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 communication filed 9/24/2026. Claims 1-23 are currently pending and claims 1, 8, and 15 are the independent claims.
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 an abstract idea without significantly more.
As per independent claim 1, it recites “A computing system, comprising: a processor system; and a computer storage medium that stores computer-executable instructions that are executable by the processor system to utilize a graph representing a source code program to generate a prompt by at least causing the computing system to: perform one or more static analyses on the source code program to generate one or more internal compiler-related data structures; generate the graph representing the source code program, the graph comprising a plurality of nodes and a plurality of edges, wherein each node represents a code element of the source code program and each edge represents a usage or definitional relationship between two code elements of the source code program, each edge being generated from the one or more internal compiler-related data structures; receive, during a user session of a software development tool, a user query relating to a software engineering task to perform on the source code program; cause a prompt generation engine of the computing system to traverse the graph to determine a first node and a second node of the graph, the first node representing a code element that is a subject of the user query, and the second node being connected to the first node by an edge of the graph; cause the prompt generation engine of the computing system to generate a code directive, the code directive comprising source code associated with the first node and a description of the usage or definitional relationship represented by the edge connecting the first node and the second node; cause the prompt generation engine of the computing system to generate the prompt for input to a language model, the prompt comprising the code directives; transmit the prompt to the language model; receive a response from the language model, the response corresponding to the software engineering task; and output in the software development tool an output that includes the response from the language model or that is derived from the response from the language model.”
The limitations “perform one or more static analyses on the source code program to generate one or more…data structures”, “generate the graph representing the source code program, the graph comprising a plurality of nodes and a plurality of edges, wherein each node represents a code element of the source code program and each edge represents a usage or definitional relationship between two code elements of the source code program, each edge being generated from the one or more …data structures”, “…traverse the graph to determine a first node and a second node of the graph, the first node representing a code element that is a subject of the user query, and the second node being connected to the first node by an edge of the graph”, “generate a code directive, the code directive comprising source code associated with the first node and a description of the usage or definitional relationship represented by the edge connecting the first node and the second node”, and “generate the prompt for input to a language model, the prompt comprising the code directives; transmit the prompt to the language model”, as drafted, recites a function that, under its broadest reasonable interpretation, covers a function that could reasonably be performed in the mind, including with the aid of pen and paper, but for the recitation of generic computer components. For example, a human may mentally/with pen and paper/etc. judge/analyze/evaluate/perform static analysis on source code and write/generate/etc. data structures; may mentally/with pen and paper write/generate/determine/etc. a graph comprising nodes and edges and which representing code/program/representing elements of code and relationships between elements/etc.; may mentally/with pen and paper/etc. analyze/evaluate/judge/ observe/traverse/etc. a graph/tree/etc. having nodes and edges and judge/decide/determine/identify/etc. nodes; may mentally/with pen and paper/etc. write/create/generate/etc. source code and a description of a relationship between nodes/a code directive comprising source code associated with the first node and a description of a relationship between the first node and the second node/etc.; and may mentally/with pen and paper/etc. write/create/generate/etc. input/prompt/information/etc. comprising source code and a description of relationships/code directives/etc. to be provided to a language model/prompt for input to a language model, the prompt comprising the code directives/etc.. As such, with broadest reasonable interpretation, the limitations encompass a human mind carrying out the function through observation, evaluation, judgment, and/or opinion, or even with the aid of pen and paper, and therefore recite the abstract idea of a mental process. Thus, these limitations recite and fall within the “Mental Processes” grouping of abstract ideas.
This judicial exception is not integrated into a practical application. The claim recites the additional elements “A computing system, comprising: a processor system; and a computer storage medium that stores computer-executable instructions that are executable by the processor system to utilize a graph representing a source code program to generate a prompt by at least causing the computing system to”, “internal compiler-related”, “receive, during a user session of a software development tool, a user query relating to a software engineering task to perform on the source code program”, “cause a/the prompt generation engine of the computing system to”, “transmit the prompt to the language model”, “receive a response from the language model, the response corresponding to the software engineering task”, and “output in the software development tool an output that includes the response from the language model or that is derived from the response from the language model.” The additional elements “A computing system, comprising: a processor system; and a computer storage medium that stores computer-executable instructions that are executable by the processor system to utilize a graph representing a source code program to generate a prompt by at least causing the computing system to”, “internal compiler-related”, “during a user session of a software development tool”, and “cause a prompt generation engine of the computing system to” recites that high level/generic computer components/computing system comprising a processor system and computer storage medium/compiler/software development tool/prompt generation engine/etc. are used to implement/perform the abstract idea/mental process/judicial exception, and as such amounts to no more than mere instructions to apply the exception using generic computer, and/or mere computer components. The additional elements “receive…a user query relating to a software engineering task to perform on the source code program”, “transmit the prompt to the language model”, “receive a response from the language model, the response corresponding to the software engineering task”, and “output in the software development tool an output that includes the response from the language model or that is derived from the response from the language model” do nothing more than add insignificant extra solution activity to the judicial exception of merely gathering/receiving/etc. data, transmitting data, and outputting/displaying/transmitting/etc. data, and the courts have identified functions such as gathering, displaying, updating, transmitting, and storing data as well-understood, routine, conventional activity (see MPEP 2106.05(d)). Accordingly, the additional elements do not integrate the recited judicial exception into a practical application and the claim is therefore directed to the judicial exception. See MPEP 2106.05(f), 2106.05(g), etc..
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 elements amount to mere instructions to apply the exception using generic computer, and/or mere computer components, which does not provide an inventive concept and is not significantly more than the abstract idea/mental process, and the insignificant extra solution activities of gathering/receiving/etc. data, transmitting data, and outputting/displaying/transmitting/etc. data, and the courts have identified functions such as gathering, displaying, updating, transmitting, and storing data as well-understood, routine, conventional activity, thus do not amount to significantly more than the judicial exception. See MPEP 2106.05(d). As such, the additional elements do not amount to significantly more than the judicial exception/mental process/abstract idea and, accordingly, the claims are not patent eligible under 35 USC 101.
As per claim 2, it incorporates the deficiencies of claim 1, upon which it depends, and further recites “…wherein the usage or definitional relationship represented by the edge connecting the first node and the second node comprises at least one of: "contains," "is defined by", "is referenced by", "writes to", "reads from", "calls to", "is called by", "extends", "is extended by", "was produced by template", "is defined by a typedef to be", and "is inclined into”” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception, and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 2 fails to correct the deficiencies of claim 1, and is therefore rejected for similar reasoning as claim 1, above.
As per claim 3, it incorporates the deficiencies of claim 1, upon which it depends, and further recites “…wherein the one or more static analyses are performed in a background process during the user session of the software development tool” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception/judgement/analysis/evaluation/ determination/etc. performed using generic/high level computer/components, and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 3 fails to correct the deficiencies of claim 1, and is therefore rejected for similar reasoning as claim 1, above.
As per claim 4, it incorporates the deficiencies of claim 1, upon which it depends, and further recites “…wherein the plurality of nodes comprises anode representing a code element used or defined in a first file of the source code program and a node representing a code element used or defined in a second file of the source code program” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception, and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 4 fails to correct the deficiencies of claim 1, and is therefore rejected for similar reasoning as claim 1, above.
As per claim 5, it incorporates the deficiencies of claim 1, upon which it depends, and further recites “… wherein the one or more internal compiler-related data structures comprise at least one of a symbol table, def-use chains, use-def chains, or a control flow graph” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception, and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 5 fails to correct the deficiencies of claim 1, and is therefore rejected for similar reasoning as claim 1, above.
As per claim 6, it incorporates the deficiencies of claim 1, upon which it depends, and further recites “…wherein the traversal of the graph generates an ordering of nodes traversed by the prompt generation engine” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception, and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 6 fails to correct the deficiencies of claim 1, and is therefore rejected for similar reasoning as claim 1, above.
As per claim 7, it incorporates the deficiencies of claim 1, upon which it depends, and further recites “… wherein the software engineering task comprises code summarization, wherein the response provides an answer to the user query on how a particular portion of the source code program functions” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the data/information being gathered/received/etc. and output/provided/displayed/etc. in the insignificant extra solution activities, and the courts have identified functions such as gathering, displaying, updating, transmitting, and storing data as well-understood, routine, conventional activity (see MPEP 2106.05(d)). As such, claim 7 does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 7 fails to correct the deficiencies of claim 1, and is therefore rejected for similar reasoning as claim 1, above.
As per independent claim 8, it recites a method having similar limitations as the steps performed by the computing system of claim 1, and as such recites the same deficiencies as claim 1 and is rejected for similar reasoning as claim 1, above.
As per claim 9, it incorporates the deficiencies of claim 8, upon which it depends, and further recites “…generating the graph is performed in a background process during the user session of the source code program in a source code editor of the software development tool” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/drawing/creating/generating the graph/tree/etc., and as such does not integrate the abstract idea into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 9 fails to correct the deficiencies of claim 8, and is rejected for similar reasoning as claim 8, above.
As per claim 10, recites a method having similar limitation as the system of claim 2, and is therefore rejected for similar reasoning as claim 2, above.
As per claim 11, it incorporates the deficiencies of claim 8, upon which it depends, and further recites “…wherein traversing the graph to determine the first node and the second node further comprises: generating a candidate set of nodes, wherein a node in the candidate set is associated with a source code line number range within a currently-viewed portion of the source code program in a source code editor of the software development tool” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception/determining/finding/analyzing/etc., and as such does not integrate the abstract idea into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 11 fails to correct the deficiencies of claim 8, and is rejected for similar reasoning as claim 8, above.
As per claim 12, it incorporates the deficiencies of claim 8, upon which it depends, and further recites “…selecting a root node from the candidate set of nodes, wherein the root node has a smallest source code line number range and a node type of function definition, type definition or file” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception/judging/selecting/determining/etc., and as such does not integrate the abstract idea into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 12 fails to correct the deficiencies of claim 8, and is rejected for similar reasoning as claim 8, above.
As per claim 13, it incorporates the deficiencies of claim 8, upon which it depends, and further recites “…further comprising: forming a target node set of target nodes from the candidate node set, wherein a target node has a smallest source code line number range” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception/judging/selecting/determining/identifying/forming/etc., and as such does not integrate the abstract idea into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 13 fails to correct the deficiencies of claim 8, and is rejected for similar reasoning as claim 8, above.
As per claim 14, it incorporates the deficiencies of claim 8, upon which it depends, and further recites “…forming a query node set comprising the root node, the target nodes, and nodes along shortest paths from the root node to each target node” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception/judging/selecting/determining/identifying/forming/etc., and as such does not integrate the abstract idea into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 14 fails to correct the deficiencies of claim 8, and is rejected for similar reasoning as claim 8, above.
As per claim 15, it incorporates the deficiencies of claim 8, upon which it depends, and further recites “…traversing the target nodes in a breadth-first traversal order to add additional nodes to the query node set” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/judicial exception/judging/analyzing/traversing/etc., and as such does not integrate the abstract idea into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 15 fails to correct the deficiencies of claim 8, and is rejected for similar reasoning as claim 8, above.
As per independent claim 16, it recites a hardware storage device having similar limitations as the system of claim 1, and as such recites the same deficiencies as claim 1 and is rejected for similar reasoning as claim 1, above. Claim 16 recites the additional elements “A hardware storage device storing computer-executable instructions that are executable by a processor system of a computing system to utilize a graph representing a source code program to generate a prompt by at least causing the computing system to” which recites that high level/generic computer components are used to implement/perform/apply/etc. the abstract idea/mental process, and as such amounts to no more than mere instructions to apply the exception using generic computer, and/or mere computer components, which does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process; and further recites the additional elements “cause the language model to perform the software engineering task based on the response” which, with broadest reasonable interpretation, amounts to an insignificant extra solution activity of performing/outputting/etc. a software engineering task, which may be upgrading data/information/code/software/etc.,/displaying information/transmitting information/storing software/etc. using a high level/generic language model, and the courts have identified functions such as gathering, displaying, updating, transmitting, and storing data as well-understood, routine, conventional activity, thus do not amount to significantly more than the judicial exception, See MPEP 2106.05(d), and as such these additional elements/limitations do not integrate the abstract idea into a practical application and are not significantly more than the abstract idea. Therefore, the additional elements of claim 16 fails to correct the deficiencies of claim 1, and claim 16 is rejected for similar reasoning as claim 1, above.
As per claim 17, it incorporates the deficiencies of claim 16, upon which it depends, and further recites “…having stored thereon computer executable instructions that are structured to be executable by the processor system of the computing device to thereby cause the computing system to perform actions that: generate a semantic model of the source code program in a background process of the software development tool, wherein the semantic model comprises symbol data, data flow data and control flow data of the source code program, and wherein the one or more internal compiler-related data structures comprise the semantic model” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/generating a model/determining data flow/judging control flow/deciding symbols/etc., and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 17 fails to correct the deficiencies of claim 16, and is rejected for similar reasoning as claim 16, above.
As per claim 18, it incorporates the deficiencies of claim 16, upon which it depends, and further recites “…utilize the semantic model to generate an edge between the first node and the second node” which, conceptually, with broadest reasonable interpretation, provides further clarification as to the abstract idea/mental process/generating/judging/deciding an edge/etc., and as such does not integrate the abstract idea/mental process into a practical application and is not significantly more than the abstract idea/mental process. Therefore, claim 18 fails to correct the deficiencies of claim 16, and is rejected for similar reasoning as claim 16, above.
As per claim 19, it recites a hardware storage device having similar limitations as the method of claim 9, and is therefore rejected for similar reasoning as claim 9, above.
As per claim 20, it recites a hardware storage device having similar limitations as the system of claim 2, and is therefore rejected for similar reasoning as claim 2, above.
Allowable Subject Matter
Claims 21-23 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
The prior art of record ( Hicks et a. US PG Pub. 2025/0217266 A1, Johnson et al. US PG Pub. 2023/0393817 A1, Mizrahi et al. US Patent 10,809,984 B2, and Clement et al. US PG Pub. 2022/0214863 A1) teaches that static analysis may be performed on a source code/software/program/etc. to generate compiler related data structures/graphs/trees/etc., that graphs/trees/etc. representing the code/program/software may be generated that has nodes representing code elements and edges representing relationships/dependencies/etc. between elements/nodes/etc., that a user query may be received and the tree/graph of a program/code/etc. may be traversed/searched/etc. to determine nodes that are being queried, that a prompt comprising code/description/data about code/code directive/etc. may be generated and transmitted to a language model/LLM/artificial intelligence/machine learning/neural network/etc., that a response from the language model/AI/machine learning/etc. may be received that corresponds to software development/engineering task/etc., and that responses from the language model/AI/machine learning/etc. may be output/displayed/etc. in a development tool/environment/etc..
However, the prior art of record fails to render an obviousness of transmitting a prompt to a language model, wherein the prompt comprises a code directive that provides the language model with additional information about a structure, syntax, or semantics of a source code program such that the language model performs a software engineering task without having been trained on a programming language of the source code program or on the software engineering task, receiving a response from the language model, the response corresponding to the software engineering task, and outputting in a software development tool an output that includes the response from the language model or that is derived from the response from the language model; when the prompt is generated by receiving, during a user session of the software development tool, a user query relating to the software engineering task to perform on the source code program, causing a prompt generation engine of a computing system to traverse a graph to determine a first node and a second node of the graph, the first node representing a code element that is a subject of the user query, and the second node being connected to the first node by an edge of the graph, causing the prompt generation engine of the computing system to generate the code directive, the code directive comprising source code associated with the first node and a description of the usage or definitional relationship represented by the edge connecting the first node and the second node, and causing the prompt generation engine of the computing system to generate the prompt for input to the language model, the prompt comprising the code directives; and when the graph represents a source code program and the graph is generated by performing one or more static analyses on the source code program to generate one or more internal compiler-related data structures, and generating the graph representing the source code program, the graph comprising a plurality of nodes and a plurality of edges, wherein each node represents a code element of the source code program and each edge represents a usage or definitional relationship between two code elements of the source code program, each edge being generated from the one or more internal compiler-related data structures, as required by dependent claims 21-23, and which also integrates the abstract idea/mental process into a practical application/is significantly more than the abstract idea/mental process as the code directive provides the language model with additional information about a structure, syntax, or semantics of the source code program such that the language model performs the software engineering task without having been trained on a programming language of the source code program or on the software engineering task.
Response to Arguments
Applicant's arguments filed 9/24/2026 have been fully considered but they are not persuasive.
As per the 101 arguments on pg. 11 par. 1-pg. 13 par. 1 of the remarks that the amended independent claims are allowable under 35 USC 101 because, as explained in the specification of this application, the claimed invention captures usage and definitional relationships between code elements by using static analysis to generate internal compiler related data structures which are used to generate graph relationships for a graph representing the code that is traversed based on user query to determine code elements represented as nodes and relationship/usage information represented as edges, and provides that information to the language model through the code directives used as prompt context, thereby providing the language model with information about the structure, syntax, and semantics of the source code that is otherwise unavailable from a code snippet alone, which reduces the number of attempts needed to obtain a useful response from the language model when performing the software engineering task, and as such the claimed invention improves the language model’s ability to perform the software engineering task, which is a technical improvement and as such the independent claims integrate any alleged abstract idea into a practical application and/or is significantly more than any abstract idea/mental process, the examiner, respectfully, disagrees.
The examiner would first like to point out that, with broadest reasonable interpretation, the actual wording/phrasing of the independent claims does not actually recite/clarify/require/etc. how/the process by which/how many attempts/etc. the language model provides a response, or even that the language model actually performs the software engineering task, but rather only recites/requires that the prompt is transmitted to the language model and that a response corresponding to the software engineering task is received from the language model, and as such, with broadest reasonable interpretation, the actual wording/phrasing of the independent claims does not actually recite/require these features/limitations providing/resulting in/etc. the argued practical application/technical improvement; rather these features/limitations are recited in new dependent claims 21-23 which are currently objected to as depending on rejected claims. If applicant intended for the broadest reasonable interpretation of the independent claims to be limited to include these features/elements, the examiner would like recommend applicant consider further amendment/clarification of the amended claims to include limitations of dependent claims 21-23 to overcome the 101 issues. The examiner would further like to point out that while the claims do recite generating a prompt to the language model that includes context/information/etc. by using static analysis to generate internal compiler related data structures, generating a graph representing code that has nodes representing code elements and edges representing relationships between the nodes using the internal-compiler related data structures, traversing the graph in response to a user query, and generating a code directing containing source code and a description of the relationships between nodes which is included in the prompt to the language model as context thereby providing the language model with information about the structure, syntax, and semantics of the source code that is otherwise unavailable from a code snippet alone, with broadest reasonable interpretation, these features/limitations/elements can be performed by a human mentally/with pen and paper/etc. but for the recitation of generic computer/computer components/etc., and as such, with broadest reasonable interpretation, these elements/limitations provide clarification as to the performance of the abstract idea/mental process using high level/generic computer components, and therefore do not integrate an abstract idea into a practical application and are not significantly more than the abstract idea/mental process, as seen in the rejection of claim 1 under 35 USC 101, above.
Therefore, the examiner finds these arguments unpersuasive and maintains that the rejection under 35 USC 101 is proper.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOUGLAS M SLACHTA whose telephone number is (571)270-0653. The examiner can normally be reached Monday-Friday 6:30am-4pm.
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, Chat Do can be reached at 571-272-3721. 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.
/DOUGLAS M SLACHTA/Examiner, Art Unit 2193
