DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
1. Claims 8 and 18 are objected to because of the following informalities:
Claims 8 and 18: the word “below” in “wherein the input is associated with a first compatibility score below for a language model type corresponding to the language model” does not currently make sense in the context of the claim limitation, and should either be removed or additional limitation added to make sense of this term in the claim. For claim interpretation purposes, claims 8 and 18 are being interpreted without the word “below”.
Appropriate correction is required.
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.
2. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claims 1 and 11, “A method” and “A processing system” are recited, which are each directed to one of the four statutory categories of invention (process and machine; Step 1: YES). However, the claim limitations of claim 1, and similar limitations recited in claim 11, under their broadest reasonable interpretation, recite mental processes which fall into the category of abstract idea (Step 2A Prong 1: YES).
The following limitations, under their broadest reasonable interpretation, recite mental processes:
receiving input comprising one of a target prompt or a preliminary task description from a user: a person reads an input from a user describing a task
generating, …, a first prompt by incorporating the input into a prompt template corresponding to an input type associated with the input, wherein the first prompt is configured…to generate a pre- processed task description associated with the input: a person writes down a first prompt/instruction in a particular template/format, the prompt related to the input to then generate a pre-processed task description
…generating the pre-processed task description associated with the input: a person writes down a pre-processed task description
receiving the pre-processed task description from the language model; generating a second prompt by incorporating the pre-processed task description and the input into a second prompt template, wherein the second prompt is configured … to generate a modified prompt based on the pre-processed task description and the input: a person uses a second prompt template/format to write down a second instruction to generate a modified prompt based on the pre-processed task description and input.
…receiving the modified prompt…; and returning the modified prompt to the user: a person writes down a modified prompt to give to the user
Claims 1 and 11 do not contain any additional elements which integrate the judicial exception into a practical application (Step 2A Prong 2: NO). Claims 1 and 11 contain the additional limitations “generating, using a context processing component”, “the first prompt is configured to cause a language model to generate…”, “providing the first prompt to a language model for generating…”, “receiving…from the language model”, “the second prompt is configured to cause the language model to generate…”, “providing the second prompt to the language model for generating…”, “receiving…from the language model”. Claim 11 further contains the additional limitations “A processing system, comprising:one or more memories comprising computer-executable instructions; andone or more processors configured to execute the computer-executable instructions causing the processing system to”. These limitations are recited at a high level of generality and amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not integrate the judicial exception into a practical application as they do not impose any meaningful limits on practicing the abstract ideas. Therefore, claims 1 and 11 are directed to abstract ideas.
Claims 1 and 11 do not contain any additional elements which amount to significantly more than the judicial exception (Step 2B: NO). As discussed above, the only additional limitations are mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not amount to significantly more than the judicial exception as they do not provide an inventive concept. Therefore, claims 1 and 11 are not patent eligible.
Regarding claims 2-10 and 12-20, “the method” and “the processing system” are recited, which are each directed to one of the four statutory categories of invention (process and machine; Step 1: YES). However, the claim limitations, under their broadest reasonable interpretation, recite mental processes which fall into the category of abstract idea (Step 2A Prong 1: YES).
The following limitations, under their broadest reasonable interpretation, recite mental processes:
Claims 2 and 12:
receiving, from the user, an expected output structure for the input: a person reads an output structure/format from a user
Claims 3 and 13:
wherein the first prompt is generated by further incorporating the expected output structure for the input: a person writes down a prompt by using a specific output structure/format
Claims 4 and 14:
wherein the pre-processed task description associated with the input comprises one or more of a description of an objective, a step for achieving the objective, and an expected outcome: a person writes down a pre-processed task description including steps to achieve an objective, an expected outcome, and a description of an objective (e.g. write down ‘the goal is _____, perform steps 1-3, obtain this output: ____’)
Claims 5 and 15:
wherein the pre-processed task description associated with the input further comprises instructions for one or more anticipated challenges based on the one or more of the description of the objective, the step for achieving the objective, and the expected outcome: a person writes down anticipated challenges (e.g. step 1 might be challenging because _____)
Claims 6 and 16:
wherein the first prompt further …to remove noise and ambiguous language from the input: a person removes ambiguous language from an input
Claims 6 and 16 recite “causes the language model to remove…”, which amounts to mere instructions to implement the judicial exception using a generic computer.
Claims 7 and 17:
wherein the second prompt is generated further based on the one or more of the description of the objective, the step for achieving the objective, and the expected outcome from the pre-processed task description: a person writes down a second prompt using the description of objective, steps, and expected outcome they wrote down
Claims 8 and 18:
wherein the input is associated with a first compatibility score below for a language model type corresponding to the language model: a person writes down a first score for the input
Claims 9 and 19:
wherein the modified prompt is associated with a second compatibility score for the language model type corresponding to the language model, the second compatibility score being greater than the first compatibility score and above a predetermined compatibility threshold: a person writes down a higher score for the second prompt which is above a threshold
Claims 10 and 20:
wherein the pre-processed task description further comprises one or more proposed supplemental resources for enhancing a quality of generated outputs associated with the received input: a person provides supplemental material to enhance quality of output (e.g. additional useful context)
Claims 2-10 and 12-20 do not contain any additional elements which integrate the judicial exception into a practical application (Step 2A Prong 2: NO). As discussed above, these limitation amount to mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not integrate the judicial exception into a practical application as they do not impose any meaningful limits on practicing the abstract ideas. Therefore, claims 2-10 and 12-20 are directed to abstract ideas.
Claims 2-10 and 12-20 do not contain any additional elements which amount to significantly more than the judicial exception (Step 2B: NO). As discussed above, the only additional limitations are mere instructions to implement the judicial exception using a generic computer. Even when viewed in combination with the claims as a whole, mere instructions to implement the judicial exception using a generic computer do not amount to significantly more than the judicial exception as they do not provide an inventive concept. Therefore, claims 2-10 and 12-20 are not patent eligible.
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 (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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.
3. Claims 1-5, 7, 10-15, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Singh (US 2026/0134004 A1) in view of Buliani et al. (US 12,530,173 B1, hereinafter Buliani).
Regarding claim 1, Singh discloses A method for generating modified prompts, comprising: receiving input comprising one of a target prompt or a preliminary task description from a user (para. 0034 “The process 200 initiates with a user 205 providing a user input. …In particular embodiments, the user input may include a task description 210 and a small set of training data (e.g., 5 input-output pairs) that exemplify the desired output style and requirements.”); generating, using a context processing component (Fig. 1, 215), a first prompt (Fig. 1, 220) by incorporating the input into a prompt template corresponding to an input type associated with the input (para. 0035 “In particular embodiments, the prompt generation module 110 may use an optimizer LLM 215 to generate the baseline prompt 220.”; para. 0047 “An example baseline prompt 220 may be as follows. The example baseline prompt 220 may include: (base) prapsing-mac:llm_trainer prapsing$ python auto_prompt.py “The task is to extract all identifiable entities from a given medical text” tune_prompt_data.csv Initial Prompt #Here is the filled prompt template…”; para. 0048 “The example baseline prompt 220 may also include a role definition. For example, the role definition may be: As an AI, your role is to extract all identifiable entities form a given medical text. This includes but is not limited to medical conditions, treatments, medications, procedures, and anatomical terms.”), wherein the first prompt is configured to cause a language model to generate a pre-processed task description associated with the input (Fig. 2, baseline prompt 220 is configured to generate an output 235 using a language model 230); providing the first prompt to a language model (Fig. 2, 230) for generating the pre-processed task description associated with the input (Fig. 2, 235; para. 0053 “The target LLM 230 then generates an output 235 based on the prompt, which is evaluated by the optimizer LLM 215 as below.”; para. 0054 “The output 235 may also include feedback and edge cases.”; para. 0055 “The output 235 may also include enhancement feedback.”); receiving the pre-processed task description from the language model (Fig. 2, 235 output from language model 230); generating a second prompt (Fig. 2, 225, output from language model 215) by incorporating the pre-processed task description and the input (Fig. 2, input (input 245) and pre-processed task description (output 235) processed together by language model 215 for generating the second prompt/input to language model 215) …wherein the second prompt is configured to cause the language model to generate a modified prompt based on the pre-processed task description and the input (Fig. 2, language model 215 uses input 245 and output 235 as prompt for generating a modified prompt 225; language model 215 and 230 in some embodiments are the same model: para. 0018 “In certain embodiments, the optimizer LLM and the target LLM are based on a same model.”); providing the second prompt to the language model for generating the modified prompt (Fig. 2, language model 215 uses input prompt to generate modified prompt 225); receiving the modified prompt from the language model (Fig. 2, prompt 225 is output from language model); and returning the modified prompt to the user (para. 0041 “This optimized prompt 225 is then presented to the user 205 as a final prompt 255 for further evaluation and application within their LLM applications.”).
Singh does not specifically disclose [generating a second prompt by incorporating the pre-processed task description and the input] into a second prompt template.
Buliani teaches [generating a second prompt by incorporating the pre-processed task description and the input] into a second prompt template (see Fig. 4; Col. 16 Lines 27-46 “FIG. 4 depicts example templates and response definitions according to some examples. Example prompt templates 412 include a troubleshooting prompt template and a project design prompt template. Example prompt templates 412 provide additional cues to an LLM about the scope and/or performance of various tasks. Prompt templates can include placeholders that can be populated with custom text, typically offset from the prompt text by special characters and identified by a variable name (indicated by braces surrounding a variable name in this and subsequent figures). In using a prompt template, agents 122 populate the placeholders prior to submitting the resulting prompt to an LLM. For example, the troubleshooting prompt template includes a placeholder 402 for a user prompt, a placeholder 404 for an identification of data sources that the LLM has at its disposal, and a placeholder 406 for a response definition that describes the form of the expected response. Prompt templates can also be used for messages sent to a user (e.g., to wrap additional context around a response or responses from an LLM).”).
Singh and Buliani are considered to be analogous to the claimed invention as
they both are in the same field of natural language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Singh to incorporate the teachings of Buliani in order to specifically generate a second prompt by incorporating the pre-processed task description and the input using a second prompt template. Doing so would be beneficial, as prompt templates encapsulate the user’s prompt with various cues that improve the quality of the response of the LLM (Buliani, Col. 15 Lines 1-20).
Regarding claim 2, Singh in view of Buliani discloses further comprising receiving, from the user, an expected output structure for the input (Singh, para. 0035 “In particular embodiments, the optimizer LLM 215 may generate prompts that incorporate chain-of-thought reasoning. To do that, the user input may also include an instruction for the optimizer LLM 215 to generate a chain-of-thought (COT) styled prompt.”).
Regarding claim 3, Singh in view of Buliani discloses wherein the first prompt is generated by further incorporating the expected output structure for the input (Singh, para. 0035 “In particular embodiments, the optimizer LLM 215 may generate prompts that incorporate chain-of-thought reasoning. To do that, the user input may also include an instruction for the optimizer LLM 215 to generate a chain-of-thought (COT) styled prompt.”; para. 0035 “Leveraging the task description 210, the prompt generation module 110 can then generate a baseline prompt.”; Fig. 2, model 215 uses user input comprising the above instruction to generate a baseline prompt 220).
Regarding claim 4, Singh in view of Buliani discloses wherein the pre-processed task description associated with the input comprises one or more of a description of an objective, a step for achieving the objective, and an expected outcome (Singh, Fig. 2, output 235 is an expected outcome output by the language model 230).
Regarding claim 5, Singh in view of Buliani discloses wherein the pre-processed task description associated with the input further comprises instructions for one or more anticipated challenges based on the one or more of the description of the objective, the step for achieving the objective, and the expected outcome (Singh, Fig. 2, output 235; based on the output/expected outcome, instructions are included for anticipated challenges: para. 0039 “The edge case detection module 140 may focus on identifying instances where the target LLM's 230 output deviates from expectations or exhibits unexpected behavior.”; para. 0054 “The output 235 may also include feedback and edge cases. For example, such feedback and edge cases may include: 1. The system might struggle with understanding and extracting entities from complex medical jargon or terms. 2. The system might not correctly identify entities when they are referred to indirectly or through pronouns. 3. The system might not correctly identify entities when they are embedded in a long, complex sentence structure. 4. The system might struggle with identifying entities when they are not explicitly mentioned but implied in the context.”).
Regarding claim 7, Singh in view of Buliani discloses wherein the second prompt is generated further based on the one or more of the description of the objective, the step for achieving the objective, and the expected outcome from the pre-processed task description (Singh, Fig. 2, second prompt (inputs to language model 215 (235, 245, 225)) uses pre-processed task description (output 235), which contain an expected outcome, as discussed above for claim 4).
Regarding claim 10, Singh in view of Buliani discloses wherein the pre-processed task description further comprises one or more proposed supplemental resources for enhancing a quality of generated output associated with the received input (Singh, pre-processed task description (output 235) includes supplemental resources for enhancing quality of generated output: para. 0055 “The output 235 may also include enhancement feedback. For example, such enhancement feedback may include: 1. The system should improve its understanding of medical terms and jargon. This can be achieved by training the system with more medical literature or data. 2. The system should improve its ability to identify entities referred to indirectly or through pronouns. This can be achieved by improving the system's context understanding capabilities. 3. The system should improve its ability to extract entities from complex sentence structures. This can be achieved by improving the system's natural language processing capabilities. 4. The system should improve its ability to identify implied entities. This can be achieved by improving the system's inference capabilities.”).
Regarding claim 11, claim 11 is a system claim with limitations similar to those recited in method claim 1, and thus is rejected under similar rationale.
Additionally, Singh discloses A processing system, comprising: one or more memories comprising computer-executable instructions (Fig. 6, 618; para. 0157 “Computer system 600 may include a storage subsystem 618 that provides a tangible non-transitory computer-readable storage medium for storing software and data constructs that provide the functionality of the embodiments described in this disclosure. The software can include programs, code modules, instructions, scripts, etc….”); and one or more processors configured to execute the computer-executable instructions causing the processing system to…(Fig. 6, 604, para. 0157 “Computer system 600 may include a storage subsystem 618 that provides a tangible non-transitory computer-readable storage medium for storing software and data constructs that provide the functionality of the embodiments described in this disclosure. The software can include programs, code modules, instructions, scripts, etc., that when executed by one or more cores or processors of processing unit 604 provide the functionality described above.”).
Regarding claim 12, claim 12 is rejected for analogous reasons to claim 2.
Regarding claim 13, claim 13 is rejected for analogous reasons to claim 3.
Regarding claim 14, claim 14 is rejected for analogous reasons to claim 4.
Regarding claim 15, claim 15 is rejected for analogous reasons to claim 5.
Regarding claim 17, claim 17 is rejected for analogous reasons to claim 7.
Regarding claim 20, claim 20 is rejected for analogous reasons to claim 10.
4. Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Singh in view of Buliani, and further in view of Tanjim et al. (US 2026/0220130 A1, hereinafter Tanjim).
Regarding claim 6, Singh in view of Buliani does not specifically disclose wherein the first prompt further causes the language model to remove noise and ambiguous language from the input.
Tanjim teaches wherein the first prompt further causes the language model to remove noise and ambiguous language from the input (para. 0022 “In response to the ambiguity classifier model classifying the query as ambiguous, the ambiguous query rewrite system is configured to build a prompt requesting a query rewrite model to rewrite the query for ambiguity reduction. In one or more implementations, the prompt includes a chat history (e.g., the last five queries submitted to the AI chat agent and corresponding responses to the queries), and an instruction to resolve ambiguities in the query based on the chat history. Additionally or alternatively, the prompt includes one or more specific instructions to clarify ambiguous pronouns in the query, and/or correct typographical errors in the query. In various implementations, the query is received in connection with a particular domain (e.g., a digital product offered by the enterprise) associated with domain-specific terminology (e.g., product-specific terms associated with the digital product), and the prompt includes one or more instructions to preserve the domain-specific terminology within the query.”).
Singh, Buliani, and Tanjim are considered to be analogous to the claimed invention as they are in the same field of natural language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Singh in view of Buliani to incorporate the teachings of Tanjim in order to specifically have the first prompt be configured to cause the language model to remove noise and ambiguous language from the input. Doing so would be beneficial, as this would correct user-submitted queries which might otherwise generate inaccurate or irrelevant response due to ambiguity (Tanjim, para. 0017).
Regarding claim 16, claim 16 is rejected for analogous reasons to claim 6.
5. Claims 8-9 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Singh in view of Buliani, and further in view of Krabach et al. (US 2026/0004078 A1, hereinafter Krabach).
Regarding claim 8, Singh in view of Buliani does not specifically disclose wherein the input is associated with a first compatibility score below for a language model type corresponding to the language model.
Krabach teaches wherein the input is associated with a first compatibility score below for a language model type corresponding to the language model (evaluation score determined corresponding to a particular type of language model (i.e. language model selected from user selection): para. 0030 “In some examples, the prompt evaluation criterion 26 includes an indication 62 of the evaluation machine learning model 60, such as a user selection from a list of evaluation machine learning models 60…”; a current prompt (i.e. Fig. 3, candidate prompt 38) is evaluated for compatibility (i.e. evaluation score 40): para. 0030 “FIG. 3 schematically shows the computing system 10 in an example in which the one or more processing devices 14 are configured to compute the evaluation scores 40 at least in part at an evaluation machine learning model 60.”).
Singh, Buliani, and Krabach are considered to be analogous to the claimed invention as they are in the same field of natural language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Singh in view of Buliani to incorporate the teachings of Krabach in order to specifically have the input be associated with a first compatibility score for a language model type corresponding to the language model. Doing so would be beneficial, as this would provide an objective criterion for determining the quality of a current iteration of the prompt.
Regarding claim 9, Singh in view of Buliani and Krabach discloses wherein the modified prompt is associated with a second compatibility score for the language model type corresponding to the language model, the second compatibility score being greater than the first compatibility score and above a predetermined compatibility threshold (Krabach, a modified prompt is generated (i.e. Fig. 3, candidate prompt 38 from a later iteration of prompt generation loop 30) which is evaluated for compatibility (i.e. i.e. evaluation score 40 for the later iteration of prompt generation 30); this candidate prompt is selected as a final prompt 40 if score is above a threshold; for a first input prompt candidate which does not meet the threshold, and a subsequent modified candidate prompt which does meet the threshold, the second compatibility score will inherently be greater than the first compatibility score: para. 0026 “In other examples, the one or more processing devices 14 may be configured to repeat the prompt generation loop 30 until the evaluation score 40 of a candidate prompt 38 is above or below a predefined threshold value.”).
Singh, Buliani, and Krabach are considered to be analogous to the claimed invention as they are in the same field of natural language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Singh in view of Buliani to incorporate the teachings of Krabach in order to specifically have the modified prompt be associated with a second compatibility score for the language model type corresponding to the language model, the second compatibility score being greater than the first compatibility score and above a predetermined compatibility threshold. Doing so would be beneficial, given the same rationale as claim 8.
Regarding claim 18, claim 18 is rejected for analogous reasons to claim 8.
Regarding claim 19, claim 19 is rejected for analogous reasons to claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Rajmohan et al. (US 12,645,723 B1): iteratively optimizing prompt to generate an optimized prompt instruction from an initial task/problem description (Fig. 2)
Shtar et al. (US 2026/0148087 A1): iteratively optimize prompt via calculating accuracy scores to generate a modified/hardened prompt (Fig. 4)
Ronen et al. (US 2026/0141245 A1): improving prompt iteratively based on prompting large language model to generate variants of the initial prompt, iterate until a loss score is below a predetermined threshold (Fig. 5)
Badjatiya et al. (US 2025/0335775 A1): use prompt writer model to generate a modified prompt based on initial prompt (Fig. 5)
Sengupta et al. (US 2025/0238662 A1): enhancing an initial prompt and modifying an enhanced prompt based on a type of the artificial intelligence model (Fig. 1)
Manandise et al. (US 2025/0139367 A1): processing a user provided prompt with LLM to generate a task description, which is further processed via validation component to generate a processed task description (Fig. 1)
Baldua et al. (US 2025/0110957 A1): receive a user query, determine classification for input, and use input classification to generate a plan generation prompt to execute the identified task (Fig. 1B)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CODY DOUGLAS HUTCHESON whose telephone number is (703)756-1601. The examiner can normally be reached M-F 8:00AM-5:00PM 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, Pierre-Louis Desir can be reached at (571)-272-7799. 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.
/CODY DOUGLAS HUTCHESON/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
