution
16 currently pending
Career history
632
Total Applications
across all art units

Statute-Specific Performance

§101
23.2%
-16.8% vs TC avg
§103
40.3%
+0.3% vs TC avg
§102
10.7%
-29.3% vs TC avg
§112
17.2%
-22.8% vs TC avg
Black line = Tech Center average estimate • Based on career data from 616 resolved cases

Office Action

§101 §103
Notice of Pre-AIA or AIA Status 1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . DETAILED ACTION 2. This communication is responsive to the RCE filed on 11/05/2025. 3. Claims 1-23 are currently pending in this Office action. Information Disclosure Statement 4. The information disclosure statement (IDS) filed on 09/24/2025 and 11/18/2025 were considered by the examiner. Claim Rejections - 35 USC § 101 5. The examiner acknowledges the applicant’s responses [pages 8-13 of Remarks] filed on 11/05/2025 and the 35 U.S.C. 101 rejection made in the prior Office action is withdrawn. Claim Rejections - 35 USC § 103 6. 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 (i.e., changing from AIA to pre-AIA ) 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. 7. 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. 8. Claims 1-5, 7-16 and 18-23 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. 2024/0362422 (hereinafter Callegari) in view of U.S. 2026/0011149 (hereinafter Lakhotia). Regarding claims 1, 12 or 23, Callegari discloses a computer-implemented method comprising: detecting, by a computing device, an updated iteration of a source document ([0018 and 0020]; fig. 1a; “…Alternatively, the LLM program 22 may be configured to self-assess and revise without further input from the user, for example, for a predetermined number of iterations. If assessment and revision is to be performed, then the LLM 26 assesses the first response 32 based on assessment criteria to thereby generate an assessment report 34, and the assessment report 34, first response 32, and prompt 30 are fed back into the LLM 26 with instructions to revise the prompt 30 in order to improve on the first response 32…”); the prior iteration for generating a set of synthetic question and answer pairs using a large language model (LLM) ([0022-0024]; fig. 2; “…The at least one processor 16 is configured to perform assessment of the response 32 and revision of the prompt 30 in the response assessment stage and prompt revision state, at least in part by (a) assessing the first response 32 according to assessment criteria 64 to generate the assessment report 34 for the first response 32, via the LLM 26, and (b) providing second input 66 including a prompt revision instruction 68 to the LLM 26 to generate a revised prompt 69 in view of the assessment report 34…”); and responsive to identifying that the given chunk of the updated iteration of the source document differs from the corresponding chunk of the prior iteration of the source document, triggering generation, using the LLM, of a new set of synthetic question and answer pairs associated with corresponding text in the given chunk ([0059-0066 and 0071]; fig. 8; “Using the newest and final revised prompt 69, the LLM 26 may output the final response 56, ‘The giant panda is a bear that lives in China…’ The final response 56 may be assessed if desired…The responses across the iterations may be compared by a sum or averaged score, or another suitable comparison method may be used…”). Callegari does not explicitly discloses the recited features of comparing, by the computing device, the updated iteration of the source document to a prior iteration of the source document to identify a given chunk of the updated iteration of the source document that differs from the corresponding chunk of the prior iteration of the source document; wherein the new set of synthetic question and answer pairs replaces at least a subset of the set of synthetic question and answer pairs associated with the source document based on mapping of the given chunk with the corresponding chunk of the prior iteration of the source document. However, Lakhotia discloses that “In some implementations, the second query (e.g., the query of the language model 114) can be a function instruction referencing a specific embedding (e.g., vid_emd15), label (e.g., “accident,” “fall,” “robot collision”), and/or task (e.g., “validate occurrence,” “extract object interaction “classify event type”) to be executed by the video model 116. That is, the second query can represent a request to generate metadata, validate a condition, or extract a response associated with a previously stored or retrieved video embedding. For example, the query can instruct the video model 116 to determine whether a specific action occurred in a segment or whether two objects appear simultaneously….”; and “…For example, the caption “a person enters the room” can be tokenized and applied alongside embedding vid_emd15 to update semantic interpretation. In another example, graph nodes representing “object: door” and “action: open” can be used to inform sequence-level predictions across a video segment” ([0090-0092]). Lakhotia additionally discloses that ““In some implementations, the agent system 110 can implement and/or otherwise facilitate retrieval-augmented generation (RAG) models to improve output quality of the language model 114 and/or the video model 116 by incorporating external knowledge sources. The RAG architecture can include a retrieval system and a generation system, where the retrieval system of agent system 110 can fetch relevant documents, embeddings, or structured data (e.g., captions, graph nodes, metadata vectors, and/or any contextual output) from knowledge bases (e.g., video embedding stores, label graphs, memory queues, and/or any indexed database), and the generation system of agent system 110 can synthesize responses using retrieved content….” ([0107 and 0145]) and it would have been obvious for one with ordinary skill in the art to utilize the teachings of Lakhotia in the system of Callegari in view of the desire to enhance the feature of revising input prompts by updating the context resulting in improving the efficiency of the assessment scheme. Additionally, Callegari discloses a non-transitory computer-readable medium (fig. 1A). Regarding claims 2 and 13, Callegari in view of Lakhotia discloses the method further comprising: applying the new set of synthetic question and answer pairs to the LLM to generate a response to a user query (Callegari: [0022-0023]; fig. 2) and (Lakhotia: [0004]). Therefore, the limitations of claims 2 and 13 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claims 3 and 14, Callegari in view of Lakhotia discloses the method wherein generating the response further comprises: applying the LLM to generate a textual response to the user query responsive to identifying a similarity to at least one of the set of synthetic question and answer pairs and the new set of synthetic question and answer pairs (Callegari: [0022-0023]) and (Lakhotia: [0070-0071]). Therefore, the limitations of claims 3 and 14 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claims 4 and 15, while Callegari in view of Lakhotia discloses the method wherein triggering generation is further based upon detecting a degree of difference between the corresponding chunk and the given chunk exceeds a defined threshold (Callegari: [0018]; wherein if the assessment report for the current response has not met a predefined assessment threshold then the assessment and revision is repeated for another iteration triggering generation) and (Lakhotia: [0062 and 0071]). Therefore, the limitations of claims 4 and 15 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claims 5 and 16, Callegari in view of Lakhotia discloses the method wherein responsive to detecting the difference, further applying semantic similarity using natural language processing to determine a similarity measure and specific segments of text within the given chunk which are modified compared to the corresponding chunk in the prior iteration and triggering the generation of the new set of synthetic question and answer pairs for the specific segments of text (Callegari: [0022-0023]; fig. 2) and (Lakhotia: [0071 and 0107]). Therefore, the limitations of claims 5 and 16 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claims 7 and 18, Callegari in view of Lakhotia does not explicitly disclose the method wherein the degree of difference is based on at least one of a distance measure or a cosine similarity (Lakhotia: [0071]). Therefore, the limitations of claims 7 and 18 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. . Regarding claims 8 and 19, Callegari in view of Lakhotia discloses the method further comprising, providing a user interface configured to receive the user query and, in response, determining a similarity between the user query and the set of synthetic questions and the new set of synthetic questions to retrieve corresponding synthetic answers for providing the textual response to the user query and displaying the textual response on a visual display of the user interface (Callegari: [0017-0018]; figs. 2 and 7) and (Lakhotia: [0071 and 0107]). Therefore, the limitations of claims 8 and 19 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claims 9 and 20, Callegari in view of Neervannan discloses the method wherein comparing further comprises initially performing content aware chunking on the updated iteration and prior iteration of the source document by accessing document metadata comprising document structure relationships providing at least one of section headers, subheaders and document boundaries, and chunking based on the document structure relationships, the chunking for identifying differing chunks between the updated iteration and prior iteration (Callegari: [0059-0066]) and (Lakhotia: [0145]). Therefore, the limitations of claims 9 and 20 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claims 10 and 21, Callegari in view of Lakhotia discloses the method wherein chunking based on the document structure relationships, further comprises, prior to performing the chunking, determining, via natural language processing, whether one or more sentences corresponding to a prior chunk and preceding a current chunk has a similar context and thereby merging the prior chunk and the current chunk into a single chunk for comparing between iterations (Callegari: [0026]; fig. 2) and (Lakhotia: [0107 and 0145]). Therefore, the limitations of claims 10 and 21 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. Regarding claim 11 and 22, Callegari in view of Lakhotia discloses the method wherein generating the textual response to the user query comprises: generating a prompt to the LLM, the prompt including the user query and a relevant set of question and answer pairs comprising: at least one of the set of synthetic question and answer pairs and the new set of synthetic question and answer pairs; and providing the prompt to the LLM and receiving the generated textual response (Callegari: [0022-0023]; figs. 2 and 7) and (Lakhotia: [0042-0043]). Therefore, the limitations of claims 11 and 22 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis. 9. Claims 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Callegari in view of Lakhotia, and further in view of WO 2020/256754 (hereinafter De Matos). Regarding claims 6 and 17, while Callegari in view of Lakhotia discloses the method of performing a validation scheme on one or more documents and comparing on each chunk to a corresponding chunk of the prior iteration of the source document to determine differing chunks for generating the new set of synthetic questions and answers therefrom (Callegari: [0022 and 0059-0066]) and (Lakhotia: [0145]), the references do not explicitly disclose the features of wherein prior to performing a comparison, performing an initial checksum on entire textual content of [the updated iteration of] the source document to determine whether an update exists in textual content of the source document as a whole and based on said determining, computing a hash on each chunk and comparing the hash on each chunk to a corresponding chunk of the prior iteration of the source document to determine differing chunks. However, De Matos discloses that “Using the functionality of Fig. 6, a requester may verify if a record is valid using a third party validator by performing two simple steps: (1) compute a checksum hash of the record…” ([0073]); and “…One is to compare their text, without the last transaction, to make sure they all have the same identical original portion. Another way, is used in the embodiment of Fig. 9, is to take all checksums that were produced in step 3, and make sure they all match…” ([0094]). De Matos also discloses that “The verification functionality can be performed in any order,…(4) Verify signature and rule compliance for each transaction, one transaction at a time…” ([0061-0062]) and it would have been obvious for one with ordinary skill in the art to utilize the teachings of De Matos in the modified system of Callegari in view of the desire to enhance the feature of revising input prompts by applying the validation scheme resulting in improving the efficiency of the assessment report. Response to Arguments 10. Applicant’s arguments have been considered but are deemed to be moot in view of new grounds of rejection presented in this Office action. Conclusion 11. Any inquiry concerning this communication or earlier communications from the examiner should be directed to MONICA M PYO whose telephone number is (571)272-8192. The examiner can normally be reached Monday-Friday 8am-4pm. 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, APU MOFIZ can be reached at 571-272-4080. 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. /MONICA M PYO/ Primary Examiner, Art Unit 2161
Read full office action

Prosecution Timeline

Jul 11, 2024
Application Filed
Mar 18, 2025
Non-Final Rejection — §101, §103
Jul 18, 2025
Response Filed
Aug 16, 2025
Final Rejection — §101, §103
Oct 15, 2025
Response after Non-Final Action
Oct 20, 2025
Response after Non-Final Action
Nov 05, 2025
Request for Continued Examination
Nov 14, 2025
Response after Non-Final Action
Jan 09, 2026
Non-Final Rejection — §101, §103
Feb 18, 2026
Interview Requested
Mar 10, 2026
Applicant Interview (Telephonic)
Mar 12, 2026
Examiner Interview Summary

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12602291
SELECTING CANDIDATES FOR DEMOTION FROM A FIRST ASYNCHONOUS REPLICATION TECHNIQUE TO A SECOND ASYNCHRONOUS REPLICATION TECHNIQUE
2y 5m to grant Granted Apr 14, 2026
Patent 12596723
DYNAMIC VALUATION SYSTEM USING OBJECT RELATIONSHIPS AND COMPOSITE OBJECT DATA
2y 5m to grant Granted Apr 07, 2026
Patent 12591751
NATURAL LANGUAGE GENERATION USING KNOWLEDGE GRAPH INCORPORATING TEXTUAL SUMMARIES
2y 5m to grant Granted Mar 31, 2026
Patent 12579175
METHOD AND DEVICE FOR GENERATING ANSWER TO NATURAL LANGUAGE QUESTION FOR DATA
2y 5m to grant Granted Mar 17, 2026
Patent 12579194
DIGITAL SUPPLEMENT ASSOCIATION AND RETRIEVAL FOR VISUAL SEARCH
2y 5m to grant Granted Mar 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
83%
Grant Probability
99%
With Interview (+35.6%)
3y 4m
Median Time to Grant
High
PTA Risk
Based on 616 resolved cases by this examiner. Grant probability derived from career allow 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