Prosecution Insights
Last updated: August 17, 2026
Application No. 18/894,141

CUSTOMIZED APPLICATION EXTENSIBILITY AND CODE GENERATION SYSTEM LEVERAGING LLM CAPABILITIES

Non-Final OA §101§103
Filed
Sep 24, 2024
Examiner
PAN, HANG
Art Unit
2193
Tech Center
2100 — Computer Architecture & Software
Assignee
SAP SE
OA Round
1 (Non-Final)
75%
Grant Probability
Favorable
1-2
OA Rounds
1y 4m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 75% — above average
75%
Career Allowance Rate
479 granted / 642 resolved
+19.6% vs TC avg
Strong +26% interview lift
Without
With
+25.5%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
23 currently pending
Career history
675
Total Applications
across all art units

Statute-Specific Performance

§101
16.5%
-23.5% vs TC avg
§103
62.9%
+22.9% vs TC avg
§102
7.7%
-32.3% vs TC avg
§112
9.1%
-30.9% vs TC avg
Black line = Tech Center average estimate • Based on career data from 642 resolved cases

Office Action

§101 §103
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 . Claims 1-20 are pending and examined in this office action. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, mathematical relationship or an abstract idea) without significantly more. Statutory Category: Claim 1 recites a computer-implemented method, comprising: receiving, via a user interface, a command to update an application; retrieving metadata of the application, the metadata comprising one or more data elements associated with the update; providing the one or more data elements for display via the user interface; generating, by one or more processors, new code corresponding to the update; providing the new code for display via the user interface; and integrating the new code, corresponding to the update, into the application, wherein the application including the update is available to one or more users. Step 2A – Prong 1: Claim 1 recites: generating new code corresponding to the update (a user can manually write new code); integrating the new code, corresponding to the update, into the application, wherein the application including the update is available to one or more users (a user can manually add new code to old code, and give the new code to others). That is, nothing in the claim elements precludes the steps from practically being performed mentally or using pen and paper. 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 process grouping of abstract idea. Accordingly, the claim recites an abstract idea under step 2A prong 1. This judicial exception is not integrated into a practical application. In particular, the claim 1 recites additional elements such as receiving a command to update an application; and retrieving metadata of the application, the metadata comprising one or more data elements associated with the update. Examiner would like to point out that with the broad reasonable interpretation, these elements amount to mere data gathering for a mental process, which do not impose any meaningful limits on practicing the mental process (insignificant additional element and an extra-solution activity). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to insignificant additional elements under Step 2B. This judicial exception is not integrated into a practical application. In particular, the claim 1 recites additional elements such as providing the one or more data elements for display, and providing the new code for display. Examiner would like to point out that with the broad reasonable interpretation, these elements amount to mere data output for a mental process, which do not impose any meaningful limits on practicing the mental process (insignificant additional element and an extra-solution activity). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to insignificant additional elements under Step 2B. This judicial exception is not integrated into a practical application. In particular, the claim 1 recites additional elements such as one or more processors; the user interface. The additional elements in the claim amounts to no more than generic hardware component or software component to apply the exception, which cannot integrate a judicial exception into a practical application or provide an inventive concept. Thus, the claim is directed to an abstract idea under Prong II step 2A and 2B. Dependent claims 2-7 do 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 dependent claims 2-7 recite more steps of a mental process (such as generating, providing) which can be performed mentally or using pen and paper. The additional element of dependent claims 2-7 recite more extra-solution activities (receiving different types of data), which do not impose any meaningful limits on practicing the mental process (insignificant additional element). The additional element of dependent claims 2-7 recite the use of LLM, which is a generic software component well known in the field of the art, see (Vadaparty, claim 1). The additional element of dependent claims 2-7 also recite performing a simulation (testing) of new code, which is an extra-solution activity well known in the field of the art, see (Vadaparty column 11, line 5-23), these do not impose any meaningful limits on practicing the mental process (insignificant additional element). Therefore, these claims are not patent eligible. Independent claim 8 (a system with memory and a processor to perform the method of claim 1) with dependent claims 9-14 are rejected under the similar rational as claims 1-7. The additional elements in the claim amounts to no more than generic hardware component with instructions to apply the exception, which cannot integrate a judicial exception into a practical application or provide an inventive concept. Independent claim 15 (a storage medium storing instructions to perform the method similar to claim 1) with dependent claims 16-20 are rejected under the similar rational as claims 1-7. The additional elements in the claim amounts to no more than generic hardware component with instructions to apply the exception, which cannot integrate a judicial exception into a practical application or provide an inventive concept. Claim Rejections - 35 USC § 103 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. Claims 1-2, 4-9, 11-16 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Vadaparty et al. (US patent 12360791) hereinafter Vadaparty, in view of Mahajan (US PGPUB 2014/0189676). Per claim 1, Vadaparty discloses a computer-implemented method, comprising: receiving, via a user interface, a command to update an application; retrieving metadata of the application, the metadata comprising one or more data elements associated with the update; providing the one or more data elements for display via the user interface (claim 1; prompting a LLM to generate, from the legacy software program, the software program in the target programming language; (i.e. requesting a LLM to update the application from one programming language to another programming language); generating by the LLM, a description (data elements), in the human language, of the source code in the file; validating, by a subject matter expert for the enterprise, the description in the human language of the source code in the legacy code file; (i.e. the subject matter expert reads the displayed description to validate); column 4, line 60-67; the UI can also have a display area where the responses from the LLM are shown); generating, by one or more processors, new code corresponding to the update; providing the new code for display via the user interface; (claim 1; column 4, line 60-67; generating, by the LLM, based on the legacy software program and the prompting, the software program code (new code corresponding to the update) in the target programming language, the output of LLM is displayed to the user). Vadaparty does not explicitly teach integrating the new code, corresponding to the update, into the application, wherein the application including the update is available to one or more users. However, Mahajan suggests (claims 1, 4; paragraph [0025]; creating a new version of the application using the updated code modules (new code) and deploying the new version of the application, which becomes available to users). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Vadaparty and Mahajan to integrate the new code to create a new version of the application and deploy it to users, this would ensure the users will get the access to the latest version of the application (containing new features and bug fixes). Per claim 2, Vadaparty further suggests generating a code prompt for a large language model (LLM), wherein the LLM is configured to generate the new code corresponding to the update; providing the code prompt to the LLM; and receiving the new code corresponding to the update from the LLM, responsive to the code prompt (claim 1; prompting a LLM to generate, from the legacy software program, the software program in the target programming language; (i.e. requesting a LLM to update the application from one programming language to another programming language); generating, by the LLM, based on the legacy software program and the prompting, the software program code (new code corresponding to the update) in the target programming language ). Per claim 4, Vadaparty further suggests generating test data for testing the new code; and providing a simulation of the application, including the new code, using the test data (column 11, line 5-23; the test orchestration engine can generate test scripts for various target apps to be tested based on the test script model, the test script model can include (based on prompts to the LLM) various tables that specify attributes and parameters for the test scripts for the apps of the enterprise computer system. The test orchestration engine of the enterprise computer system can convert the test activities defined in the test script model into code artifacts at compile time for the test orchestration engine to use at run time for testing the apps of the enterprise computer system). Per claim 5, Vadaparty further suggests wherein the simulation is provided locally for a user. (column 11, line 5-23; the test orchestration engine of the enterprise computer system can convert the test activities defined in the test script model into code artifacts at compile time for the test orchestration engine to use at run time for testing the apps of the enterprise computer system; the testing is done locally by the test orchestration engine). Per claim 6, Vadaparty in view of Mahajan further suggests receiving approval, from the user, on the simulation; and wherein the integrating comprises integrating the new code into a cloud version of the application, wherein the cloud version of the application is accessible by a plurality of users. (Vadaparty, column 11, line 5-23; a test orchestration engine to perform a test on the application, it would have been obvious that a user issues a command (approves) to start the test orchestration engine to perform the test; Mahajan, claims 1, 4; paragraph [0052]; an application needs to be tested for updates; creating a new version of the application using the updated code modules (new code) and deploying the new version of the application, the application allows users to play a multi-player cloud online game). Per claim 7, Vadaparty in view of Mahajan further suggests wherein the providing the new code for display further comprises: receiving a modification, from a user, to the new code, wherein the new code, including the modification is integrated into the application (Vadaparty, claim 1, column 4, line 60-67; the LLM can generate new code based on user prompt, the UI can also have a display area where the responses from the LLM are shown (i.e. displayed the generated code from LLM); Mahajan, claims 1, 4; paragraph [0049]; the developer system may analyze the provided code (new code), modify the code if needed; creating a new version of the application using the updated code modules (modified new code) and deploying the new version of the application, i.e. integrating the modified new code to the application). Claims 8-9 and 11-14 are rejected under similar rationales as claims 1-2 and 4-7. Claims 15-16 and 18-20 are rejected under similar rationales as claims 1-2 and 4-6. Claims 3, 10 and 17 are rejected under 35 U.S.C. 103 as being unpatentable Vadaparty, in view of Mahajan, in view of Mallisetty et al. (US PGPUB 2016/0291970) hereinafter Mallisetty Per claim 3, Vadaparty does not explicitly teach generating a finalize prompt for the LLM, the finalize prompt comprising a command to integrate the new code into source code of the application; providing the finalize prompt to the LLM; and receiving a notification from the LLM after the new code has been integrated into the source code of the application. However, Vadaparty suggests generating and providing a prompt to a LLM to generate new code (claim 1). Mallisetty further suggests receiving a notification after the new code has been integrated into the source code of the application (paragraphs [0079][0080]; merging new code into source code of an application, receiving a notification if merge is not successful, if the merge is successful, a test (an indication of success) is triggered). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Vadaparty, Mahajan and Mallisetty to use a LLM to integrate new code to source code of an application and to receive a notification of a successful merge; this would increase the capability of the LLM, facilitate users in the field software development and code management. Claims 17 and 10 are rejected under similar rationales as claim 3. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892 form. Vaughn (US PGPUB 2024/0111498) discloses a method of generating code updates using a LLM, including: obtain a prompt of a user for generating code for implementing an additional component for the modular application, the prompt comprising a textual description of a desired functionality of the additional component, provide the information on the existing application architecture and the prompt as input for a Large Language Model (LLM), obtain an output of the LLM, the output comprising a portion of the code for implementing the additional component, and provide the code for implementing the additional component based on the output of the LLM. Hu et al. (US PGPUB 2025/0094138) disclose a method of code generation by large language models. The method accesses a collection of software code samples that intermix sample code and human language description, prompts to an LLM to write code that performs as described by the human language description of the sample code, generates an evaluation score for performance of the tuned large language model as a code generator based on code generation loss for second generated code. And, the method automatically signals that fine-tuning of the tuned large language is complete in response to the evaluation score satisfying a threshold. Any inquiry concerning this communication or earlier communications from the examiner should be directed to HANG PAN whose telephone number is (571)270-7667. The examiner can normally be reached 9 AM to 5 PM. 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. /HANG PAN/Primary Examiner, Art Unit 2193
Read full office action

Prosecution Timeline

Sep 24, 2024
Application Filed
Jul 14, 2026
Non-Final Rejection mailed — §101, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12688034
APPLICATION MIGRATION METHOD FROM CLIENT-SERVER ARCHITECTURE TO BLOCKCHAIN ARCHITECTURE
2y 1m to grant Granted Jul 21, 2026
Patent 12670015
Detached Global Scheduler
4y 5m to grant Granted Jun 30, 2026
Patent 12669983
CODE GENERATION METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM
1y 4m to grant Granted Jun 30, 2026
Patent 12664070
ROOT CAUSE ANALYSIS SYSTEM AND ROOT CAUSE ANALYSIS METHOD IN HETEROGENEOUS VIRTUALIZATION ENVIRONMENT
2y 7m to grant Granted Jun 23, 2026
Patent 12639200
AUTOMATED TRACKING OF CONSISTENT SOFTWARE TEST FAILURES
2y 4m to grant Granted May 26, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

1-2
Expected OA Rounds
75%
Grant Probability
99%
With Interview (+25.5%)
3y 3m (~1y 4m remaining)
Median Time to Grant
Low
PTA Risk
Based on 642 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month