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 .
DETAILED ACTION
This office action is in response to application 19/000,833, which was filed 12/24/24. Claims 1-20 are pending in the application and have been considered.
Foreign Priority
Receipt is acknowledged of certified copies of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file.
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.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Claim 1 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites “receiving a natural language instruction to modify a structured workflow representation; invoking a first large language model to identify a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters; invoking the function using the one or more parameters to produce a list of one or more identified elements; and invoking a second large language model to generate an output instruction to update the structured workflow representation based on a second prompt including the natural language instruction and the list of one or more identified elements”.
The limitation of “receiving a natural language instruction to modify a structured workflow representation”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “receiving a natural language instruction to modify a structured workflow representation” in the context of this claim encompasses receiving a natural language instruction to modify a structured workflow representation written down on a sheet of paper.
The limitation of “invoking a first large language model to identify a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters”, 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. For example, but for the “invoking a first language model” language, “identify a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters” in the context of this claim encompasses mentally identifying a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters.
The limitation of “invoking the function using the one or more parameters to produce a list of one or more identified elements” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “invoking the function using the one or more parameters to produce a list of one or more identified elements” in the context of this claim encompasses mentally invoking a mental function using the one or more parameters to mentally produce and write down a list of one or more identified elements.
Similarly, the limitation of “invoking a second large language model to generate an output instruction to update the structured workflow representation based on a second prompt including the natural language instruction and the list of one or more identified elements”, 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. For example, but for the “invoking a second large language model” language, “generate an output instruction to update the structured workflow representation based on a second prompt including the natural language instruction and the list of one or more identified elements” in the context of this claim encompasses mentally generating an output instruction to update the structured workflow representation based on a second prompt including the natural language instruction and the list of one or more identified elements.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. This judicial exception is not integrated into a practical application. In particular, the claim only recites two additional elements – “a first large language model” and “a second large language model”. The computing elements in this step are recited at a high-level of generality (i.e., as generic large language models) such that they amount to no more than mere instructions to apply the exception using generic computer elements. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using large language models to perform the function identification and output generation amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
Specifically with respect to Step 2A, Prong Two, of the Alice/Mayo test, the judicial exception is not integrated into a practical application. Claim 1 does not recite any limitations that are not mental steps.
Specifically with respect to Step 2B of the Alice/Mayo test, “the claim as a whole does not amount to significantly more than the exception itself (there is no inventive concept in the claim)”. MPEP 2106.05 Il. There are no limitations in claim 1 outside of the judicial exception. As a whole, there does not appear to contain any inventive concept. As discussed above, claim 1 is a mental process that pertains to the mental process of updating a structured workflow, which can be performed entirely by a human with physical aids.
Dependent claims 2-9 depend from claim 1, do not remedy any of the deficiencies of claim 1, and therefore are rejected on the same grounds as claim 1 above.
Generally, claims 2-9 merely recite additional steps for updating a structured workflow representation, all of which could be performed mentally or by writing down relationships with a pen and paper, and do not amount to anything more than substantially the same abstract idea as explained with respect to claim 1.
Specifically:
Claim 2 recites “the second large language model generates the output instruction without utilizing the structured workflow representation as input” which, but for the “second large language model”, could be performed by mentally generates the output instruction without utilizing the structured workflow representation as input. The “second large language model” does not amount to significantly more than the judicial exception for the same reasons as in claim 1.
Claim 3 recites “modifying the structured workflow representation based on the output instruction” which could be performed by mentally modifying the structured workflow representation on a sheet of paper based on the output instruction.
Claim 4 recites “the second prompt includes a description of a syntax to be used to generate the output instruction including a category, a sub-category, and a message” which could be performed by mentally determining second prompt which includes a description of a syntax to be used to generate the output instruction including a category, a sub-category, and a message.
Claim 5 recites “the second prompt includes the natural language instruction as a question after the list of one or more identified elements” which could be performed by mentally determining a second prompt which includes the natural language instruction as a question after the list of one or more identified elements.
Claim 6 recites “the second prompt includes text instructing the second large language model to utilize the list of one or more identified elements when generating the output instruction” which could be performed by mentally determining a second prompt that includes text instructing the second large language model to utilize the list of one or more identified elements when generating the output instruction.
Claim 7 recites “the syntax to be used to generate the output instruction is parsed using regex” which could be performed by visually parsing the output instructions by mentally matching regular expressions to the text.
Claim 8 recites “the syntax to be used to generate the output instruction utilizes, in order, an opening expression, the category, sub-category, and message separated by delimiters, and a closing expression” which could be performed by writing down output instructions with, in order, an opening expression, the category, sub-category, and message separated by delimiters, and a closing expression.
Claim 9 recites “the first prompt includes a series of examples mapping an example natural language instruction to an example function and example one or more parameters” which could be performed by writing down a first prompt including a series of examples mapping an example natural language instruction to an example function and example one or more parameters.
In sum, claims 2-9 depend from claim 1 and further recite mental processes as explained above. None of the additional limitations recited in claims 2-9 amount to anything more than the same or a similar abstract idea as recited in claim 1. Nor do any limitations in claims 2-9 (a) integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea or (b) amount to significantly more than the judicial exception. Claims 2-9 are not patent eligible.
Claim 10 is directed to a non-transitory computer readable medium that corresponds to the method of claim 1 and is therefore rejected for the same reasons set for the above with respect to claim 1. While claim 10 recites generic computer components (non-transitory computer readable medium, instructions, one or more processors), such generic computing components are recited at a high-level of generality (i.e., as a generic non-transitory computer readable medium, generic instructions, and a generic one or more processors) such that they amount to no more than mere instructions to apply the exception using generic computer components. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Claim 10 does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional limitations of using generic computer components amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. Claim 10 is not patent eligible.
Claims 11-15 depend from claim 10, do not remedy any of the deficiencies of claim 10, and contain subject matter that corresponds to that discussed with regard to claims 2-6, and therefore these claims are rejected on the same grounds as claims 10 and 2-6 above.
Claim 16 is directed to an apparatus that corresponds to the method of claim 1 and is therefore rejected for the same reasons set forth above with respect to claim 1. Moreover, while claim 16 recites generic computing components (e.g., instructions, one or more processors), such components are only claimed at a high-level of generality and are not sufficient to render the claim subject matter eligible for the same reasons discussed above with respect to claims 10 and 1.
Claims 17-20 depend from claim 16, do not remedy any of the deficiencies of claim 16, and contain subject matter that corresponds to that discussed with regard to claims 2-5, and therefore these claims are rejected on the same grounds as claims 16 and 2-5 above.
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.
Claims 1-6 and 9-20 are rejected under 35 U.S.C. 103 as being unpatentable over Hawes et al. (US 20240403194) in view of Abadi et al. (US 20250348360).
Consider claim 1, Hawes discloses a computer-implemented method (computer-implemented method, [0215]) comprising:
receiving a natural language instruction to modify a structured representation (receiving a natural language input from the user indicating tools associated with a task and object types associated with a tool, [0042], e.g. to update rows of a table or edit or update an object type, [0045]);
invoking a first large language model to identify a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters (generating a prompt for an LLM which includes the user input, [0087], and based on object types and tools associated with a task in the request, [0042], [0045]; e.g. ontology function tool to update parameter values for an object instance in ontology, [0045], the LLM generating tool calls that are usable to obtain further information associated with the task from available tools, [0110]-[0111], the tools may be automatically configured based on the user inputs, [0114], to identify data objects having an object data type and properties in the ontology, [0091])
invoking the function using the one or more parameters to produce a list of one or more identified elements (using the tool call information, including object type parameters to query a database and return data elements from the ontology, [0089-0091], [0079-0082]); and
invoking a second large language model to generate an output instruction to update the structured representation based on a second prompt including the natural language instruction and the list of one or more identified elements (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]).
Hawes does not specifically mention a structured workflow representation.
Abadi discloses a structured workflow representation (workflow defined according to a schema which defines the permitted structure and statements of the workflow, such as JSON, [0030]).
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 invention of Hawes by using it to modify a structured workflow representation such as found in Adabi in addition to the structured data representations found in Hawes (e.g. ontologies) in order to make such operations accessible to users lacking programming skills, which security analysts may not possess, as suggested by Abadi ([0003]). Doing so would have led to predictable results of making the tasks of adding new actions to the workflow less daunting and time intensive tasks for novice users, as suggested by Abadi ([0004]). The references cited are analogous art in the same field of natural language processing.
Consider claim 10, Hawes discloses a non-transitory computer readable medium including instructions that, when executed by one or more processors (non-transitory computer readable storage device storing software instructions executable by the computing system, [0215], having one or more processors, [0191]), cause the one or more processors to perform the following steps:
receiving a natural language instruction to modify a structured representation (receiving a natural language input from the user indicating tools associated with a task and object types associated with a tool, [0042], e.g. to update rows of a table or edit or update an object type, [0045]);
invoking a first large language model to identify a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters (generating a prompt for an LLM which includes the user input, [0087], and based on object types and tools associated with a task in the request, [0042], [0045]; e.g. ontology function tool to update parameter values for an object instance in ontology, [0045], the LLM generating tool calls that are usable to obtain further information associated with the task from available tools, [0110]-[0111], the tools may be automatically configured based on the user inputs, [0114], to identify data objects having an object data type and properties in the ontology, [0091])
invoking the function using the one or more parameters to produce a list of one or more identified elements (using the tool call information, including object type parameters to query a database and return data elements from the ontology, [0089-0091], [0079-0082]); and
invoking a second large language model to generate an output instruction to update the structured representation based on a second prompt including the natural language instruction and the list of one or more identified elements (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]).
Hawes does not specifically mention a structured workflow representation.
Abadi discloses a structured workflow representation (workflow defined according to a schema which defines the permitted structure and statements of the workflow, such as JSON, [0030]).
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 invention of Hawes by using it to modify a structured workflow representation such as found in Adabi in addition to the structured data representations found in Hawes (e.g. ontologies) for reasons similar to those for claim 1.
Consider claim 16, Hawes discloses an apparatus including at least one processor and at least one computer readable medium including instructions that, when executed by the one or more processors, cause the processor (general purpose computer having a processor executes instructions from computer-readable storage medium, [0191]) to perform the following steps:
receiving a natural language instruction to modify a structured representation (receiving a natural language input from the user indicating tools associated with a task and object types associated with a tool, [0042], e.g. to update rows of a table or edit or update an object type, [0045]);
invoking a first large language model to identify a function and one or more parameters usable to specifically identify one or more elements referred to by a portion of the natural language instruction based on a first prompt including the natural language instruction and a description of available functions and available parameters (generating a prompt for an LLM which includes the user input, [0087], and based on object types and tools associated with a task in the request, [0042], [0045]; e.g. ontology function tool to update parameter values for an object instance in ontology, [0045], the LLM generating tool calls that are usable to obtain further information associated with the task from available tools, [0110]-[0111], the tools may be automatically configured based on the user inputs, [0114], to identify data objects having an object data type and properties in the ontology, [0091])
invoking the function using the one or more parameters to produce a list of one or more identified elements (using the tool call information, including object type parameters to query a database and return data elements from the ontology, [0089-0091], [0079-0082]); and
invoking a second large language model to generate an output instruction to update the structured representation based on a second prompt including the natural language instruction and the list of one or more identified elements (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]).
Hawes does not specifically mention a structured workflow representation.
Abadi discloses a structured workflow representation (workflow defined according to a schema which defines the permitted structure and statements of the workflow, such as JSON, [0030]).
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 invention of Hawes by using it to modify a structured workflow representation such as found in Adabi in addition to the structured data representations found in Hawes (e.g. ontologies) for reasons similar to those for claim 1.
Consider claim 2, Hawes discloses the second large language model generates the output instruction without utilizing the structured workflow representation as input (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]; this is done without providing the actual ontology to the LLM).
Consider claim 3, Hawes discloses: modifying the structured workflow representation based on the output instruction (AIS uses results from LLM to apply an action to the objects, [0113], e.g. edits the ontology, [0129], [0130], [0045])).
Consider claim 4, Hawes discloses the second prompt includes a description of a syntax to be used to generate the output instruction including a category, a sub-category, and a message (a second LLM prompt provides conversation history, information from the data processing service regarding the identified dish, and a request to generate a review of the dish and, if the review is positive to include a tool call to perform an action, i.e. a syntax to be used to generate an output description about a dish, a sub-category, at a restaurant, a category, [0176]).
Consider claim 5, Hawes discloses the second prompt includes the natural language instruction as a question after the list of one or more identified elements (after returning data elements from the ontology, [0089-0091], [0079-0082], generating a second prompt including the user input prompt, [0092], which may be a question, [0066]; this is considered a natural language instruction for the second LLM after a list of one or more identified elements, as shown on Fig. 3).
Consider claim 6, Hawes discloses the second prompt includes text instructing the second large language model to utilize the list of one or more identified elements when generating the output instruction (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093]).
Consider claim 9, Hawes discloses the first prompt includes a series of examples mapping an example natural language instruction to an example function and example one or more parameters (system augments prompt with additional information including examples of how the LLM may use the various system tools, [0052], the object types and tools associated with a task in the request, [0042], [0045]; e.g. ontology function tool to update parameter values for an object instance in ontology, [0045], in other words, the system augments the prompt with examples of using tools and objects to modify the ontology).
Consider claim 11, Hawes discloses the second large language model generates the output instruction without utilizing the structured workflow representation as input (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]; this is done without providing the actual ontology to the LLM).
Consider claim 12, Hawes discloses instructions that, when executed by one or more processors, cause the one or more processors to perform the following steps: modifying the structured workflow representation based on the output instruction (AIS uses results from LLM to apply an action to the objects, [0113], e.g. edits the ontology, [0129], [0130], [0045])).
Consider claim 13, Hawes discloses the second prompt includes a description of a syntax to be used to generate the output instruction including a category, a sub-category, and a message (after returning data elements from the ontology, [0089-0091], [0079-0082], generating a second prompt including the user input prompt, [0092], which may be a question, [0066]; this is considered a natural language instruction for the second LLM after a list of one or more identified elements, as shown on Fig. 3).
Consider claim 14, Hawes discloses the second prompt includes the natural language instruction as a question after the list of one or more identified elements (after returning data elements from the ontology, [0089-0091], [0079-0082], generating a second prompt including the user input prompt, [0092], which may be a question, [0066]; this is considered a natural language instruction for the second LLM after a list of one or more identified elements, as shown on Fig. 3).
Consider claim 15, Hawes discloses the second prompt includes text instructing the second large language model to utilize the list of one or more identified elements when generating the output instruction (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093]).
Consider claim 17, Hawes discloses the second large language model generates the output instruction without utilizing the structured workflow representation as input (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]; this is done without providing the actual ontology to the LLM).
Consider claim 18, Hawes discloses instructions that, when executed by the one or more processors, cause the processor to perform the following steps: modifying the structured workflow representation based on the output instruction (AIS uses results from LLM to apply an action to the objects, [0113], e.g. edits the ontology, [0129], [0130], [0045])).
Consider claim 19, Hawes discloses the second prompt includes a description of a syntax to be used to generate the output instruction including a category, a sub-category, and a message (after returning data elements from the ontology, [0089-0091], [0079-0082], generating a second prompt including the user input prompt, [0092], which may be a question, [0066]; this is considered a natural language instruction for the second LLM after a list of one or more identified elements, as shown on Fig. 3).
Consider claim 20, Hawes discloses the second prompt includes the natural language instruction as a question after the list of one or more identified elements (after returning data elements from the ontology, [0089-0091], [0079-0082], generating a second prompt including the user input prompt, [0092], which may be a question, [0066]; this is considered a natural language instruction for the second LLM after a list of one or more identified elements, as shown on Fig. 3).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Hawes et al. (US 20240403194) in view of Abadi et al. (US 20250348360), in further view of Zawadowskiy et al. (US 20240330365).
Consider claim 7, Hawes discloses generating the output instruction (generating a subsequent LLM prompt with the data objects, object types, and properties, and LLM output includes an additional tool call, [0093], which instructs AIS to apply an action to the objects, [0113], e.g. to edit the ontology, [0129], [0130], [0045]).
Hawes and Abadi do not specifically mention a syntax to be used is parsed using regex.
Zawadowskiy discloses a syntax to be used to generate the output instruction is parsed using regex (generating regular expressions using the LLM and parsing from the log format, [0080]-[0081]).
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 invention of Hawes and Abadi such that a syntax to be used such as the one in Hawes to generate the output instructions is parsed using regex as in Zawadowskiy in order to avoid the prohibitive expensive of processing large volumes of text with LLM models identified by Zawadowskiy ([0070]), predictably improving efficiency, as suggested by Zawadowskiy ([0070]). The references cited are analogous art in the same field of text processing.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Hawes et al. (US 20240403194) in view of Abadi et al. (US 20250348360), in further view of Zawadowskiy et al. (US 20240330365), in further view of Nucci (US 20260187131).
Examiner note: Nucci is published 07/02/26 and filed 01/24/25, which is after Applicant’s effective filing date of 11/11/24 based on Applicant’s foreign priority claim to IN202411086827. However, because Nucci claims domestic priority to provisional application No. 63/626,755, filed 01/30/24, Nucci was effectively filed prior to the instant application and qualifies as prior art under 35 U.S.C. 102(a)(2). The sections of Nucci cited in this office action are supported by the original text of provisional application No. 63/626,755.
Consider claim 8, Hawes, Abadi, and Zawadowskiy do not specifically mention the syntax to be used to generate the output instruction utilizes, in order, an opening expression, the category, sub-category, and message separated by delimiters, and a closing expression.
Nucci discloses a syntax to be used to generate the output instruction utilizes, in order, an opening expression, the category, sub-category, and message separated by delimiters, and a closing expression ( { “category”: “employee_data_management_general_inquiry”, … “subcategory”: “Address Change Inquiry”, … “issue_type”, i.e. “message”, : “Request Employee Data Transaction”, … }, [0097]; see also page 45, paragraphs [0151]-[0163] of provisional application No. 63/626,755).
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 invention of Hawes, Abadi, and Zawadowskiy such that the syntax to be used to generate the output instruction utilizes, in order, an opening expression, the category, sub-category, and message separated by delimiters, and a closing expression in order to realize the ability of LLMs to improve enterprise operations, as suggested by Nucci ([0001]), predictably making them more efficient, accurate, and personalized, as suggested by Nucci ([0001]). The references cited are analogous art in the same field of text processing.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20240379100 Shivani discloses a bidirectional assistant for development platforms that allows users to create and edit workflows using natural language prompts (see Figs. 6A-6C)
US 12346712 Eberhardt discloses a virtual assistant system that receives a request from a user such as a query or task and prompts an LLM with metadata and available functions to determine subsequent prompts, see Fig. 6
US 20240289545 Miller discloses automated plan generation and execution for LLMs
US 20260023615 Marquez Ayala (published and filed after Applicant’s EFD but claiming priority to provisional application 63/673,364 filed 07/19/24) describes generating and editing workflows with a natural language interface with a series of searches for information and LLM prompts (See Fig. 8A)
US 20250363371 Nicolae discloses leverage language models in designing no-code workflows for machine learning within no-code and low-code platforms
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jesse Pullias whose telephone number is 571/270-5135. The examiner can normally be reached on M-F 8:00 AM - 4:30 PM. The examiner’s fax number is 571/270-6135.
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, Andrew Flanders can be reached on 571/272-7516.
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.
/Jesse S Pullias/
Primary Examiner, Art Unit 2655 08/13/26
