Prosecution Insights
Last updated: May 29, 2026
Application No. 18/395,099

INTELLIGENT DOCUMENT CREATION AND REVIEW GENERATED BY A LARGE LANGUAGE MODEL

Non-Final OA §103
Filed
Dec 22, 2023
Examiner
KELLS, ASHER
Art Unit
2171
Tech Center
2100 — Computer Architecture & Software
Assignee
Dropbox Inc.
OA Round
2 (Non-Final)
79%
Grant Probability
Favorable
2-3
OA Rounds
1m
Est. Remaining
90%
With Interview

Examiner Intelligence

Grants 79% — above average
79%
Career Allowance Rate
498 granted / 633 resolved
+23.7% vs TC avg
Moderate +11% lift
Without
With
+11.1%
Interview Lift
resolved cases with interview
Typical timeline
2y 6m
Avg Prosecution
22 currently pending
Career history
650
Total Applications
across all art units

Statute-Specific Performance

§101
7.3%
-32.7% vs TC avg
§103
72.8%
+32.8% vs TC avg
§102
11.3%
-28.7% vs TC avg
§112
6.6%
-33.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 633 resolved cases

Office Action

§103
DETAILED ACTION Continued Examination under 37 CFR § 1.114 A request for continued examination under 37 C.F.R. § 1.114, including the fee set forth in 37 C.F.R. § 1.17(e), was filed in this application after allowance or after an Office action under Ex Parte Quayle, 25 USPQ 74, 453 O.G. 213 (Comm'r Pat. 1935). Since this application is eligible for continued examination under 37 C.F.R. § 1.114, and the fee set forth in 337 C.F.R. § 1.17(e) has been timely paid, prosecution in this application has been reopened pursuant to 37 C.F.R. § 1.114. 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 Objections Claim 16 is objected to because of the following informalities: Claim 16 recites the limitation “cause at least one processor to: … providing, to the signor recipient device, a signature metric score that indicates at least one of: a percentage of additional signor recipient devices that signed the digital document, an average amount of time taken by the additional signor recipient devices to sign the digital document, or a signor document modification rate.” The phrase “providing, to the signor recipient device” contains a typographical/grammatical error. Appropriate correction is required. 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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1, 7, and 16 are rejected under 35 U.S.C. § 103 as being unpatentable over GoGwilt et al., US 2024/0086651 A1, in view of Salehian et al., US 11,301,616 B1. Regarding claim 1, GoGwilt discloses a computer-implemented method comprising: Generating, utilizing a large language model to process a digital document, a document summary comprising a condensed version of the digital document in a target language associated with a user account of a signor recipient device. GoGwilt teaches using a generative language model (e.g., a GPT) to generate output, such as a summary and translation of a document. GoGwilt ¶¶ 21, 93. Providing the document summary for display on a signor recipient device within a document review interface comprising one or more document modification elements for modifying the digital document via the large language model. GoGwilt teaches presenting a display screen on a user device using, in part, the output of the generative language model. GoGwilt figs. 5A-5C. Additionally, the display screen may include a graphical element, such as “suggestions and recommendations,” that modifies the document by means of the generative language model. Id. ¶¶ 73-75. Generating a suggested document modification element to include within the document review interface based on one or more stored digital documents within a content management system. GoGwilt teaches the generative language model may be trained using a corpus of documents stored in a database. GoGwilt ¶¶ 32, 103-104. The generative language model may be used to generate a suggestion or recommendation. Id. ¶¶ 73-75. In response to a user interaction with the suggested document modification element, generating, utilizing the large language model, a modified digital document to provide to a requestor device. GoGwilt teaches that a user may accept a suggestion or recommendation in order for the modification generated by the generative language model to be incorporated into the document. GoGwilt ¶ 58. GoGwilt does not disclose, but Salehian discloses providing, to the signor recipient device, a signature metric score that indicates … a percentage of additional signor recipient devices that signed the digital document. Salehian teaches a secure document service providing feature modification activities to a recipient user. Salehian 12:31-34, fig. 5 (step 560). The recipient user may be a user tasked with signing a secure document. Id. 3:37-49, 5:16-23. A notification module may generate notifications associated with a feature modification activity. Id. 9:32-37. A notification may include any relevant information, such as a predicted likelihood of a recipient user completing a request. Id. 9:37-46. For example, the notification may indicate a percentage of other users that completed a task. Id. 10:42-45. fig. 3 (third notification 325). It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of providing a suggested document modification element with Salehian’s process of providing a signature metric score indicating a percentage of other recipient users that completed a task (e.g., signed a document). Such a modification would protect the recipient user from exploitation by providing the recipient user with an indication that other users have not signed the document. Regarding claim 7, which depends on claim 1, GoGwilt discloses: utilizing the large language model to generate the digital document in the target language associated with the user account of the signor recipient device; identifying an additional signor recipient device with an additional target language associated with an additional user account of an additional signor recipient device; utilizing the large language model to generate the digital document in the additional target language; and providing the digital document in the additional target language to the additional signor recipient device. GoGwilt teaches using a generative language model to translate the language of a digital document. GoGwilt ¶ 21. Regarding claim 16, GoGwilt discloses a non-transitory computer-readable medium storing executable instructions which, when executed by at least one processor, cause the at least one processor to: Generate, utilizing a large language model to process a digital document, a document summary comprising a condensed version of the digital document in a target language associated with a user account of a signor recipient device. GoGwilt teaches using a generative language model (e.g., a GPT) to generate output, such as a summary and translation of a document. GoGwilt ¶¶ 21, 93. Provide the document summary for display on a signor recipient device within a document review interface comprising document modification elements for modifying the digital document via the large language model. GoGwilt teaches presenting a display screen on a user device using, in part, the output of the generative language model. GoGwilt figs. 5A-5C. Additionally, the display screen may include a graphical element, such as “suggestions and recommendations,” that modifies the document by means of the generative language model. Id. ¶¶ 73-75. Generate a suggested document modification element to include within the document review interface based on stored digital documents within a content management system. GoGwilt teaches the generative language model may be trained using a corpus of documents stored in a database. GoGwilt ¶¶ 32, 103-104. The generative language model may be used to generate a suggestion or recommendation. Id. ¶¶ 73-75. In response to a user interaction with the suggested document modification element, generate, using the large language model, a modified digital document with redlined portions that indicate a difference between the digital document and the modified digital document to provide to a requestor device. GoGwilt teaches that a user may accept a suggestion or recommendation in order for the modification generated by the generative language model to be incorporated into the document. GoGwilt ¶ 58. GoGwilt teaches depicting redlined portions of a document indicating edits to the document. Id. ¶ 82, fig. 5C. GoGwilt does not disclose, but Salehian discloses providing [sic], to the signor recipient device, a signature metric score that indicates … a percentage of additional signor recipient devices that signed the digital document. Salehian teaches a secure document service providing feature modification activities to a recipient user. Salehian 12:31-34, fig. 5 (step 560). The recipient user may be a user tasked with signing a secure document. Id. 3:37-49, 5:16-23. A notification module may generate notifications associated with a feature modification activity. Id. 9:32-37. A notification may include any relevant information, such as a predicted likelihood of a recipient user completing a request. Id. 9:37-46. For example, the notification may indicate a percentage of other users that completed a task. Id. 10:42-45. fig. 3 (third notification 325). It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of providing a suggested document modification element with Salehian’s process of providing a signature metric score indicating a percentage of other recipient users that completed a task (e.g., signed a document). Such a modification would protect the recipient user from exploitation by providing the recipient user with an indication that other users have not signed the document. Claims 2, 9-11, 14, and 17 are rejected under 35 U.S.C. § 103 as being unpatentable over GoGwilt et al., US 2024/0086651 A1, in view of Salehian et al., US 11,301,616 B1, further in view of Hariri et al., US 2024/0330580 A1. Regarding claim 2, which depends on claim 1, GoGwilt does not explicitly disclose, but Hariri discloses wherein providing the document modification elements further comprises providing, to the signor recipient device, a text field in the document review interface for entering document modification prompts to modify the digital document. Hariri teaches providing a text field wherein a user may enter an open-ended request. Hariri fig. 5, ¶ 85. It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of using a generative language model to edit a contract with Hariri’s process of providing a text field for entering document modification prompts. Such a modification would increase utility and usability by providing a user with an easy method for providing any desired modification. Regarding claim 9, GoGwilt discloses a system comprising: at least one processor; and a non-transitory computer-readable medium storing instructions which, when executed by the at least one processor, cause the system to: Generate, utilizing a large language model to process a digital document, a document summary comprising a condensed version of the digital document in a target language associated with a user account of a signor recipient device. GoGwilt teaches using a generative language model (e.g., a GPT) to generate output, such as a summary and translation of a document. GoGwilt ¶¶ 21, 93. Provide the document summary for display on a signor recipient device within a document review interface. GoGwilt teaches presenting a display screen on a user device using, in part, the output of the generative language model. GoGwilt figs. 5A-5C. Additionally, the display screen may include a graphical element, such as “suggestions and recommendations,” that modifies the document by means of the generative language model. Id. ¶¶ 73-75. Generate a suggested document modification element to include within the document review interface based on stored digital documents within a content management system. GoGwilt teaches the generative language model may be trained using a corpus of documents stored in a database. GoGwilt ¶¶ 32, 103-104. The generative language model may be used to generate a suggestion or recommendation. Id. ¶¶ 73-75. In response to a user interaction with the suggested document modification element, generate, utilizing the language model, a modified digital document to provide to a requestor device. GoGwilt teaches that a user may accept a suggestion or recommendation in order for the modification generated by the generative language model to be incorporated into the document. GoGwilt ¶ 58. GoGwilt does not explicitly disclose, but Hariri discloses a document review interface comprising a text field in the document review interface for entering document modification prompts to modify the digital document via the large language model. Hariri teaches providing a text field wherein a user may enter an open-ended request. Hariri fig. 5, ¶ 85. It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of using a generative language model to edit a contract with Hariri’s process of providing a text field for entering document modification prompts. Such a modification would increase utility and usability by providing a user with an easy method for providing any desired modification. GoGwilt does not disclose, but Salehian discloses provide, to the signor recipient device, a signature metric score that indicates … a percentage of additional signor recipient devices that signed the digital document. Salehian teaches a secure document service providing feature modification activities to a recipient user. Salehian 12:31-34, fig. 5 (step 560). The recipient user may be a user tasked with signing a secure document. Id. 3:37-49, 5:16-23. A notification module may generate notifications associated with a feature modification activity. Id. 9:32-37. A notification may include any relevant information, such as a predicted likelihood of a recipient user completing a request. Id. 9:37-46. For example, the notification may indicate a percentage of other users that completed a task. Id. 10:42-45. fig. 3 (third notification 325). It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of providing a suggested document modification element with Salehian’s process of providing a signature metric score indicating a percentage of other recipient users that completed a task (e.g., signed a document). Such a modification would protect the recipient user from exploitation by providing the recipient user with an indication that other users have not signed the document. Regarding claim 10, which depends on claim 9, GoGwilt discloses generating a similarity threshold for the digital document; and identifying one or more content items within the content management system that satisfies the similarity threshold with the digital document. GoGwilt teaches determining a suggestion that a counterparty will likely accept based on a document that both parties have signed. GoGwilt ¶ 93. Regarding claim 11, which depends on claim 9, GoGwilt discloses generat[ing] the suggested document modification element based on identifying features associated with the signor recipient device comprising at least one of geographic location, language settings, age, and gender. GoGwilt teaches recognizing properties of a document that identify features (e.g., a name or address) associated with a counterparty. GoGwilt ¶ 41, Table I. Regarding claim 14, which depends on claim 9, GoGwilt discloses generat[ing] the modified digital document by depicting within the digital document, redlined portions that indicate a difference between the modified digital document and the digital document. GoGwilt teaches depicting redlined portions of a document indicating edits to the document. GoGwilt ¶ 82, fig. 5C. Regarding claim 17, which depends on claim 16, GoGwilt does not explicitly disclose, but Hariri discloses provid[ing], to the signor recipient device, a text field in the document review interface for entering document modification prompts to modify the digital document. Hariri teaches providing a text field wherein a user may enter an open-ended request. Hariri fig. 5, ¶ 85. It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of using a generative language model to edit a contract with Hariri’s process of providing a text field for entering document modification prompts. Such a modification would increase utility and usability by providing a user with an easy method for providing any desired modification. Claim 6 is rejected under 35 U.S.C. § 103 as being unpatentable over GoGwilt et al., US 2024/0086651 A1, in view of Salehian et al., US 11,301,616 B1, further in view of Allison et al., US 2017/0322681 A1. Regarding claim 6, which depends on claim 1, GoGwilt does not explicitly disclose, but Allison discloses providing a single selectable element option in the document review interface for the signor recipient device to sign all placeholder fields in response to a selection of the single selectable element option. Allison ¶ 33, fig. 2. It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of using a generative language model to edit a contract with Allison’s process of providing a single selectable element to sign all placeholder fields. Such a modification would decrease the time and labor necessary to sign electronic documents. See Allison ¶ 18. Claim 15 is rejected under 35 U.S.C. § 103 as being unpatentable over GoGwilt et al., US 2024/0086651 A1, in view of Salehian et al., US 11,301,616 B1, further in view of Hariri et al., US 2024/0330580 A1, further in view of Allison et al., US 2017/0322681 A1. Regarding claim 15, which depends on claim 1, GoGwilt does not explicitly disclose, but Allison discloses provid[ing] a single selectable element option in the document review interface for the signor recipient device to sign all placeholder fields in response to a selection of the single selectable element option. Allison ¶ 33. It would have been obvious before the effective filing date of the claimed invention to a person with ordinary skill in the art to modify GoGwilt’s process of using a generative language model to edit a contract with Allison’s process of providing a single selectable element to sign all placeholder fields. Such a modification would decrease the time and labor necessary to sign electronic documents. See Allison ¶ 18. Allowable Subject Matter Claims 3-5, 8, 12-13, and 18-20 contain allowable subject matter. Claims 3-5, 8, 12-13, and 18-20 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. The following prior art made of record and not relied upon is considered pertinent to applicant’s disclosure: Bui et al., US 2018/0239959 A1, discloses a document management system comprising a graphical user interface comprising an indication of signatures that have been collected. Follis et al., US 2016/0204944 A1, discloses an electronic signature service that stores a percentage of designated signers who sign a document. Travis et al., US 2025/0045664 A1, discloses a digital contract management system that presents a risk score along with a modification to a document. 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, Kieu Vu can be reached at 571-272-4057. 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

Show 1 earlier event
Oct 14, 2025
Non-Final Rejection mailed — §103
Dec 09, 2025
Interview Requested
Dec 15, 2025
Examiner Interview Summary
Dec 15, 2025
Applicant Interview (Telephonic)
Jan 07, 2026
Response Filed
Apr 14, 2026
Request for Continued Examination
Apr 22, 2026
Response after Non-Final Action
May 20, 2026
Non-Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12626092
METHOD FOR LEARNING SYNAPTIC WEIGHT VALUES OF A NEURAL NETWORK, RELATED DATA PROCESSING METHOD, COMPUTER PROGRAM, CALCULATOR AND PROCESSING SYSTEM
3y 5m to grant Granted May 12, 2026
Patent 12626053
SYSTEM, METHOD, AND COMPUTER PROGRAM FOR USER INPUT FIELDS AUTO-COMPLETION USING MACHINE LEARNING MODEL SELECTION WITH DYNAMIC THRESHOLD MECHANISM
2y 3m to grant Granted May 12, 2026
Patent 12613721
METHOD AND SYSTEM FOR REMOTELY CONTROLLING INTERFACE DISPLAY, DEVICE AND STORAGE MEDIUM
2y 3m to grant Granted Apr 28, 2026
Patent 12613612
MEDIA CONTENT DETECTION AND MANAGEMENT
2y 6m to grant Granted Apr 28, 2026
Patent 12614022
METHOD, APPARATUS, ELECTRONIC DEVICE AND COMPUTER READABLE STORAGE MEDIUM FOR TASK CREATION
2y 4m to grant Granted Apr 28, 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 (+11.1%)
2y 6m (~1m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 633 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