Prosecution Insights
Last updated: April 19, 2026
Application No. 18/529,663

PROACTIVE PROMPTING FOR CONTENT ENHANCEMENT VIA FOUNDATION MODEL INTEGRATIONS IN APPLICATIONS

Non-Final OA §103
Filed
Dec 05, 2023
Examiner
DISTEFANO, GREGORY A
Art Unit
2174
Tech Center
2100 — Computer Architecture & Software
Assignee
Microsoft Technology Licensing, LLC
OA Round
3 (Non-Final)
69%
Grant Probability
Favorable
3-4
OA Rounds
3y 8m
To Grant
92%
With Interview

Examiner Intelligence

Grants 69% — above average
69%
Career Allow Rate
363 granted / 527 resolved
+13.9% vs TC avg
Strong +23% interview lift
Without
With
+23.0%
Interview Lift
resolved cases with interview
Typical timeline
3y 8m
Avg Prosecution
25 currently pending
Career history
552
Total Applications
across all art units

Statute-Specific Performance

§101
12.0%
-28.0% vs TC avg
§103
58.1%
+18.1% vs TC avg
§102
14.7%
-25.3% vs TC avg
§112
8.2%
-31.8% vs TC avg
Black line = Tech Center average estimate • Based on career data from 527 resolved cases

Office Action

§103
DETAILED ACTION This action is in response to the amendment filed 3/2/2026. Claims 1-20 are currently pending. 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 . Continued Examination Under 37 CFR 1.114 A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 3/2/2026 has been entered. Response to Arguments Applicant’s arguments, see page 9 of amendment, filed 3/2/2026, with respect to the rejection(s) of claim(s) 1 under 35 U.S.C. 103 over Wilde in view of Margolin have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Robertson et al. (US 7,149,983), hereinafter Robertson. 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, 10, and 18 is/are rejected under 35 U.S.C. 103 as being obvious over Wilde et al. (US 2022/0236843), hereinafter Wilde, in view of Liu, in view of Robertson. The applied Wilde reference has a common assignee with the instant application. Based upon the earlier effectively filed date of the reference, it constitutes prior art under 35 U.S.C. 102(a)(2). This rejection under 35 U.S.C. 103 might be overcome by: (1) a showing under 37 CFR 1.130(a) that the subject matter disclosed in the reference was obtained directly or indirectly from the inventor or a joint inventor of this application and is thus not prior art in accordance with 35 U.S.C.102(b)(2)(A); (2) a showing under 37 CFR 1.130(b) of a prior public disclosure under 35 U.S.C. 102(b)(2)(B); or (3) a statement pursuant to 35 U.S.C. 102(b)(2)(C) establishing that, not later than the effective filing date of the claimed invention, the subject matter disclosed and the claimed invention were either owned by the same person or subject to an obligation of assignment to the same person or subject to a joint research agreement. See generally MPEP § 717.02. As per claim 1, Wilde teaches the following: a method of operating an application on a computing device, (see Fig. 1), the method comprising: displaying, in a user interface of the application, a content canvas populated with content. As Wilde teaches in paragraph [0075], a user types content in a dynamic document canvas. Further see Fig. 13; capturing a state of the content canvas. As Wilde teaches in paragraph [0089], and corresponding Fig. 6, step 602, text on authored content is analyzed, where the authored content is interpreted as being a current “state”; generating a prompt displaying, in a user interface of the application, suggestion components corresponding to the follow-on prompts. As Wilde further teaches in paragraph [0089], at step 606, candidate document suggestions are provided; and in response to a selection of a suggestion component of the suggestion components: sending, . As Wilde further teaches in paragraph [0089], step 608, a selection of a candidate document is selected; and populating the content canvas with an enhancement As Wilde further teaches in paragraph [0089], step 610, the selected document is included in the content sharing board. While Wilde teaches in paragraph [0030] that the suggestion system includes a machine learning model and further see paragraph [0056], Wilde does not explicitly teach of the use of a foundation model or that the follow on prompt includes natural language instructions for said model. In a similar field of endeavor, Liu teaches of recommending content in response to user requests (see abstract). Liu further teaches in column 51, lines 27-57, that a trained machine learning model is utilized (foundation model). Liu further teaches in column 2, line 61 – column 3, line 32, that recommendations may be presented in an open-ended manner responsive to user request and include follow-up queries, i.e., responses may include follow-up prompts of natural language queries to be resubmitted to the system. It would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have modified the AI responses of Wilde with the foundation model and follow on prompts of Liu. One of ordinary skill would have been motivated to have made such modifications because as Liu teaches in column 51, lines 61-67, such follow up prompt benefit users in refining recommendations to better fit a user’s desires. Liu further teaches in column 1, lines 19-39, that an assistant (foundation model) benefits users in providing a wide variety of services. Furthermore, Wilde does not explicitly teach of generating the prompt by selecting a prefix based on contextual information and one or more completions to append to said prefix to form a natural language instruction. Robertson teaches of a method to facilitate the construction of queries (see abstract). Robertson teaches in column 19, lines 49-65, that the method may utilized synonym searching across the columns of query building information to find relative terms, which may be applied to Wilde’s analysis of content, where the content may be used to find relative terms in Robertson. Robertson further shows on Fig. 8 that a natural language query 240 is constructed based upon user selections and in column 18, lines 25-39, that such natural language generation is created as the selections are made. This natural language query shown in Fig. 8 is interpreted as encompassing a prefix/completion as the user may define first a “do” task (prefix) and then a “do what” task (completion). It would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have modified the keyword searching of Wilde with the query construction of Robertson. One of ordinary skill would have been motivated to have made such modification because as Robertson teaches in column 18, lines 25-39, such query construction benefits users who may not understand complex Boolean statements. As per claim 10, Wilde teaches the following: a computing apparatus comprising: one or more computer readable storage media; one or more processors operatively coupled with the one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media. See Fig. 22. The remaining limitations of claim 10 are substantially similar to those of claim 1 and are rejected using the same reasoning. As per claim 18, Wilde teaches the following: one or more computer-readable storage media having program instructions stored thereon that, when executed by one or more processors of a computing device. See Fig. 22. The remaining limitations of claim 10 are substantially similar to those of claim 1 and are rejected using the same reasoning. Claim(s) 2-4, 11-13, 19, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wilde in view of Liu in view of Robertson as applied to claims 1, 10, and 18 above, and further in view of Granot et al. (US 2020/0104146), hereinafter Granot. Regarding claim 2, modified Wilde teaches the method of claim 1 as described above. However, Wilde does not explicitly teach of generating titles for the recommendations. In a similar field of endeavor, Grano teaches of an assistor for suggesting steps for a user (see paragraph [0030]. Granot further teaches the following: the prompt further tasks the foundation model with generating titles for the follow-on prompts, and wherein displaying the suggestion components corresponding to the follow-on prompts comprises displaying the suggestion components labeled with the titles. As Granot teaches in paragraph [0005], a program constructs a list of end-goals based on prior user experience. Granot further teaches in paragraph [0052] that a list of end-goal textual titles is generated for presenting suggestions to the user. Further see Fig. 5A. It would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have modified the suggestions of Wilde with the end-goal titles of Granot. One of ordinary skill would have been motivated to have made such modification because the titles of Granot benefit users in relaying a determined possible goals of the user instead of simply titles of documents. Regarding claim 3, modified Wilde teaches the method of claim 2 as described above. Wilde further teaches the following: capturing the state of the content canvas further comprises capturing the state of the content canvas in response to detecting a change to the state of the content canvas. As Wilde teaches in paragraph [0039], events of a programmatic client may comprise words/phrases just typed by the user, suggesting that the content discovery captures data as the user enters/updates it. Further see paragraph [0052]. Regarding claim 4, modified Wilde teaches the method of claim 3 as described above. Wilde further teaches the following: in response to a second change in the state of the content canvas: capturing an updated state of the content canvas; and generating a third prompt for the foundation model including the updated state of the content canvas, wherein the third prompt tasks the foundation model with generating new suggestions for enhancements to the content based on the updated state of the content canvas. As Wilde teaches in paragraph [0075], suggestions are surfaced as the user types, i.e., the suggestions are updated as new content is added by the user. Regarding claims 11-13, modified Wilde teaches the apparatus of claim 10 as described above. The remaining limitations of claims 11-13 are substantially similar to those of claims 2-44 respectively, and are rejected using the same reasoning. Regarding claims 19 and 20, modified Wilde teaches the media of claim 18 as described above. The remaining limitations of claims 19 and 20 are substantially similar to those of claims 2 and 3 respectively, and are rejected using the same reasoning. Claim(s) 5-9 and 14-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wilde in view of Liu in view of Robertson in view of Granot as applied to claims 1-4 and 10-13 above, and further in view of Katahanas et al. (US 2024/0329802), hereinafter Katahanas. Regarding claim 5, modified Wilde teaches the method of claim 4 as described above. While Wilde teaches of a user creating/editing text, Wilde does not explicitly teach of a virtual whiteboard with virtual sticky notes. In a similar field of endeavor, Katahanas teaches of utilizing a learning model to analyze user entered text (see paragraph [0041]. Katahanas further teaches the following: the content canvas comprises a virtual whiteboard, wherein the content comprises content items, and wherein content items comprise virtual sticky notes. As Katahans teaches in the abstract, the method is directed to a virtual whiteboard and in paragraph [0034], users are able to create graphical objects such as sticky notes. It would have been obvious to one of ordinary skill in the art before the effective filing date of applicant’s claimed invention to have modified the canvas of Wilde with the whiteboard and sticky notes of Katahanas. One of ordinary skill would have been motivated to have made such modification because as Katahanas teaches in paragraph [0002], such graphical displays benefit users with a more flexible collaborative display. Regarding claim 6, modified Wilde teaches the method of claim 5 as described above. Wilde further teaches the following: the state of the content canvas comprises one or more of: text from the content items, authors of the content items, reactions to the content items, a placement of the content items relative to other content items on the content canvas, and content canvas metadata. As Wilde teaches in paragraph [0089], and corresponding Fig. 6, step 602, text on authored content is analyzed, where the authored content is interpreted as being a current “state”. Regarding claim 7, modified Wilde teaches the method of claim 6 as described above. Wilde further teaches the following: the contextual information further comprises a meeting state, wherein the meeting state comprises one or more of: a chat pane message, a meeting transcript, an elapsed time, and a calendar invite. As Wilde teaches in paragraph [0082], recommendations may be faded based on an amount of time from the authorship activity. Regarding claim 8, modified Wilde teaches the method of claim 7 as described above. Wilde further teaches the following: the contextual information further comprises a user state, wherein the user state comprises a viewport and user activity with respect to the content canvas. As Wilde teaches in paragraph [0055], the library of documents considered by the system is those documents which are publicly or privately accessible by the user (viewport). Wilde teaches in paragraph [0074] of leveraging contextual signals to improve relevant documents/content. Wilde further teaches in paragraph [0075], that content the user is typing is monitored (user activity). Regarding claim 9, modified Wilde teaches the method of claim 8 as described above. Wilde further teaches the following: the contextual information further comprises user feedback with respect to a suggestion generated by the foundation model. As Wilde teaches in paragraph [0028], user provide feedback to a platform and re-arranges or filters suggested documents based upon said feedback. Further see paragraph [0062]. Regarding claims 14-17, modified Wilde teaches the apparatus of claim 13 as described above. The remaining limitations of claims 14 -17 are substantially similar to those of claims 5 -8 respectively, and are rejected using the same reasoning. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. -Dumais et al. (US 2004/ 0267730), background searches based upon interaction of a user with an application. -Ayzenshtat et al. (US 10,185,748), intelligent auto completion which may apply to applicant’s amended limitations. Any inquiry concerning this communication or earlier communications from the examiner should be directed to GREGORY A DISTEFANO whose telephone number is (571)270-1644. The examiner can normally be reached Monday - Friday: 9 am - 5 pm. 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, William Bashore can be reached at 5712424088. 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. /GREGORY A. DISTEFANO/ Examiner Art Unit 2174 /WILLIAM L BASHORE/ Supervisory Patent Examiner, Art Unit 2174
Read full office action

Prosecution Timeline

Dec 05, 2023
Application Filed
Jul 09, 2025
Non-Final Rejection — §103
Oct 17, 2025
Applicant Interview (Telephonic)
Oct 17, 2025
Examiner Interview Summary
Nov 11, 2025
Response Filed
Nov 26, 2025
Final Rejection — §103
Feb 13, 2026
Applicant Interview (Telephonic)
Feb 13, 2026
Examiner Interview Summary
Mar 02, 2026
Request for Continued Examination
Mar 10, 2026
Response after Non-Final Action
Mar 20, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12591356
ELECTRONIC DEVICE FOR PERFORMING SCREEN CAPTURE AND METHOD FOR CAPTURING SCREEN BY ELECTRONIC DEVICE
2y 5m to grant Granted Mar 31, 2026
Patent 12585867
METHOD, SYSTEM, AND COMPUTING DEVICE FOR FACILITATING PRIVATE DRAFTING
2y 5m to grant Granted Mar 24, 2026
Patent 12566913
Artificial Intelligence Agents to Automate Multimodal Interface Task Workflows
2y 5m to grant Granted Mar 03, 2026
Patent 12541285
ELECTRONIC APPARATUS AND METHOD FOR OBTAINING A CAPTURE IMAGE THEREOF
2y 5m to grant Granted Feb 03, 2026
Patent 12530086
TRACTABLE BODY-BASED AR SYSTEM INPUT
2y 5m to grant Granted Jan 20, 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
69%
Grant Probability
92%
With Interview (+23.0%)
3y 8m
Median Time to Grant
High
PTA Risk
Based on 527 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