CTNF 18/905,611 CTNF 84441 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia 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 07-42-04 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 1/2/2026 has been entered. Claims 1 – 20 are pending. Claim Rejections - 35 USC § 112 07-36 AIA The following is a quotation of 35 U.S.C. 112(d): (d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers. The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph: Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers. 07-36-01 AIA Claim 14 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Claim 14 recites “The method of claim 7, wherein the rubric engine comprises a generative artificial intelligence (Al) model”; however, claim 7 already recites limitation of a “GAI model” . Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1 – 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Step 1: Is the claimed invention a statutory category of invention? Claims 1, 7 and 15 are directed to a method / system / computer program for generating rubric (Step 1, Yes). Step 2A, Prong 1: Does the claim recite an abstract idea? The limitation of steps: … receive, from a client device via a graphical user interface (GUI), an indication to generate a rubric for an assignment; determine, by a rubric engine operatively coupled to a generative artificial intelligence (GAI) model, an assignment type for the assignment; determine, by the rubric engine, one or more evaluation criteria for the rubric based on the assignment type; determine, by the rubric engine, a rubric scale for the rubric; determine, by the rubric engine, audience context for the assignment; generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment, wherein: the rubric comprises one or more assessments for each of the one or more evaluation criteria across the rubric scale; the one or more assessments are modifiable by a user via the GUI on the client device; and generating the rubric for the assignment comprises: generating, by the rubric engine, a request prompt for the rubric, wherein the request prompt is configured to elicit a response from the Gai model and comprises the assignment type, the one or more evaluation criteria, the rubric scale, and the audience context; and submitting, by the rubric engine, the request prompt to the GAI model which generates the rubric responsive to receiving the request prompt; display, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments; and associate, by the rubric engine, the rubric with the assignment and a corresponding version history of the rubric as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. The claimed abstract idea akin performing mental observations, evaluations, and judgements. The mere nominal recitation of at least one processor performing these steps does not take the claim limitation outside of the mental processes grouping. Thus, the claim recites a mental process (Step 2A, Prong 1: yes). Step 2A, Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application? Per the 2019 Revised Patent Subject Matter Eligibility Guidance , if a claim as a whole integrates the recited judicial exception into a practical application of that exception, a claim is not "directed to" a judicial exception. Alternatively, a claim that does not integrate a recited judicial exception into a practical application is directed to the exception. Evaluating whether a claim integrates an abstract idea into a practical application is performed by a) identifying whether there are any additional elements recited in the claim beyond the abstract idea, and b) evaluating those additional elements individual and in combination to determine whether they integrate the abstract idea into a practical application, using one or more of the considerations laid out by the Supreme Court and the Federal Circuit. Exemplary considerations indicative that an additional element (or combination of elements) may have or has not been integrated into a practical application are set forth in the 2019 PEG With respect to the instant claims, claims 1, 7 and 15 recite the additional elements of: one or more computer readable storage media; one or more processors operatively coupled with the one or more computer readable storage media; a client device, a rubric engine (claim 1) ; a client device and a rubric engine (claim 7) and A computer readable storage media comprising processor-executable instructions configured to cause one or more processors (claim 15). The limitation of a rubric engine disclosed as being software module or program. As such, the claims are drawn to a computer program or software per se and are thus drawn to non-statutory subject matter. It is particularly noted that the use of processor and client device "as a tool" to perform an abstract method and steps that only amount to extra solution activity are indicated in the 2019 PEG as examples that an additional element has not been integrated into a practical application. Even in combination, the recited additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits, such as an improvement to a computing system, on practicing the abstract idea (STEP 2A, Prong 2: NO). Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception? Claims 1, 7 and 15 recite the additional elements of: one or more computer readable storage media; one or more processors operatively coupled with the one or more computer readable storage media; a client device, a rubric engine (claim 1) ; a client device and a rubric engine (claim 7) and A computer readable storage media comprising processor-executable instructions configured to cause one or more processors (claim 15) set forth above for Step 2A, Prong 2. Regarding these limitations: Applicant's specification describes these features in generic manner " The processor executes computer-executable program instructions stored in memory, such as executing one or more computer programs. Such processors may comprise a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), field programmable gate arrays (FPGAs), and state machines ” in the Applicant’s specification, para. [0086] – [0089]). “ The client devices 102, 104, and 106 communicate with application service 101 via one or more internets and intranets, the Internet, wired and wireless networks, local area networks (LANs), wide area networks (WANs), or any other type of network or combination thereof. Examples of the client devices 102, 104, and 106 may include personal computers, tablet computers, mobile phones, gaming consoles, wearable devices, Internet of Things (loT) devices, and any other suitable devices, of which computing system 1501 ” in the Applicant’s specification, para. [0032]). There is no indication in the Specification that Applicants have achieved an advancement or improvement in computer for education. Dependent claims 2 – 6, 8 – 14, 16 – 20 inherit the deficiencies of their respective parent claims through their dependencies and do not recite additional limitations sufficient to direct the claims to more than the claimed abstract idea, and are thus rejected for the same reasons. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. 07-21-aia AIA Claim s 1 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Delgado et al. (US 2024/0119855 A1) in view of Marahta et al. (US 2026/0087936 A1) . Re claims 1, 7 and 15: Delgado teaches 1. A system for generating a rubric using a rubric engine, the system comprising (Delgado, Abstract; fig. 1) : one or more computer readable storage media; one or more processors operatively coupled with the one or more computer readable storage media; and an application comprising program instructions stored on the one or more computer readable storage media that, when executed by the one or more processors (Delgado, [0144]; [0147]; fig. 1) , direct a computing system to at least: receive, from a client device via a graphical user interface (GUI), an indication to generate the rubric for an assignment (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question) ; determine, by the rubric engine, an assignment type for the assignment (Delgado, [0059], “The open-ended unstructured-text questions 106 can include secondary school questions, high school questions, entrance and standardized exam questions, college course questions (engineering, science, calculus, psychology, humanities), and professional exams (medical training)”; [0094], “selection of the problem types 354”; [0093], “select the desired test type”; [0018]; [0094], “Based on the selection of the problem types 354 … for a chemistry problem type”; [0060], “open-ended questions (e.g., essay)”; The instantiated template and rubric (e.g., 128a, 128b, 128c) may include a solver or a solver instance 136 to perform an intermediate mathematical operation (e.g., addition, subtraction, multiplication, division, exponential …”) ; determine, by the rubric engine, one or more evaluation criteria for the rubric based on the assignment type (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) ; determine, by the rubric engine, a rubric scale for the rubric (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) ; determine, by the rubric engine, audience context for the assignment (Delgado, [0059], “The tests 110 include open-ended unstructured-text questions 106, e.g., for topics in math, science, physics, chemistry, STEM, etc.”; [0093], “problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … the dialogue configuration box can be implemented as a wizard that allows the test developer to walk through a series of dialogue boxes to select the desired test type and/or grade/difficulty level”; [0094]; topics, grade level and difficulty level are audience contexts) ; generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment (Delgado, [0059], “The tests 110 include open-ended unstructured-text questions 106, e.g., for topics in math, science, physics, chemistry, STEM, etc.”; [0093], “problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … a series of dialogue boxes to select the desired test type and/or grade/difficulty level”; [0094]) , wherein: the rubric comprises one or more assessments for each of the one or more evaluation criteria across the rubric scale (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) ; the one or more assessments are modifiable by a user via the GUI on the client device (Delgado, [0060], “System 100 may maintain a library of open-ended unstructured-text question 106 and corresponding answer model 112 that can access and modified to generate new full tests, test templates, and new test library files”) ; and generating the rubric for the assignment comprises: generating, by the rubric engine, a request prompt for the rubric, wherein the request prompt is configured to elicit a response and comprises the assignment type (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]) , the one or more evaluation criteria (Delgado, Delgado, [0086]; [0021]; [0018]; [0094]) , the rubric scale (Delgado, [0012]), and the audience context (Delgado, [0059]; [0093]; [0094]) ; and submitting, by the rubric engine, the request prompt which generates the rubric responsive to receiving the request prompt (Delgado, figs. 3A – 3G; [0059], “"Exam Template and Rubric”) ; and display, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]; [0086]; [0021]; [0012]) ; and associate, by the rubric engine, the rubric with the assignment (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question); [0013], “a total partial credit or score value for the word problem by summing each matching set of one or more rubric response models to the consolidated scorable response model”; [0031], “the one or more rubric response models and the associated credit or score values are generated in a test development workspace”) . 7. A method for generating a rubric using a rubric engine, the method (Delgado, Abstract) comprising: receiving, from a client device via a graphical user interface (GUI), an indication to generate the rubric for an assignment (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question) ; determining, by the rubric engine, an assignment type for the assignment (Delgado, [0059], “The open-ended unstructured-text questions 106 can include secondary school questions, high school questions, entrance and standardized exam questions, college course questions (engineering, science, calculus, psychology, humanities), and professional exams (medical training)”; [0094], “selection of the problem types 354”; [0093], “select the desired test type”; [0018]; [0094], “Based on the selection of the problem types 354 … for a chemistry problem type”; [0060], “open-ended questions (e.g., essay)”; The instantiated template and rubric (e.g., 128a, 128b, 128c) may include a solver or a solver instance 136 to perform an intermediate mathematical operation (e.g., addition, subtraction, multiplication, division, exponential …”) ; determining, by the rubric engine, one or more evaluation criteria for the rubric based on the assignment type (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) ; determining, by the rubric engine, a rubric scale for the rubric (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) ; determining, by the rubric engine, audience context for the assignment (Delgado, [0059], “The tests 110 include open-ended unstructured-text questions 106, e.g., for topics in math, science, physics, chemistry, STEM, etc.”; [0093], “problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … the dialogue configuration box can be implemented as a wizard that allows the test developer to walk through a series of dialogue boxes to select the desired test type and/or grade/difficulty level”; [0094]; topics, grade level and difficulty level are audience contexts) ; generating, by the rubric engine, the rubric for the assignment based on the evaluation criteria and the audience context for the assignment (Delgado, [0059], “The tests 110 include open-ended unstructured-text questions 106, e.g., for topics in math, science, physics, chemistry, STEM, etc.”; [0093], “problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … a series of dialogue boxes to select the desired test type and/or grade/difficulty level”; [0094]) , wherein: the rubric comprises one or more assessment for each of the one or more evaluation criteria across the rubric scale (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) ; the one or more assessments are modifiable by a user via the GUI on the client device (Delgado, [0060], “System 100 may maintain a library of open-ended unstructured-text question 106 and corresponding answer model 112 that can access and modified to generate new full tests, test templates, and new test library files”) ; and generating the rubric for the assignment comprises: generating, by the rubric engine, a request prompt for the rubric, wherein the request prompt is configured to elicit a response and comprises the assignment type (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]) , the one or more evaluation criteria (Delgado, Delgado, [0086]; [0021]; [0018]; [0094]) , the rubric scale (Delgado, [0012]), and the audience context (Delgado, [0059]; [0093]; [0094]) ; and submitting, by the rubric engine, the request prompt which generates the rubric responsive to receiving the request prompt (Delgado, figs. 3A – 3G; [0059], “"Exam Template and Rubric”) ; and displaying, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]; [0086]; [0021]; [0012]) ; and associating, by the rubric engine, the rubric with the assignment (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question); [0013], “a total partial credit or score value for the word problem by summing each matching set of one or more rubric response models to the consolidated scorable response model”; [0031], “the one or more rubric response models and the associated credit or score values are generated in a test development workspace”). 15. A computer readable storage media comprising processor-executable instructions configured to cause one or more processors (Delgado, Abstract) to: receive, from a client device via a graphical user interface (GUI), an indication to generate a rubric for an assignment (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question) ; determine, by a rubric engine, an assignment type for the assignment (Delgado, [0059], “The open-ended unstructured-text questions 106 can include secondary school questions, high school questions, entrance and standardized exam questions, college course questions (engineering, science, calculus, psychology, humanities), and professional exams (medical training)”; [0094], “selection of the problem types 354”; [0093], “select the desired test type”; [0018]; [0094], “Based on the selection of the problem types 354 … for a chemistry problem type”; [0060], “open-ended questions (e.g., essay)”; The instantiated template and rubric (e.g., 128a, 128b, 128c) may include a solver or a solver instance 136 to perform an intermediate mathematical operation (e.g., addition, subtraction, multiplication, division, exponential …”) ; determine, by the rubric engine, one or more evaluation criteria for the rubric based on the assignment type (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) ; determine, by the rubric engine, a rubric scale for the rubric (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) ; determine, by the rubric engine, audience context for the assignment (Delgado, [0059], “The tests 110 include open-ended unstructured-text questions 106, e.g., for topics in math, science, physics, chemistry, STEM, etc.”; [0093], “problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … the dialogue configuration box can be implemented as a wizard that allows the test developer to walk through a series of dialogue boxes to select the desired test type and/or grade/difficulty level”; [0094]; topics, grade level and difficulty level are audience contexts) ; generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment (Delgado, [0059], “The tests 110 include open-ended unstructured-text questions 106, e.g., for topics in math, science, physics, chemistry, STEM, etc.”; [0093], “problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … a series of dialogue boxes to select the desired test type and/or grade/difficulty level”; [0094]) , wherein: the rubric comprises one or more assessments for each of the one or more evaluation criteria across the rubric scale (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) ; the one or more assessments are modifiable by a user via the GUI on the client device (Delgado, [0060], “System 100 may maintain a library of open-ended unstructured-text question 106 and corresponding answer model 112 that can access and modified to generate new full tests, test templates, and new test library files”) ; and generating the rubric for the assignment comprises: generating, by the rubric engine, a request prompt for the rubric, wherein the request prompt is configured to elicit a response and comprises the assignment type (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]) , the one or more evaluation criteria (Delgado, Delgado, [0086]; [0021]; [0018]; [0094]) , the rubric scale (Delgado, [0012]), and the audience context (Delgado, [0059]; [0093]; [0094]) ; and submitting, by the rubric engine, the request prompt which generates the rubric responsive to receiving the request prompt (Delgado, figs. 3A – 3G; [0059], “"Exam Template and Rubric”) ; and display, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]; [0086]; [0021]; [0012]) ; and associate, by the rubric engine, the rubric with the assignment (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question); [0013], “a total partial credit or score value for the word problem by summing each matching set of one or more rubric response models to the consolidated scorable response model”; [0031], “the one or more rubric response models and the associated credit or score values are generated in a test development workspace”) . Marahta does not explicitly disclose determine, by a rubric engine operatively coupled to a generative artificial intelligence (GAI) model … generating, by the rubric engine, a request prompt for the rubric, wherein the request prompt is configured to elicit a response from the GAI model … a corresponding version history of the rubric. Marahta teaches a dialogue system presents questions and learning content, assesses the responses provided by the user and presents tailored further questions and content based on the assessment (Marahta, Abstract). Marahta teaches determine, by a rubric engine operatively coupled to a generative artificial intelligence (GAI) model (Marahta, Abstract, “language model”; [0138], “the generative LM”; [0258]) , an assignment type for the assignment (Marahta, [0206], “The LM 155 will also generate scoring rubrics based on the expected answers, detailing how points should be allocated for correct or partial answers”; [0243]; [0208], “the assessment items will vary according to the type, for example, Multiple-Choice Questions (MCQs), fill-in-the-blanks, and true-false statements used in assessments . The primary objective is to guarantee the accuracy, relevance, and fairness of test items through rigorous double-checking processes. To cold start the skill assessment module 120, the skill assessment module 120 can leverage prompt engineering techniques to instruct LLM 155 to generate a diverse array of test items ”; [0541], “A prompt schema created in prompt engineering may include contextual examples within the prompt to assist the language model in generation of content”; [0210] – [0212], “Detailed instructions on how to award points for each question, which helps standardize grading and provides feedback mechanisms … Each test item comes with metadata, including its relevancy to certain topics, the skills it tests, its difficulty level, and any alignment with educational standards”) … comprises: generating, by the rubric engine, a request prompt for the rubric, wherein the request prompt is configured to elicit a response from the GAI model and comprises the assignment type, the one or more evaluation criteria, the rubric scale, and the audience context (Marahta, figs. 2A – 2B; [0208], “the assessment items will vary according to the type, for example, Multiple-Choice Questions (MCQs), fill-in-the-blanks, and true-false statements used in assessments. The primary objective is to guarantee the accuracy, relevance, and fairness of test items through rigorous double-checking processes. To cold start the skill assessment module 120, the skill assessment module 120 can leverage prompt engineering techniques to instruct LLM 155 to generate a diverse array of test items”) ; and submitting, by the rubric engine, the request prompt to the GAI model which generates the rubric responsive to receiving the request prompt (Marahta, [0206], “The LM 155 will also generate scoring rubrics based on the expected answers, detailing how points should be allocated for correct or partial answers”) ; display, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments (Marahta, Abstract, “language model”; [0138], “the generative LM”; [0258]; [0206], “The LM 155 will also generate scoring rubrics based on the expected answers, detailing how points should be allocated for correct or partial answers”; [0243]; [0208], “the assessment items will vary according to the type, for example, Multiple-Choice Questions (MCQs), fill-in-the-blanks, and true-false statements used in assessments … instruct LLM 155 to generate a diverse array of test items”; [0541], “A prompt schema created in prompt engineering may include contextual examples within the prompt to assist the language model in generation of content”) ; and associate, by the rubric engine, the rubric with the assignment and a corresponding version history of the rubric (Marahta, [0239], “A report on item performance, including items flagged for potential removal or revision will be then generated”; [0475], “a new entry may be created, but if a newer version of an existing resource is created, the existing resource entry may be updated/replaced”; [0498], “perform version control for the generated questions, in which validators are queried to validate newly added questions”; [0509]; [0511], “adding a new resource/question/answer version to the system”) . Therefore, in view of Marahta, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method and computer program described in Delgado, by providing GAI model to generate question and rubric and version history taught by Marahta, since using transformer models the answers of a user may be provided within a much wider context that enables the generation of questions that are more targeted toward the user's interactions with the LLM, based on free-form text answers, and thus provide a more accurate assessment of any changing skill level of the user and thus generate targeted questions to accurately assess that change in skill level. This allows for a focused assessment during the digital coaching session that can quickly and accurately track the user's change in skill with minimal interruption to the user's learning experience. This expands the range of skill assessment options available for the user (Marahta, [0106]). The content generation module may be configured to perform version control for the generated schemas, in which validators are queried to validate newly added schema (Marahta, [0544]). Re claims 2, 16: 2. The system of claim 1, wherein the program instructions to generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment cause (Delgado, [0026]; [0061]; [0064]) , when executed by the one or more processors, to further direct the computing system to: receive, by the rubric engine, a selection on a level of detail for the one or more assessments for each of the one or more evaluation criteria across the rubric scale (Delgado, fig. 3A; fig. 3B, “Step 1 … Step 6 … Answer”; each step includes a partial credit or score value; fig. 2C, “Step 1: 0.75”; “Step 2: 0.75”; “Step 3: 0.5”; total score: 2; the score depends on the detail of the student answer) ; and generate, by the rubric engine, the one or more assessments based on the selection, wherein each of the one or more assessments corresponds to a respective evaluation criteria of the one or more evaluation criteria and a respective scale factor on the rubric scale (Delgado, fig. 3A; fig. 3B, “Step 1 … Step 6 … Answer”; each step includes a partial credit or score value; fig. 2C, “Step 1: 0.75”; “Step 2: 0.75”) . 16. The computer readable storage media of claim 15, wherein the processor-executable instructions to generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]; [0086]; [0021]; [0012]) cause the one or more processors to further execute processor-executable instructions stored in the computer readable storage media to: receive, by the rubric engine, a selection on a level of detail for the one or more assessments for each of the one or more evaluation criteria across the rubric scale (Delgado, fig. 3A; fig. 3B, “Step 1 … Step 6 … Answer”; each step includes a partial credit or score value; fig. 2C, “Step 1: 0.75”; “Step 2: 0.75”; “Step 3: 0.5”; total score: 2; the score depends on the detail of the student answer) ; and generate, by the rubric engine, the one or more assessments based on the selection, wherein each of the one or more assessments corresponds to a respective evaluation criteria of the one or more evaluation criteria and a respective scale factor on the rubric scale (Delgado, fig. 3A; fig. 3B, “Step 1 … Step 6 … Answer”; each step includes a partial credit or score value; fig. 2C, “Step 1: 0.75”; “Step 2: 0.75”) . Re claim 3: 3. The system of claim 1, wherein the program instructions to determine, by the rubric engine, the one or more evaluation criteria for the rubric based on the assignment type cause (Delgado, [0086]; [0021]; [0018]; [0094]) , when executed by the one or more processors, to further direct the computing system to: submit, by the rubric engine, a request prompt to a content generator (Delgado, [0086]; [0021]; [0018]; [0094]) , wherein the request prompt comprises: assignment instructions for the assignment to a content generator (Delgado, [0059], “The open-ended unstructured-text questions 106 can include secondary school questions, high school questions, entrance and standardized exam questions, college course questions (engineering, science, calculus, psychology, humanities), and professional exams (medical training)”; [0094], “selection of the problem types 354”; [0093], “select the desired test type”; [0018]; [0094], “Based on the selection of the problem types 354 … for a chemistry problem type”; [0060], “open-ended questions (e.g., essay)”; The instantiated template and rubric (e.g., 128a, 128b, 128c) may include a solver or a solver instance 136 to perform an intermediate mathematical operation (e.g., addition, subtraction, multiplication, division, exponential …”)) ; and a request for evaluation criteria based on the assignment instructions (Delgado, [0086]; [0021]; [0018]; [0094]) ; and receive, by the rubric engine, the one or more evaluation criteria for the rubric based on the assignment instructions from the content generator (Delgado, [0060], “provides a graphical user interface to receive inputs from an exam developer/teacher to generate test questions, structure an exam, and create rubric answers for the generated test questions”) . Re claims 5, 18: 5. The system of claim 1, wherein the program instructions to determine, by the rubric engine, the one or more evaluation criteria for the rubric based on the assignment type cause, when executed by the one or more processors, to further direct the computing system to: generate, by the rubric engine, one or more recommended evaluation criteria; provide, by the rubric engine, the one or more recommended evaluation criteria to the client device; and receive, by the rubric engine, a selection of a first evaluation criteria from the one or more recommended evaluation criteria (Delgado, [0033], “the system further includes a data store configured to store a library of template or example word problems and associated rubric solutions”; [0059], “exam developer/teacher to develop questions 106 (shown as 106a, 106b, 106c) and answer rubrics 108 (shown as 108a, 108b, 108c) for tests 110 (shown as “Exam Template and Rubric 1” 110a, “Exam Template and Rubric 2” 110b, and “Exam Template and Rubric n” 110c) comprising the open-ended unstructured-text question 106”; [0060], “a library of open-ended unstructured-text question 106 and corresponding answer model 112 that can access and modified to generate new full tests, test templates, and new test library files”; [0061], “testing workflow module 126 configured to generate a workspace for a plurality of exam instances 128 (e.g., 128a, 128b, 128c) of a selected template and rubric 110 (shown as 110′). Each instantiated template and rubric (e.g., 128a, 128b, 128c) can include an instantiated answer model 130 and a question model 132 for each exam taker/student 134”; Exam template/library includes question template, answer template, answer rubrics ( recommended ) template) . 18. The computer readable storage media of claim 15, wherein the processor-executable instructions to determine, by the rubric engine, one or more evaluation criteria for the rubric based on the assignment type cause the one or more processors to further execute processor-executable instructions stored in the computer readable storage media to: generate, by the rubric engine, one or more recommended evaluation criteria; provide, by the rubric engine, the one or more recommended evaluation criteria to the client device; and receive, by the rubric engine, a selection of a first evaluation criteria from the one or more recommended evaluation criteria (Delgado, [0033], “the system further includes a data store configured to store a library of template or example word problems and associated rubric solutions”; [0059], “exam developer/teacher to develop questions 106 (shown as 106a, 106b, 106c) and answer rubrics 108 (shown as 108a, 108b, 108c) for tests 110 (shown as “Exam Template and Rubric 1” 110a, “Exam Template and Rubric 2” 110b, and “Exam Template and Rubric n” 110c) comprising the open-ended unstructured-text question 106”; [0060], “a library of open-ended unstructured-text question 106 and corresponding answer model 112 that can access and modified to generate new full tests, test templates, and new test library files”; [0061], “testing workflow module 126 configured to generate a workspace for a plurality of exam instances 128 (e.g., 128a, 128b, 128c) of a selected template and rubric 110 (shown as 110′). Each instantiated template and rubric (e.g., 128a, 128b, 128c) can include an instantiated answer model 130 and a question model 132 for each exam taker/student 134”; Exam template/library includes question template, answer template, answer rubrics ( recommended ) template) . Re claim 6: 6. The system of claim 1, wherein the program instructions cause, when executed by the one or more processors, to further direct the computing system to: receive, by the rubric engine, a completed assignment (Delgado, fig. 3B – 3G) ; provide, by the rubric engine, the rubric associated with the completed assignment to the client device (Delgado, [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0059], “an interface for an exam developer/teacher to develop questions 106 (shown as 106a, 106b, 106c) and answer rubrics 108 (shown as 108a, 108b, 108c) for tests 110 (shown as "Exam Template and Rubric 1" 110a, "Exam Template and Rubric 2" 110b, and "Exam Template and Rubric n" 110c) comprising the open-ended unstructured- text question 106”) ; receive, by the rubric engine, selection of one or more assessments for the one or more evaluation criteria from the client device (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) ; and generate, by the rubric engine, an overall assessment of the completed assignment (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”; [0073], “the aggregated score for a given question, or the total score for the test to a report”) . Re claim 9: 9. The method of claim 7, wherein generating, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment comprises: receiving, by the rubric engine, the rubric from the GAI model responsive to submitting the request prompt, wherein at least one of the one or more assessments within the rubric is presented to the user for optional modification prior to finalization (Delgado, fig. 3A; 3B; [0079] – [0080], “an example computerized test development environment and interface 300 … preview pane 304 is configured to take the user input provided into the input workspace (e.g., 302) to present the open-ended unstructured-text question (e.g., 106) to the test developer. The answer workspace 306 may correspond to the input … button 310 to add a dynamic element (also previously referred to as a "selectable displayed element" 204a or "operand") to the input workspace or to modify a selected static text into a dynamic element”; the generated question can be previewed and modified by the test developer; Marahta, Abstract, “language model”; [0138], “the generative LM”; [0258]) . Re claims 11, 13: 11. The method of claim 7, wherein generating, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment further comprises: determining, by the rubric engine, a point-value for each scale factor of the rubric scale; and assigning, by the rubric engine, a respective point-value to each scale factor of the rubric scale within the rubric (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”; [0073], “the aggregated score for a given question, or the total score for the test to a report”) . 13. The method of claim 7, wherein generating, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment further comprises: determining, by the rubric engine, a point-value for each scale factor of the rubric scale; and assigning, by the rubric engine, a respective point-value to each scale factor of the rubric scale within the rubric (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total, which would be 0.75 points for each partial credit step”; [0073], “the aggregated score for a given question, or the total score for the test to a report”) ; and the method further comprises: identifying, by the rubric engine, a completed assignment associated with the rubric (Delgado, [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0059], “an interface for an exam developer/teacher to develop questions 106 (shown as 106a, 106b, 106c) and answer rubrics 108 (shown as 108a, 108b, 108c) for tests 110 (shown as "Exam Template and Rubric 1" 110a, "Exam Template and Rubric 2" 110b, and "Exam Template and Rubric n" 110c) comprising the open-ended unstructured- text question 106”) ; receiving, by the rubric engine, selection of one or more assessments for the one or more evaluation criteria from the client device (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) ; determining, by the rubric engine, the point-value associated with each selected assessment; and generating, by the rubric engine, an overall assessment of the completed assignment, wherein the overall assessment comprises an aggregation of the point-values of the selected assessments (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”; [0073], “the aggregated score for a given question, or the total score for the test to a report”) . Re claims 4, 8, 17: 4. The system of claim 1, wherein the program instructions to generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment cause, when executed by the one or more processors, to further direct the computing system to: generate, by the rubric engine, a first draft rubric based on the one or more evaluation criteria and the audience context for the assignment, wherein the first draft rubric comprises a first set of evaluation criteria across a first rubric scale (Delgado, [0033], “store a library of template or example word problems and associated rubric solutions”; [0059], “Exam Template and Rubric 1”; [0060], “Test data store 124 can store a programmed test template and/or rubric 110”; template rubric – first draft rubric) ; receive, by the rubric engine, a modification to a first assessment within the first draft rubric (Delgado, [0032], “a plurality of input rubric field”; [0086], “each input field (e.g., 316a-316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0084], “Process 311 may then execute a loop (315), e.g., for the question development module 116 and rubric development module 118 of FIG. 1, to monitor for specific events, including … detection of a rubric modification operation (323)”) ; and generate, by the rubric engine, the rubric comprising the one or more evaluation criteria across the rubric scale based on the first draft rubric and the modification (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) . 8. The method of claim 7, wherein generating, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment comprises: generating, by the rubric engine, a first draft rubric based on the one or more evaluation criteria and the audience context for the assignment, wherein the first draft rubric comprises a first set of evaluation criteria across a first rubric scale; receiving, by the rubric engine, a modification to at least one of the first set of evaluation criteria or the first rubric scale (Delgado, [0032], “a plurality of input rubric field”; [0086], “each input field (e.g., 316a-316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0084], “Process 311 may then execute a loop (315), e.g., for the question development module 116 and rubric development module 118 of FIG. 1, to monitor for specific events, including … detection of a rubric modification operation (323)”) ; and generating, by the rubric engine, the rubric comprising the one or more evaluation criteria across the rubric scale based on the first draft rubric and the modification (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) . 17. The computer readable storage media of claim 15, wherein the processor-executable instructions to generate, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment cause the one or more processors to further execute processor-executable instructions stored in the computer readable storage media to: generate, by the rubric engine, a first draft rubric based on the one or more evaluation criteria and the audience context for the assignment, wherein the first draft rubric comprises a first set of evaluation criteria across a first rubric scale; receive, by the rubric engine, an indication to add a new evaluation criteria to the first set of evaluation criteria (Delgado, [0032], “a plurality of input rubric field”; [0086], “each input field (e.g., 316a-316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0084], “Process 311 may then execute a loop (315), e.g., for the question development module 116 and rubric development module 118 of FIG. 1, to monitor for specific events, including … detection of a rubric modification operation (323)”) ; generate, by the rubric engine, a plurality of new assessments for the new evaluation criteria across the rubric scale (Delgado, [0074], “detection of an add-line or select line command (224), detection of an "=" operand being selected (226)”; [0071], “add other response models (e.g., add new lines)”; fig. 2A, “the new/selected line”) ; and generate, by the rubric engine, the rubric based on the first draft rubric and the new evaluation criteria, wherein the one or more evaluation criteria comprise the new evaluation criteria (Delgado, [0086], “The workspace may include multiple input fields 316 (shown as "Line 1" 316a, "Line 2" 316b, "Line 3" 316c, and "Line n" 316d) in which each input field (e.g., 316a- 316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0021], “the test development workspace includes a plurality of input rubric fields to receive the one or more rubric response models and the associated credit or score values”; [0018]; [0094]) . Re claim 10: 10. The method of claim 7, wherein generating, by the rubric engine, the rubric for the assignment based on the one or more evaluation criteria and the audience context for the assignment further comprises: receiving, by the rubric engine, a selection on a level of detail for the one or more assessments for each of the one or more evaluation criteria across the rubric scale (Delgado, [0095], “FIG. 3G also shows input for the interface to set the significant digit or decimal rounding for the provided answer”; digital or rounding is a level of detail; col. 11, table 1, “correct number of significant figures”; [0122]) ; and generating, by the rubric engine, the one or more assessments based on the selection, wherein each of one or more assessments corresponds to a respective evaluation criteria of the one or more evaluation criteria and a respective scale factor on the rubric scale (Delgado, [0012], “partial credit or score value associated with at least one of the set of one or more rubric response models”; [0077], “FIGS. 2C and 2D show two methods for scoring the answer model of FIGS. 2A and 2B, e.g., by weighted grading or by fine-grained grading. The scoring may be based on integer, fraction, or any value expression. The partial credit for a solution step could be a fraction of the total score for a correct answer. For example, a four step problem could assign a total value for a correct score as 3 points, and specify that each partial credit is 25% of the total , which would be 0.75 points for each partial credit step”) . Re claim 12: 12. The method of claim 7, wherein determining, by the rubric engine, the one or more evaluation criteria for the rubric comprises: generating, by the rubric engine, a request prompt for generation of the one or more evaluation criteria (Delgado, [0059]; [0093]; [0018]; [0094]; [0060]) , wherein the request prompt comprises: assignment instructions for the assignment to a content generator; and a request for evaluation criteria based on the assignment instructions (Delgado, figs. 3A – 3G; [0059], “"Exam Template and Rubric”) ; and submit, by the rubric engine, the request prompt to a content generator, wherein the content generator generates the one or more evaluation criteria for the rubric based on the assignment instructions from the content generator (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question); [0013], “a total partial credit or score value for the word problem by summing each matching set of one or more rubric response models to the consolidated scorable response model”; [0031], “the one or more rubric response models and the associated credit or score values are generated in a test development workspace”) . Re claim 14: 14. The method of claim 7, wherein the rubric engine comprises a generative artificial intelligence (Al) model (Marahta, Abstract, “language model”; [0138], “the generative LM”; [0258]) . Re claim 19: 19. The computer readable storage media of claim 15, wherein the processor-executable instructions cause the one or more processors to further execute processor-executable instructions stored in the computer readable storage media to: responsive to receiving, from the client device, the indication to generate the rubric, determine, by the rubric engine, one or more recent rubrics (Delgado, [0033], “the system further includes a data store configured to store a library of template or example word problems and associated rubric solutions”; [0059], “exam developer/teacher to develop questions 106 (shown as 106a, 106b, 106c) and answer rubrics 108 (shown as 108a, 108b, 108c) for tests 110 (shown as “Exam Template and Rubric 1” 110a, “Exam Template and Rubric 2” 110b, and “Exam Template and Rubric n” 110c) comprising the open-ended unstructured-text question 106”) ; and provide, by the rubric engine, the one or more recent rubrics to the client device (Delgado, [0059], “exam developer/teacher to develop questions 106 (shown as 106a, 106b, 106c) and answer rubrics 108 (shown as 108a, 108b, 108c) for tests 110 (shown as “Exam Template and Rubric 1” 110a, “Exam Template and Rubric 2” 110b, and “Exam Template and Rubric n” 110c) comprising the open-ended unstructured-text question 106”)) . Re claim 20: 20. The computer readable storage media of claim 15, wherein the processor-executable instructions cause the one or more processors to further execute processor-executable instructions stored in the computer readable storage media to: save, by the rubric engine, the rubric to a rubric database at a first time (Delgado, figs. 3A – 3G; [0059], "Exam Template and Rubric”; fig. 1, “Exam Template and Rubric 1”) ; receive, by the rubric engine, an indication to generate a second rubric at a second time (Delgado, fig. 1, “Exam Template and Rubric 2”) ; receive, by the rubric engine, a selection of the rubric from the rubric database (Delgado, fig. 2A) ; modify, by the rubric engine, the rubric based on input from a client device (Delgado, [0032], “a plurality of input rubric field”; [0086], “each input field (e.g., 316a-316d) has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination”; [0084], “Process 311 may then execute a loop (315), e.g., for the question development module 116 and rubric development module 118 of FIG. 1, to monitor for specific events, including … detection of a rubric modification operation (323)”) ; and generate, by the rubric engine, the second rubric based on the input from the client device (Delgado, [0032]; [0084]) . Response to Arguments 07-37 AIA Applicant's arguments filed 1/2/2026 have been fully considered but they are not persuasive. Applicant argues: Specifically, claim 1 as amended herein recites, in part, "a rubric engine operatively coupled to a generative artificial intelligence (GAI) model," wherein a "request prompt is configured to elicit a response from the GAI model," and the request prompt is submitted "to the GAI model which generates the rubric responsive to receiving the request prompt." These are computer-centric operations, not mental steps, and cannot be performed by the human mind. For example, a human cannot be "operatively coupled to a GAI model." … The human mind cannot use a GUI to perform these tasks, as this requires execution of programmed interface logic, rendering of dynamic layouts, and interaction with underlying software modules that process rubric content in real time. The Examiner respectfully disagrees. The claims apply the abstract idea on a computer by replacing the human intermediary with a GUI. The claims merely recite generic and conventional computer components (i.e., “The assignment prompt 520 may be part of a graphical user interface (GUI) provided via the client device 306 to an educator for generating the assignment 320. As shown, the assignment prompt 520 includes an input field for an assignment title 521, into which the educator can input a desired title for the assignment 320”) and functionality for "carrying out" the abstract idea. The claimed/disclosed GUI, which is utilized as a tool to facilitate one or more basic functions (e.g., receive, from a client device via a graphical user interface (GUI) … the one or more assessments are modifiable by a user via the GUI on the client device … display, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments … ), does not constitute a technological improvement over the existing computer/network technology. All of which are well-known in the prior art. See, e.g., the CAFC's opinion in CXLoyalty, Inc. v. Maritz Holdings Inc. slip. op., pages 16-17. As such, the argument is not persuasive. Applicant argues: The technical improvements include: 1. Operative Coupling to GAI Model The rubric engine is operatively coupled to a GAI model and submits structured prompts configured to elicit targeted rubric content based on assignment metadata and audience context. This is a machine-to-machine integration and, under USPTO guidance, indicates practical application when AI is used to solve a technical problem rather than merely "apply the concept." The claimed process using Generative Artificial Intelligent (GAI) to generate the rubric provides no indication that the functioning of the computer is improved. Applicant does not explain how the use of AI would somehow improve the computer’s function. Rather, it appears that the claim merely utilizes conventional computer functions of receiving user prompt, analysis and generate rubric using AI models. Instead, each of the claimed GAI with some automation algorithm to generate a rubric based on some parameters (i.e., the assignment type, the one or more evaluation criteria, the rubric scale, and the audience context ). Additionally, it has been held that “claims that do no more than apply established methods of machine learning to a new data environment are [not] patent eligible.” Recentive Analytics, Inc. v. Fox Corp. , 134 F.4th 1205, 1211 (Fed. Cir. 2025). Applicant argues: Claim 1 recites receiving the generation indication via a GUI; displaying the rubric in a structured format that adjusts based on evaluation criteria, rubric scale, and assessments; and enabling user modifications. This mirrors the GUI improvement pattern recognized in Example 37 (rearranging icons by use metrics). Here, the GUI is not a generic output screen; rather, it transforms displayed information based on system conditions. The Examiner respectfully disagrees. The claims apply the abstract idea on a computer by replacing the human intermediary with a GUI. The claims merely recite generic and conventional computer components (i.e., “The assignment prompt 520 may be part of a graphical user interface (GUI) provided via the client device 306 to an educator for generating the assignment 320. As shown, the assignment prompt 520 includes an input field for an assignment title 521, into which the educator can input a desired title for the assignment 320”) and functionality for "carrying out" the abstract idea. The claimed/disclosed GUI, which is utilized as a tool to facilitate one or more basic functions (e.g., receive, from a client device via a graphical user interface (GUI) … the one or more assessments are modifiable by a user via the GUI on the client device … display, via the GUI on the client device, the rubric in a structured format that adjusts based on the one or more evaluation criteria, the rubric scale, and the one or more assessments … ), does not constitute a technological improvement over the existing computer/network technology. All of which are well-known in the prior art. See, e.g., the CAFC's opinion in CXLoyalty, Inc. v. Maritz Holdings Inc. slip. op., pages 16-17. As such, the argument is not persuasive. Applicant argues: Version Management The system associates the rubric with the assignment and a corresponding version history of the rubric, allowing educators to switch or scroll among versions for reproducibility and rollback. This version-managed association is a computing system improvement to rubric management, ensuring consistent grading, auditability, and efficient reuse/modification, all within the platform's architecture. The examiner respectfully submits that labeling a content by versions have been known before the use of the existing computer technology. In this regard, neither the claims nor the original specification describes any advanced algorithm to label a rubric version. Furthermore, the alleged advantages / improvements: i.e., improvement to rubric management, ensuring consistent grading, auditability, and efficient reuse/modification are not recited in the original specification . See Mayo , 566 U.S. at 72–73 (requiring “a process that focuses upon the use of a natural law also contain other elements or a combination of elements, sometimes referred to as an ‘inventive concept,’ sufficient to ensure that the patent in practice amounts to significantly more than a patent upon the natural law itself” (emphasis added)); BSG Tech. LLC v. Buyseasons, Inc ., 899 F.3d 1281, 1290 (Fed. Cir. 2018) (“It has been clear since Alice that a claimed invention’s use of the ineligible concept to which it is directed cannot supply the inventive concept that renders the invention ‘significantly more’ than that ineligible concept.”). Applicant argues: Structured Prompt Logic The request prompt imposes functional constraints on the GAi model (assignment type, evaluation criteria, rubric scale, audience context), yielding context-aligned outputs rather than generic text. The 2019 PEG and 2024 AI Update emphasize that such specific, technical use of AI to solve a field-specific computing problem (here, rubric generation at scale) is directed toward practical application. The Office maintains that customizing questions using parameters (multiple-choice, step-by-step), evaluation criteria (correct/incorrect, acceptable answer), rubric scale (partial credit, subscore) and audience context (difficulty, grade level), are inherently human actions that predate the invention of computer systems. For instance, school teachers have historically designed exams tailored to various student abilities. It is the Office’s position is that the instant claims include mental process of determining an assignment type / evaluation criteria / a rubric scale / audience context; generating the rubric for the assignment; generating a request prompt for the rubric wherein the request prompt comprises the assignment type, the one or more evaluation criteria, the rubric scale, and the audience context. In the instant case, the hardware so claimed is merely used as an tool to create an assignment based on user prompts; and no improvement on how the hardware carry out data functions is claimed; only processes of data collection (prompts), analysis (modify assignments based on the prompt) and associating assignment with the defined rubric are provided for. Applicant argues: The Applicant asserts in the response dated July 31, 2025 that this inventive concept is analogous to DDR Holdings v. Hotels.com, 773 F.3d 1245 (Fed. Cir. 2014). The Examiner responds that the computer in this particular case is not directed to solving a computer only problem. See Office Action, pg. 33. The Applicant respectfully disagrees. The analogous problem to the internet-centric one described in DDR Holdings v. Hotels.com is with educational platforms. There is no existing computer architecture that will apply a GAI model to obtain assignment-aligned, population-specific rubrics with greater efficiency and precision than previously possible. The examiner takes the position that both the specification and the claim limitation does not support the Applicant’s argument addressing a computer only problem as seen in the DDR Holdings vs. Hotels.com decision. In the DDR Holdings decision, the claim limitations are specifically directed to the creation of an automatic webpage that contain the similar visual elements of a source webpage. Instead, the examiner takes the position that the computer in this particular case is not directed to solving a computer only problem. In this particular case the computer is being used as a tool to automate the process of customizing questions based on some user parameters which was known in the pre-computer world. It has been held that “claims that do no more than apply established methods of machine learning to a new data environment are [not] patent eligible.” Recentive Analytics, Inc. v. Fox Corp. , 134 F.4th 1205, 1211 (Fed. Cir. 2025). Applicant argues: 1. Delgado Does Not Disclose or Suggest a Generative Artificial Intelligence Model Amended claim 1 recites a rubric engine operatively coupled to a generative artificial intelligence (GAI) model, and generating a structured request prompt comprising assignment type, evaluation criteria, rubric scale, and audience context, which is designed to elicit a response from the GAI model to produce rubric content. Delgado never teaches or suggests any generative model or structured prompt mechanism. Instead, Delgado's rubric development is manual and template-based, relying on a GUI for human input and selection of pre-authored templates from a data store. Delgado, ¶¶[0059], [0032] - [0033. There is no disclosure of rubric generation in response to machine-generated prompts, nor any component equivalent to a content generator that contextually composes rubric text in real-time. Delgado's "Exam Template and Rubric" is static and human-driven, not operatively coupled to generative artificial intelligence. The newly cited reference Marahta et al. (US 2026/0087936 A1) teaches the newly cited limitations (i.e., GAI model). Applicant argues “Delgado's templates are predefined scoring models selected by a test developer (¶¶ [0060], [0033]). They are not generated in response to structured prompts, do not include context-aware assessments across evaluation criteria and rubric scales, and are not modifiable post-generation via a GUI.”. The examiner disagrees . In Delgado, para. [0093] states “FIG. 3F shows an example dialogue configuration box 352 to configure the workspace for a given problem type 354. In the example shown in FIG. 3F, problem types 354 include subject areas such as math, chemistry, biology, engineering, physics, and business … sthe dialogue configuration box can be implemented as a wizard that allows the test developer to walk through a series of dialogue boxes to select the desired test type and/or grade/difficulty level” (question type). Para. [0086], “has a corresponding input field 318 (shown as "Score 1" 318a, "Score 2" 318b, "Score 3" 318c, and "Score n" 318d) for an assignable credit or score value for a partial credit/scoring determination. These sub-expressions, as defined by the input fields 316” (evaluation criteria). Para. [0012], “a partial credit or score value associated with at least one of the set of one or more rubric response models.” (rubric scale) and para. [0093], “The dialogue box 352, in this example, also includes a grade-level field 356, which is also provided only as an example and is non-exhaustive. … allows the test developer to walk through a series of dialogue boxes to select the desired test type and/or grade/difficulty level” (audience context). However, the phrase “structure request prompt” is not claimed. Furthermore, “structure request prompt” is not clearly recited in the specification; nor it is a term that is well-known to one of an ordinary skilled in the art. Applicant argues “3. Manual Selection is Not Equal to Automated Audience Context Determination Delgado's "dialogue configuration box" (¶ [0093]) allows a human to select grade level or difficulty manually. This is not equivalent to the claimed rubric engine determining audience context automatically based on assignment metadata”. It is unclear which limitation requires “audience context” to be automatically selected. Applicant’s own specification states that the “audience context” is defined by an educator manually. See applicant’s specification, [0063], “the rubric engine 308 may determine an audience context 330 for the assignment (460), such as identifying the grade, academic, or age level 830 defined by the educator via the prompt 800.” Applicant argues “Amended claim 1 recites that the rubric includes assessments for each evaluation criterion across a rubric scale, and that these assessments are modifiable via the GUI after generation. Additionally, such rubrics are associated with a corresponding version history. Delgado does not teach any such structure or functionality. Its scoring models are static and fixed at creation by the developer (¶¶[0060], [0086] - [0089]). There is no concept of dynamic generation or user-driven modification after rubric creation.” Delgado teaches the require User Graphic Interface (GUI) for generating rubric (Delgado, fig. 1; figs. 3A – 3G show generate a rubric for question) and the newly cited reference Marahta teaches the claimed “version” history. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to JACK YIP whose telephone number is (571)270-5048. The examiner can normally be reached Monday thru Friday; 9:00 AM - 5:00 PM EST. 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, XUAN THAI can be reached at (571) 272-7147. 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. /JACK YIP/Primary Examiner, Art Unit 3715 Application/Control Number: 18/905,611 Page 2 Art Unit: 3715 Application/Control Number: 18/905,611 Page 3 Art Unit: 3715 Application/Control Number: 18/905,611 Page 4 Art Unit: 3715 Application/Control Number: 18/905,611 Page 5 Art Unit: 3715 Application/Control Number: 18/905,611 Page 6 Art Unit: 3715 Application/Control Number: 18/905,611 Page 7 Art Unit: 3715 Application/Control Number: 18/905,611 Page 8 Art Unit: 3715 Application/Control Number: 18/905,611 Page 9 Art Unit: 3715 Application/Control Number: 18/905,611 Page 10 Art Unit: 3715 Application/Control Number: 18/905,611 Page 11 Art Unit: 3715 Application/Control Number: 18/905,611 Page 12 Art Unit: 3715 Application/Control Number: 18/905,611 Page 13 Art Unit: 3715 Application/Control Number: 18/905,611 Page 14 Art Unit: 3715 Application/Control Number: 18/905,611 Page 15 Art Unit: 3715 Application/Control Number: 18/905,611 Page 16 Art Unit: 3715 Application/Control Number: 18/905,611 Page 17 Art Unit: 3715 Application/Control Number: 18/905,611 Page 18 Art Unit: 3715 Application/Control Number: 18/905,611 Page 19 Art Unit: 3715 Application/Control Number: 18/905,611 Page 20 Art Unit: 3715 Application/Control Number: 18/905,611 Page 21 Art Unit: 3715 Application/Control Number: 18/905,611 Page 22 Art Unit: 3715 Application/Control Number: 18/905,611 Page 23 Art Unit: 3715 Application/Control Number: 18/905,611 Page 24 Art Unit: 3715 Application/Control Number: 18/905,611 Page 25 Art Unit: 3715 Application/Control Number: 18/905,611 Page 26 Art Unit: 3715 Application/Control Number: 18/905,611 Page 27 Art Unit: 3715 Application/Control Number: 18/905,611 Page 28 Art Unit: 3715 Application/Control Number: 18/905,611 Page 29 Art Unit: 3715 Application/Control Number: 18/905,611 Page 30 Art Unit: 3715 Application/Control Number: 18/905,611 Page 31 Art Unit: 3715 Application/Control Number: 18/905,611 Page 32 Art Unit: 3715 Application/Control Number: 18/905,611 Page 33 Art Unit: 3715 Application/Control Number: 18/905,611 Page 34 Art Unit: 3715 Application/Control Number: 18/905,611 Page 35 Art Unit: 3715 Application/Control Number: 18/905,611 Page 36 Art Unit: 3715 Application/Control Number: 18/905,611 Page 37 Art Unit: 3715 Application/Control Number: 18/905,611 Page 38 Art Unit: 3715 Application/Control Number: 18/905,611 Page 39 Art Unit: 3715
Prosecution Insights