DETAILED ACTION
Claim Rejections - 35 USC § 101
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.
Applicant’s amendments filed 11/12/25 suffice to obviate the 35 U.S.C. 101 rejection of claims 1-14. Claims 15, 17-20 remain 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. Claim(s) 15 is/are directed to a system, method, medium for decomposing an input request into component portions, such as for completing the request by addressing each portion based on a target simplicity thereof. The claim does not recited additional elements that suffice to integrate the claimed subject matter into a practical application. Further the claims rely on well understood, routine, and conventional structures such as a processor, memory, data structure, etc. to instruct the system along methods by which the input is reified into differently represented more granular data by application of well understood, routine, and conventional instructions such as software routines. As such the claims are considered a manner by which data resolves more data, in this case a subset of the original data. Thus the claims cannot be considered to integrate the judicial exceptions of an abstract idea such as data per se or programs per se. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Claims 17-20 do not remedy and are similarly rejected. The amendments filed 11/12/25 do not amount to sufficiently more and as such the claims remain interpreted under the judicial exception as corresponding to a process of changing data into subsequent data, and/or of a stand in for human behaviors as discussed supra.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claims 1-14 rejected under 35 U.S.C. 103 as being unpatentable over Khot: Decomposed Prompting (provided by Applicant in IDS filed 12/23/2024 and hereinafter Khot further in view of Zhao: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment (copy provided by Examiner, available at least 8/10/23 and hereinafter Zha) and further in view of Chen: ALPAGASUS (copy provided by Examiner, available at least 7/17/23).
Regarding claim 1
Kho teaches:
A method implemented by one or more processors (Kho: Abstract), the method comprising:
receiving an input prompt for a large language model, LLM (Kho: Fig 2, 3: such as receipt of a lexical request by an inference model);
decomposing the input prompt into a subprompts, the subprompts comprising a plurality of nodes of sub-prompts that form the input prompt, the plurality of nodes (Kho:§ 3.3; Fig 4: system decomposes input into plurality of sub-tasks); comprising:
a plurality of nodes corresponding to simple sub-prompts of the input query, a plurality of branching nodes of sub-prompts each corresponding to multiple simple sub-prompts, and a root node corresponding to the input prompt (Kho:§ 3.3; Fig 4: such as for forming leaf processes corresponding to upstream sub-tasks);
including the input prompt in a set of training prompts and/or a set of evaluation prompts (Kho:§ 3.3; Fig 4: input prompts, sub-tasks thereof, displayed to a user as part of evaluative processes).
Kho measures task accuracy (Kho: § 4.1, 4.3) as a form of complexity and iteratively decomposes complex task prompts into increasing simpler sub-tasks, sub-prompts, etc. to improve the accuracy based on a comparison with a threshold complexity, accuracy, etc. (Kho: Abstract; § 1; Fig 1, 2) until a prompt length is of sufficient accuracy (Kho: § 3.3, 4.2) and based on a length threshold (Kho: § G.2.1) and thus teaches:
determining a prompt complexity based on length by comparing the prompt complexity to a threshold complexity (Kho: § G.2.1: prompted tasks decomposed based on a specified minimum task complexity, length, etc.) of the prompt tree;
in response to determining, based on the comparing, that the prompt complexity is above the threshold complexity (Kho: § G.2.1: such as by determining a sequence of tasks greater than a threshold length), including the input prompt in a set of evaluation prompts (Kho: § G.2.1: such as by subsequently evaluating additional portions of tasks decomposed based on length).
Kho does not explicitly teach determining complexity based on a path length of the prompt tree as Kho embraces but does not rely on a tree like data structure, nor does Kho discuss determining a threshold complexity based on a specific LLM with respect to the input prompt nor causing the input prompt to be stored in a set of training prompts and/or a set of evaluation prompts.
In a related field of endeavor Zha teaches the utility of generating a nodal tree structure representative of a semantic tree of prompt data which embraces complexity by adding additional nodes to the representation thereby determining the prompt complexity with respect to tree parameters to thereby measure complexity based on tree size and with respect to a plurality of defined thresholds (Zha: Abstract; § 1, pp 3; § 3, pp 5, 6; figure thereon: such as by adding new nodes to increase the complexity of instructions ; “We add 3, 6, and 10 nodes to the semantic tree of each sample, resulting in performance gains of 14%, 18%, and 24%”); the system measures complexity based on particular LLMs with respect to the input prompting (Zha: Figure 1); and adds training information to semantic trees in a controllable manner generative of said measurements (Zha: § 1, 4.3, 4.4; Fig 1: system introduces, trains and tests on enhanced training sets).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to decompose an input prompt of Kho to utilize a tree like data structure such as that of Zha to thereby extend and test a training set based thereon for at least the purpose of performing tree and/or graph like operations to thereby test the efficacy of increasingly complex training data sets on a plurality of LLM to determine efficaciousness of a training set extended thereby; one of ordinary skill in the art would have expected only predictable results therefrom.
Kho in view of Zha does not explicitly discuss determining a threshold complexity based on a specific LLM with respect to the input prompt.
In a related field of endeavor Chen teaches a system and method for developing improved training prompts based on enhancing training data with prompts meeting a quality threshold (Chen: § 1, pp2, § 2.1; Fig 2, 3: system fine tunes an LLM based on prompting with respect to training tuples of determined higher quality; “we design a prompt applied to a powerful LLM (e.g., ChatGPT) for evaluating the quality of each (instruction, input, response) tuple and then filter out the ones with scores lower than a threshold,“) It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to improve the Kho in view of Zha system and method to include augmenting input prompts based on the Chen taught threshold for determine prompts of high quality and complexity for at least the purpose of generating, saving and testing additional training data to thereby optimize, fine tune, etc. a model based on a threshold quality, a threshold complexity, and/or a threshold generally; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 2
Kho in view of Sah in view of Rez teaches or suggests:
The method of claim 1, wherein the simple sub-prompts that correspond to the leaf nodes of the prompt tree have at least a target simplicity (Kho:§ 3.3; Fig 4: tasks iteratively decomposed until a threshold accuracy, simplicity, etc.); (Zha: Abstract; § 1, pp 3; § 3, pp 5, 6; figure thereon: adding new nodes increases the complexity of the originally decomposed tasks); (Chen: § 1, pp2, § 2.1; Fig 2, 3: a threshold simplicity or complexity used to fine tune a model). Examiner has taken official notice which Applicant has failed to timely and explicitly traverse and it is thus accepted as Admitted Prior Art (APA: please see MPEP 2144.03) that the leaf nodes, representative of terminal or end of chain nodes in a tree, such as at the far terminus of a branch would have comprised an obvious inclusion for at least the purpose of representing a fully decomposed function, terminal prompt, etc.; one of ordinary skill in the art would have expected only predictable results from such an inclusion. The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 3
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 2, wherein decomposing the input prompt into the prompt tree comprises: decomposing the input prompt into a first set of sub-prompts using the LLM; and iteratively decomposing, using the LLM, each sub-prompt into a further set of sub-prompts until the target simplicity is reached (Kho:§ 3.3; Fig 4: tasks iteratively decomposed until a threshold accuracy, that is, until determined sufficient for a highly accurate model). The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 4
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 2, further comprising determining that a given sub-prompt, of the sub-prompts, has the target simplicity, determining that the given sub-prompt has the target simplicity comprising one or more of:
determining that no further decomposition of the given sub-prompt is achievable by the LLM; determining that the given sub-prompt falls within a domain of expertise of one or more expert models accessible by the LLM; and/or determining that the LLM classifies the sub-prompt as a simple sub-prompt (Kho:§ 3.3; Fig 4: tasks iteratively decomposed until a threshold accuracy, that is, until determined sufficient for a highly accurate model). The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 5
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 1, wherein determining the prompt complexity based on a path length of the prompt tree comprises: determining the path length (Khot: § 3.3, Recursive Decomposition: system reduces the input to a length where the model is accurate) of the prompt tree (Zha: Abstract; § 1, pp 3; § 3, pp 5, 6; figure thereon: system determines a tree and enhances complexity such as by adding a predetermined amount of new nodes to increase the complexity of instructions), comprising summing a plurality of leaf path lengths, each leaf path length corresponding to a path from the root node to a respective leaf node (Zha: Abstract; § 1, pp 3; § 3, pp 5, 6; figure thereon; Fig 2). The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 6
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 5, wherein determining the prompt complexity based on the path length of the prompt tree comprises: determining a logarithm of the path length (Kho: § E, G.2.1: system operates to decompose over a branch in log (n) time, that is the length of the execution path is logarithmically determined over execution, simulation, etc.). Examiner has taken official notice which Applicant has failed to timely and explicitly travers and it is thus accepted as Admitted Prior Art (APA: please see MPEP 2144.03) that relying on a determined logarithm would have comprised an obvious inclusion such as for limiting an overall compute time, complexity, etc. of a particular coded instruction, subset thereof. The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 7
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 1, wherein determining the prompt complexity based on the path length of the prompt tree comprises: averaging the complexity over a plurality of decodings of the input prompt. Examiner has taken official notice which Applicant has failed to timely and explicitly travers and it is thus accepted as Admitted Prior Art (APA: please see MPEP 2144.03) that relying on an average would have comprised an obvious inclusion such as for determining a reasonable manner in which to parse a task. The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 8
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 1, wherein the input prompt is included in the set of training prompts in response to determining that the prompt complexity is above the threshold complexity, and the method further comprises: training parameters of the LLM, and/or of an additional LLM, based on the set of training prompts. Examiner has taken official notice which Applicant has failed to timely and explicitly travers and it is thus accepted as Admitted Prior Art (APA: please see MPEP 2144.03) that iterative training based on output parameters of a model would have comprised an obvious inclusion for at least the purpose of operating within well-known machine learning paradigms to generate predictable results. The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 9
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 1, wherein the input prompt is included in the set of evaluation prompts in response to determining that the prompt complexity is above the threshold complexity, and the method further comprises: evaluating a performance of the LLM based on the set of evaluation prompts (Kho:§ 3.3; Fig 4: input prompts, sub-tasks thereof, displayed to a user as part of evaluative processes). The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 10
Kho in view of Zha in view of Chen teaches or suggests:
The method of claim 1, wherein the threshold complexity is a dynamic threshold complexity that is based on a performance of the LLM (Kho: Abstract § 3.1-3.4: system dynamically decomposes a prompt based on a determined threshold); ((Zha: Abstract; § 1, pp 3; § 3, pp 5, 6; figure thereon; Fig 2: system dynamically adjusts path length, tree size by adding additional leaf nodes to increase complexity and analyze any gains provided thereby). The claim is thus considered obvious over Kho as modified by Zha and/or Chen as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Zha, and/or Chen to the modified device of Kho, Zha, and Chen; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 11—the claims is considered to recite substantially similar subject matter to that of claim 1 and is similarly rejected.
Regarding claim 12
Kho in view of Zha in view of Chen teaches or suggests:
The system of claim 11, wherein the simple sub-prompts that correspond to the leaf nodes of the prompt tree have at least a target simplicity (Kho: Abstract; 3.3, 3.4 Fig 6, 11: decomposition of prompts into simpler sub-prompts); (Zha: Abstract; § 1, pp 3; § 3, pp 5, 6; figure thereon; Fig 2); (Chen: § 1, pp2, § 2.1; Fig 2, 3: a threshold simplicity or complexity used to fine tune a model). The claim is thus considered obvious over Kho as modified by Sah and/or Rez as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Sah, and/or Rez to the modified device of Kho, Sah, and Rez; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 13—the claims is considered to recite substantially similar subject matter to that of claim 2 and is similarly rejected.-
Regarding claim 14—the claims is considered to recite substantially similar subject matter to that of claim 4 and is similarly rejected.
Claims 15, 17-20 rejected under 35 U.S.C. 103 as being unpatentable over Khot: Decomposed Prompting (provided by Applicant in IDS filed 12/23/2024 and hereinafter Kho) further in view of DeLuca: 20180330011 hereinafter Del and further in view of Schick: Toolformer (copy provided by Examiner, available at least 2/9/23 and hereinafter Sch).
Regarding claim 15
Kho teaches:
A method implemented by one or more processors (Kho: Abstract), the method comprising:
receiving, from a client device, an input prompt for a large language model, LLM (Kho: Fig 2, 3: such as receipt of a lexical request by an inference model);
decomposing, using the LLM, the input prompt into a plurality of simple sub-prompts (Kho:§ 3.3; Fig 4: system decomposes input into plurality of sub-tasks);
wherein decomposing the input prompt into the plurality of simple sub-prompts comprises decomposing the input prompt until a given sub-prompt, of the plurality of simple sub-prompts, has a target simplicity, (Kho: Abstract; 3.2-3.4; Fig 6, 11: decomposition of prompts into simpler sub-prompts if necessary; that is until it is sufficiently simple; that is the system, method, etc. “allows each prompt to be optimized for its specific sub-task, further decomposed if necessary, and even easily replaced with more effective prompts, trained models, or symbolic functions) and wherein determining that given sub- prompt has the target simplicity comprises:
determining that the given sub-prompt falls within the scope of a particular library function or API call (Khot: decomposed prompt passed to sub task handler such as a further prompt, decomposed prompt and/or symbolic function; wherein the system provides an interface to simpler handler functions in a manner similar to accessing a software library or framework (Khot: pp2, 5; Fig 1, 6)
for one or more sub-prompts in the plurality of simple sub-prompts, determining to invoke an external application from a plurality of external application accessible by the LLM, based at least in part on: the one or more simple sub-prompt relating to subject matter within a domain of said external application (Kho: § 3.3, 4.4, Fig 6, 11: such as operating an elasticsearch, google call or other external API call over a sub-task);
invoking the external application using the one or more simple sub-prompts (Kho: § 3.3, 4.4, Fig 6, 11: such as operating an elasticsearch, google call or other external API call over a sub-task); receiving, responsive to invoking the external application using the one or more simple sub-prompts, one or more responses from the external application (Kho: ¶ 3.2, 3.3, 4.4; Fig 6, 11: answers, received, combined etc. as part of a sub-task); generating, by the LLM, a response to the input prompt based at least in part on the one or more responses from the external application (Kho: ¶ 3.2, 3.3, 4.4; Fig 6, 11: answers, received, combined, concatenated, merged, etc. etc. as part of a sub-task and in response to the user input); and causing the response to be rendered at the client device (Kho: ¶ 3.2, 3.3, 4.4; Fig 6, 11: appropriately constructed answer presented to a user.
Khot does not explicitly teach the system operative to determine a target simplicity, based on an external application accessible by the LLM, nor that a given sub-prompt falls within a domain of expertise of an external application accessible by the LLM.
IN a related field of endeavor Del teaches or suggests a system and method operable to determine a domain of expertise of a prompt, sub-prompt, etc. (Del: Abstract; ¶ 16: detect domain specific language with a query, decomposed query, etc.; wherein each of a plurality of domains has a language domain detection model) and a detected domain, separate from the user system is accessed, such as by a domain search engine or other services (Del: ¶ 16, 21, 27). It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to utilize detect a domain of expertise in the manner taught or suggested by Del to determine particular symbolic functions or API calls available upon detected external domains such that determining the domain and availability indicate a necessary level of simplification or decomposing in the manner taught or suggested by Khot and for at least the purpose of assisting a user to engage with a chatbot, website, or other data structure of a camera equipment supplier, such as for finding information about, viewing images of, or purchasing a camera, accessories therefor; one of ordinary skill in the art would have expected only predictable results therefrom.
Khot in view of Del does not explicitly teach the system operative to determine a target simplicity, based on an external application accessible by the LLM.
In a related field of endeavor Sch teaches a system for allowing LLMs to teach themselves to utilize external applications, api’s thereof (Sch: Abstract) wherein the system filters API calls using a threshold and only keeps API calls which reduce loss. It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to access external tools, apis, etc. as taught or suggested by Khot in the manner taught or suggested by Sch and thereby utilize the filtering threshold taught or suggested by Sch to provide a simplicity threshold based on determining helpful calls to external apis, tools, etc.; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 17
Kho in view of Del in view of Sch teaches or suggests:
The method of claim 16, wherein decomposing the input prompt into the plurality of simple sub-prompts comprises: decomposing the input prompt into a first set of sub-prompts using the LLM (Kho:§ 3.2-3.4; Fig 4: system decomposes input into plurality of sub-tasks); and iteratively decomposing, using the LLM, each sub-prompt into a further set of sub-prompts until the target simplicity is reached (Kho: § 3.2-3.4, 4.4; Fig 4, 6, 11: system iteratively decomposes until threshold is reached, a granular sub-task arrived at thereby is processed by an external application, API call, etc.). The claim is thus considered obvious over Kho as modified by Del and Sch as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Del, and/or Sch to the modified device of Kho, Del, and Sch; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 18
Kho in view of Del in view of Sch teaches or suggests:
The method of claim 16, further comprising determining that a given sub-prompt, of the sub-prompts, has the target simplicity, determining that the given sub-prompt has the target simplicity comprises comprising one or more of: determining that no further decomposition of the given sub-prompt is achievable by the LLM (Kho:§ 3.2-3.4, 4.4, G.2.1; Fig 4: such as by determining the decomposition of a prompt with respect to a complexity threshold, length threshold, etc.); determining that the given sub-prompt falls within a domain of expertise of the external application accessible by the LLM; and/or determining that the LLM classifies the sub-prompt as a simple sub-prompt (Kho:§ 3.2-3.4; Fig 4: system decomposes input into plurality of sub-prompts until the tasks therein do not exceed a determined complexity, length, etc. threshold). The claim is thus considered obvious over Kho as modified by Del and Sch as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Del, and/or Sch to the modified device of Kho, Del, and Sch; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 19
Kho in view of Del in view of Sch teaches or suggests:
The method of claim 15, further comprising: for an additional sub-prompt in the plurality of simple sub-prompts, generating an additional response based on processing the additional sub-prompt using the LLM and without invoking any external application using the additional sub-prompt; wherein generating, by the LLM, the response to the input prompt is further based at least in part on the additional response (Kho: § § 3.1-3.4, 4G.2.1: system generalates decomposed and nested responses based on the complexity, length, etc. threshold and merges the results thereof, the system optionally but does not necessarily perform a call to an external application). The claim is thus considered obvious over Kho as modified by Del and Sch as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Del, and/or Sch to the modified device of Kho, Del, and Sch; one of ordinary skill in the art would have expected only predictable results therefrom.
Regarding claim 20
Kho in view of Del in view of Sch teaches or suggests:
The method of claim 15, further comprising: for a further sub-prompt in the plurality of simple sub-prompts: determining to invoke iteratively the external application from the plurality of external applications accessible by the LLM (Kho: § 3.1-3.4, 4.4; Figs 6, 11: such as by multiple invocations of an api call or query of an external application), based at least in part on:
the further sub-prompt relating to further subject matter within a further domain of said external application (Kho: § 3.1-3.4, 4.4; Figs 6, 11: such as by multiple invocations of an api call or query of an external application); and
receiving, responsive to invoking the further external application using the sub-prompt, a second, etc. response from the external application (Kho: § 3.1-3.4, 4.4; Figs 6, 11: decomposed prompts resolve particular portions of granular information); wherein generating, by the LLM, the response to the input prompt is further based at least in part on the further response (Kho: § 3.1-3.4, 4.4; Figs 6, 11: resolved particular portions of granular information merged, etc. into an appropriate response). Kho strongly suggests the resolving of a further external application diverse from the first external application as a plurality of external applications are discussed as external applications such as google, elasticsearch, etc. (Kho: § 3.1-3.4, 4.4; Figs 6, 11). Thus Kho is considered to teach the utility of a variety of external applications as claimed but not to explicitly discuss the employ of a further, second, etc. external application such as for to address a requirement of a sub-prompt however such an approach is considered obvious to try. Kho in view of Del recognizes the problem of addressing requirements of sub-prompts by an external API call, there exist a finite number of ways to accomplish this, such as by limiting the call of a plurality of sub-prompts to a singular external application or by allowing multiple applications to address the various needs of a plurality of sub-prompts. Thus it would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to experiment with potential solutions such as by calling a plurality external applications for at least the purpose of parsimoniously addressing diverse needs within a plurality of sub-prompts; one of ordinary skill in the art would have expected only predictable results therefrom. The claim is thus considered obvious over Kho as modified by Del and Sch as addressed in the base claim as it would have been obvious to apply the further teaching of Kho, Del, and/or Sch to the modified device of Kho, Del, and Sch; one of ordinary skill in the art would have expected only predictable results therefrom.
Response to Arguments
Applicant’s arguments in concert with claim amendments, see Remarks and Claims, filed 11/12/25, with respect to the rejection(s) of claim(s) 1-14 under 35 USC 103 over Khot and Sahar; Claims 15-19 under 35 USC 102 over Khot and claim 20 under 35 USC 103 over Khot have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Khot in view of Shar in view of Reza and/or Khot in view of Deluca.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAUL C MCCORD whose telephone number is (571)270-3701. The examiner can normally be reached 730-630 M-F.
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, CAROLYN EDWARDS can be reached at (571) 270-7136. 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.
/PAUL C MCCORD/Primary Examiner, Art Unit 2692
Prosecution Insights