DETAILED ACTION
Claims 1 – 20, which are currently pending, are fully considered below.
No claims are amended.
No claims are added.
No claims are cancelled.
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 .
Response to Arguments
Applicant's arguments filed July 28, 2026 have been fully considered but they are not persuasive.
Applicant argues that Applicant's Specification teaches that "The prompt refinement datastore can store prompt analysis data and prompt refinement data corresponding to the prompt analysis data. By way of example, the prompt analysis data can include a natural-language analysis (e.g., critique) of a prompt and the corresponding refinement data for the prompt can include prompt refinements
(e.g., prompt edits) or an updated prompt generated based on the analysis of the prompt." (Applicant's Specification, paragraph [0058]) (remarks, pages 7 - 8).
Examiner disagrees, and responds that Kuan discloses that data is stored as part of a “digital analytics system” in paragraph [0036], which is equivalent to prompt analysis data.
Applicant argues that the Office Action further alleges that Kuan discloses the claimed machine-learned prompt refinement model at paragraph [0116] and Figure 5 (remarks, page 8).
Examiner disagrees, and responds that Kuan’s “code prompt generation engine” and “presentation prompt generation engine” combined, are equivalent to the instant “machine-learned prompt refinement model.”
Accordingly, this Office Action is made Final.
35 USC § 101
Note: Examiner has considered claims 1 – 20 with respect to 35 USC 101 and has determined that the claims recite significantly more than an abstract idea.
Claim Rejections - 35 USC § 102
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.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1 – 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Johnson Hao Wen Kuan (U.S. Patent Publication 20240362409).
With respect to claims 1, 13, and 20, Kuan teaches:
or more machine-learned generative models configured to generate one or more outputs in response to an input prompt (see paragraph [0029], where a prompt generation engine generates prompts optimized for input into a large language model, also see paragraph [0038], where an output is generated);
a prompt refinement datastore configured to store prompt analysis data and prompt refinement data for a plurality of prompts provided to the one or more machine-learned generative models (see paragraph [0036], where the data storage is included as part of the digital analytics system); and
a machine-learned prompt refinement model configured to receive an input including data indicative of a particular prompt issued to the machine-learned generative model, the machine-learned prompt refinement model configured to generate one or more outputs including prompt refinement data for the particular prompt based at least in part on the prompt analysis data and prompt refinement data in the prompt refinement datastore (see paragraph [0116] and Fig. 5, where the prompt generation engine uses inputs and refines prompts to produce outputs).
PNG
media_image1.png
666
428
media_image1.png
Greyscale
With respect to claim 2, Kuan teaches:
the input includes data indicative of an analysis of the output of the one or more machine-learned generative models in response to the particular prompt (see paragraph [0058], where the input is indicative of an output (the generated prompt)).
With respect to claim 3, Kuan teaches:
the prompt analysis data for each of the plurality of prompts includes data indicative of an analysis of the output of the one or more machine-learned generative models in response to a corresponding prompt (see paragraph [0058], where the input is indicative of an output (the generated prompt)); and
the prompt refinement data for each of the plurality of prompts includes data indicative of at least one edit to said each prompt in association with a corresponding prompt analysis (see paragraph [0053], where the prompt is updated (or edited)).
With respect to claim 4, Kuan teaches:
the analysis of the output of the one or more machine-learned generative models in response to the particular prompt is a natural language description associated with the output of the one or more machine-learned generative models (see paragraph [0037], for natural language descriptions with the output).
With respect to claim 5, Kuan teaches:
the natural language description is based on an output of a machine-learned rating model generated in response to an input including the output of the one or more machine-learned generative models in response to the particular prompt (see paragraph [0037], for natural language descriptions with the output, also see paragraph [0098], where the weights (for rating) of the machine learning model are output).
With respect to claim 6, Kuan teaches:
the machine-learned prompt refinement model is configured to perform semantic matching to identify one or more prompts in the prompt refinement datastore corresponding to the analysis of the output of the one or more machine-learned generative models in response to the particular prompt (see paragraph [0063], for semantics matching).
With respect to claim 7, Kuan teaches:
the machine-learned prompt refinement model is configured to generate the prompt refinement data for the particular prompt based at least in part on the prompt refinement data for the one or more prompts identified by semantic matching (see paragraph [0063], for semantics matching).
With respect to claim 8, Kuan teaches:
a prompt lineage datastore configured to store prompt change data indicative of changes to each of the plurality of prompts over time (see paragraphs [0053] and [0054], where the prompts are changed over time).
With respect to claim 9, Kuan teaches:
generating a user interface including a representation of one or more edits to the particular prompt from the prompt refinement data (see paragraph [0038], for the user interface);
receiving, via the user interface, user selection of at least one of the one or more edits (see paragraph [0053], where the prompt is updated (or edited));
generating an updated prompt based at least in part on the user selection of the at least one of the one or more edits (see paragraph [0058], where the input is indicative of an output (the generated prompt)); and
displaying, via the user interface, a response of the one or more machine-learned generative models to the updated prompt (see paragraph [0070, where the interface is displayed).
With respect to claim 10, Kuan teaches:
wherein the one or more machine-learned generative models includes a sequence processing model (see paragraph [0045], for sequences).
With respect to claim 11, Kuan teaches:
wherein the sequence processing model includes a large language model (see paragraph [0029], where a prompt generation engine generates prompts optimized for input into a large language model, also see paragraph [0038], where an output is generated).
With respect to claim 12, Kuan teaches:
wherein the machine-learned prompt refinement model includes a large language model (see paragraph [0029], where a prompt generation engine generates prompts optimized for input into a large language model, also see paragraph [0038], where an output is generated).
With respect to claim 14, Kuan teaches:
obtaining, by the computing system, prompt analysis data for the prompt; and providing, by the computing system, the prompt analysis data to the machine-learned prompt refinement model (see paragraph [0036], where the data storage is included as part of the digital analytics system).
With respect to claim 15, Kuan teaches:
wherein identifying, by the computing system from the datastore of prompt refinement data using the machine-learned prompt refinement model, the prompt refinement data matching the prompt data comprises: identifying prompt analysis data in the datastore that matches the prompt analysis data for the prompt (see paragraph [0036], where the data storage is included as part of the digital analytics system).
With respect to claim 16, Kuan teaches:
wherein: the prompt data includes data indicative of an analysis of the output of the machine-learned generative model in response to the prompt (see paragraph [0058], where the input is indicative of an output (the generated prompt)).
With respect to claim 17, Kuan teaches:
wherein: the datastore of prompt refinement data includes prompt analysis data for each of a plurality of prompts including data indicative of an analysis of an output of the machine-learned generative model in response to said each of the plurality of prompts (see paragraph [0058], where the input is indicative of an output (the generated prompt)); and
the datastore of prompt refinement data includes prompt refinement data for each of a plurality of prompts including data indicative of at least one edit to said each of the plurality of prompts in association with a corresponding prompt analysis (see paragraph [0053], where the prompt is updated (or edited)).
With respect to claim 18, Kuan teaches:
wherein: the analysis of the output of the one or more machine-learned generative models in response to said each of the plurality of prompts is a natural language description associated with the output of the machine-learned generative model (see paragraph [0037], for natural language descriptions with the output).
With respect to claim 19, Kuan teaches:
wherein: the natural language description is based on an output of a machine-learned rating model generated in response to an input including the output of the machine-learned generative model in response to said each of the plurality of prompts (see paragraph [0058], where the input is indicative of an output (the generated prompt)).
Conclusion
THIS ACTION IS MADE FINAL. 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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDRIA Y BROMELL whose telephone number is (571)270-3034. The examiner can normally be reached M-F 8-4.
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, Ajay Bhatia can be reached at 571-272-3906. 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.
/ALEXANDRIA Y BROMELL/Primary Examiner, Art Unit 2156 September 29, 2026
