Prosecution Insights
Last updated: April 19, 2026
Application No. 18/759,439

DYNAMIC PROMPT GENERATION FOR A CONVERSATIONAL ARTIFICIAL INTELLIGENCE SYSTEM

Final Rejection §101
Filed
Jun 28, 2024
Examiner
GAW, MARK H
Art Unit
3693
Tech Center
3600 — Transportation & Electronic Commerce
Assignee
Paypal Inc.
OA Round
2 (Final)
50%
Grant Probability
Moderate
3-4
OA Rounds
3y 3m
To Grant
99%
With Interview

Examiner Intelligence

Grants 50% of resolved cases
50%
Career Allow Rate
146 granted / 292 resolved
-2.0% vs TC avg
Strong +60% interview lift
Without
With
+60.2%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
33 currently pending
Career history
325
Total Applications
across all art units

Statute-Specific Performance

§101
46.0%
+6.0% vs TC avg
§103
32.0%
-8.0% vs TC avg
§102
5.7%
-34.3% vs TC avg
§112
13.5%
-26.5% vs TC avg
Black line = Tech Center average estimate • Based on career data from 292 resolved cases

Office Action

§101
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 . Status of Claims Claims 1-20 are pending in this application. Information Disclosure Statement The information disclosure statement (IDS) submitted on 1/22/26 filed after the mailing date of the Non-final Office Action. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Examiner’s Comments Relating to Prior Art In the office action dated 10/27/25, the examiner rejected claims 1-3, 6-13, 15-16, and 18-20 under AIA 35 U.S.C. 103 as being unpatentable over Karp (20200374394) in view of Mehta (11936814). Claims 4-5, 14, and 17 were rejected under AIA 35 U.S.C. 103 as being unpatentable over Karp in view of Mehta, further in view of and Harris (20230259960). In response, the applicant substantially narrowed down the claim scope in the amendments dated 1/26/26. Note, the independent claims 1, 8, and 15 have slightly different wordings. To be comprehensive, the examiner is listing them individually below. Specifically, the independent claim 1 now recites the limitations of: determining, based on information included in the particular prompt template, a software module that is configured to perform the transaction and a first data type or first content usable by the software module to perform the transaction; and generate, by the Al model and based on the information included in the particular prompt template, a function call associated with the software module to perform the transaction, wherein the function call includes the first data as one or more parameters for the Al model; and execute, by the Al model, the function call. The independent claim 8 now recites the limitations of: determining, based on the particular template, a software module that is configured to perform the transaction corresponding to the particular transaction type and a first data type usable by the software module to perform the transaction, and generating, by the Al module and based on the first data obtained from the user, instructions for the software module in a format according to a specification included in the particular template; and providing, by the Al module, the instructions to the software module The independent claim 15 now recites the limitations of: to conduct a set of dialogs with the user, wherein the plurality of templates corresponds to a plurality of software modules configured to perform different transactions for an entity, and wherein the particular template comprises information that indicates a set of data types usable by a particular software module for performing a transaction for the user; and generating a function call for the particular software module in a format according to the information included in the particular template, wherein the function call includes the first data as one or more parameters for the particular software module; and instructing, by the AI model, the machine or a server associated with the machine to execute the function call. This is in addition to the other disclosed elements for conducting a transaction based on user’s chats/answers previously disclosed and currently existing in the claim language. The newly added elements – in combination with existing elements – overcome the prior art previously found and currently searched. The prior art rejections are withdrawn. 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. Claims 1-20 are directed to a system, method, or product, which are/is one of the statutory categories of invention. (Step 1: YES). The Examiner has identified independent method claim 8 as the claim that represents the claimed invention for analysis and is similar to independent system claim 1 and product claim 15. Claim 8 recites the limitations of conducting a transaction based on user’s chats/answers. These limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. Determining a transaction request based on user’s chat; selecting a prompt to conduct transaction; determining based on the template used, a software module to perform the transaction and a first data type OR first content usable by the software module; conducting chat = question + via user interface; obtaining user answer; and generating, based on information in from user, instructions for the software module in a format according to a specification included in the particular template, and providing instruction to the software module, – specifically, the claim recites: “receiving… an utterance from a device of a user… determining… based on the utterance, a request for performing a transaction corresponding to a particular transaction type for the user; selecting, from a plurality of templates, a particular template based on the particular transaction type, wherein the particular template is usable… to facilitate a processing of the transaction; conducting… a set of dialogues with the user… using the particular template, wherein the conducting comprises (i) determining, based on the particular template, a software module that is configured to perform the transaction corresponding to the particular transaction type and a first data type usable by the software module to perform the transaction, (ii) generating a first inquiry that prompts the user for first data corresponding to the first data type required by the software module to process the transaction for the user and (iii) providing the first inquiry to the user… obtaining… the first data from the user… based on the conducting the set of dialogs with the user; generating… and based on the first data obtained from the user, instructions for the software module in a format according to a specification included in the particular template; and providing… the instructions to the software module”, recites a fundamental economic practice, directed to mitigating risk. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a fundamental economic practice or commercial or legal interactions, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. The “a system”, “a non-transitory memory”, “one or more hardware processors”, “a chat interface”, “a device of the user”, “an artificial intelligence (AI) model”, “a function call”, and “a software module”, in claim 1; and the additional technical element of “a non-transitory machine-readable medium” “a machine”, and “a particular software module”, in claim 15, are just applying generic computer components to the recited abstract limitations. The recitation of generic computer components in a claim does not necessarily preclude that claim from reciting an abstract idea. Claims 8 and 15 are also abstract for similar reasons. (Step 2A-Prong 1: YES. The claims recite an abstract idea) This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of: a computer such as a system, one or more hardware processors, a device of the user, and a machine; a communication device such as a chat interface; a storage unit such as a non-transitory memory and a non-transitory machine-readable medium; and software module and algorithm such as an artificial intelligence (AI) model, a software module, a function call, and a particular software module. The computer hardware/software is/are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are at a high level of generality. Therefore, claims 1, 8, and 15 are directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application) The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, when considered separately and as an ordered combination, they do not add significantly more (also known as an “inventive concept”) to the exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer hardware 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. Accordingly, these additional elements, do not change the outcome of the analysis, when considered separately and as an ordered combination. Thus, claims 1, 8, and 15 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more) Dependent claims further define the abstract idea that is present in their respective independent claims 1, 8, and 15 and thus correspond to Certain Methods of Organizing Human Activity, and hence are abstract for the reasons presented above. Dependent claim 2 discloses the limitation of wherein the particular prompt template indicates a plurality of data types corresponding to a requirement of the software module, which further narrows the abstract idea. Note that the technical element “the software module” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Dependent claim 3 discloses the limitation of wherein the first question is in a natural language format, which further narrows the abstract idea. Dependent claim 4 discloses the limitation of (i) receiving second data from the user via the chat session in response to the first question, (ii) determining that the second data does not correspond to data for the Al model to process the request, and (iii) generating a second question for the chat session, wherein the second question prompts the user for the first data corresponding to the first data type using a different syntax than the first question, which further narrows the abstract idea. Note that the technical element “the Al model” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Dependent claim 5 discloses the limitation of (i) generating, by the Al model and based on the particular prompt template, a second question that prompts the user for second data corresponding to a second data type required by the software module to perform the transaction for the user and (ii) providing the second question to the user via the chat interface, which further narrows the abstract idea. Note that the technical elements “the Al model”, “the software module”, and “the chat interface”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Dependent claim 6 discloses the limitation of wherein the plurality of prompt templates indicates different sets of data types corresponding to requirements of different software modules for performing respective transactions, which further narrows the abstract idea. Note that the technical element “different software modules” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Dependent claim 7 discloses the limitation of the plurality of prompt templates, which further narrows the abstract idea. Dependent claim 9 discloses the limitation of obtaining, by the AI model and from the software module, a result from the processing the transaction; generating, by the AI model, content based on the result; and providing the content to the user via the chat interface, which further narrows the abstract idea. Note that the technical elements “AI model”, “the software module”, and “the chat interface”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Dependent claim 10 discloses the limitation of wherein the transaction corresponds to accessing information related to a topic, and wherein the result comprises data related to the topic and obtained from a plurality of data sources, and wherein the content comprises a summary or at least a portion of the information, which further narrows the abstract idea. Dependent claim 11 discloses the limitation of wherein the result indicates whether the transaction has been completed, has been denied, or requires additional information to complete, and wherein the content provides a notification to the user regarding the result, which further narrows the abstract idea. Dependent claim 12 discloses the limitation of wherein the transaction corresponds to a payment transaction, and wherein the first data corresponds to an identity of a recipient or an amount of the payment transaction, which further narrows the abstract idea. Dependent claim 13 discloses the limitation of wherein the particular template indicates a plurality of data types required by the particular software module for processing the transaction for the user, which further narrows the abstract idea. Note that the technical element “the particular software module” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Dependent claim 14 discloses the limitation of (i) receiving second data from the user via the chat session in response to the first inquiry, (ii) determining that the second data does not correspond to the first data type, and (iii) generating a second inquiry for the chat session, wherein the second inquiry prompts the user for the first data corresponding to the first data type using a different syntax than the first question, which further narrows the abstract idea. Dependent claim 16 discloses the limitation of wherein the first question is in a natural language format, which further narrows the abstract idea. Dependent claim 17 discloses the limitation of (i) receiving second data from the user via the chat session in response to the first question, (ii) determining that the second data does not correspond to the first data type, and (iii) generating a second question for the chat session, wherein the second question prompts the user for the first data corresponding to the first data type using a different syntax than the first question, which further narrows the abstract idea. Note that the technical element “the AI model” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Dependent claim 18 discloses the limitation of wherein the operations further comprise (i) generating, by the AI model and based on the particular template, a second question that prompts the user for second data corresponding to a second data type from the set of data types and (ii) providing the second question to the user via the chat interface, which further narrows the abstract idea. Note that the technical elements “the AI model”, and “the chat interface” are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Dependent claim 19 discloses the limitation of wherein the plurality of templates indicates different sets of data types corresponding to requirements of different software modules from the plurality of software modules for performing respective transactions, which further narrows the abstract idea. Note that the technical element “different software modules” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Dependent claim 20 discloses the limitation of obtaining, by the AI model and from the software module, a result from performing the transaction; generating, by the AI model, content based on the result; and providing the content to the user via the chat interface, which further narrows the abstract idea. Note that the technical elements “AI model”, “the software module”, and “the chat interface”, are recited at a high level of generality. They do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus, the dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Therefore, the dependent claims are directed to an abstract idea. Thus, the claims 1-20 are not patent-eligible. Response to Arguments Applicant's arguments filed 1/26/26 have been fully considered but they are not persuasive. The applicant’s 35 USC 103 arguments are moot because the prior art rejections are withdrawn. The examiner is withdrawing the prior art rejections because the amended claims contain new scope narrowing elements which, in combination with the existing elements, sufficiently narrow the claimed scope to overcome the existing prior art and additional art searched. See Examiner Comment Relating to Prior Art above. In response to applicant's argument that: “35 U.S.C. § 101… Applicant respectfully asserts that the amended claimed subject matter is not directed to an abstract idea,” the examiner respectfully disagrees. The claims are directed to the abstract idea of conducting a transaction based on user’s chats/answers. In response to applicant's argument that: “claim 1 integrates the abstract idea into a practical application… (reciting the claim language with emphasis on the newly added language),” the examiner respectfully disagrees. In comparison to the prior version, the added elements (see underlined) and deleted elements (if any, struck out with a line) are essentially: (1) “wherein conductingdetermining, based on information included in the particular prompt template, a software module that is configured to perform the transaction and a first data type or first content usable by the software module to perform the transaction”; (2) “generate, by the Al model and based on the information included in the particular prompt template, a function call associated with the software module to perform the transaction, wherein the function call includes the first data as one or more parameters for the Al model; and execute, by the Al model, the function call”; These changes are not sufficient to overcome the 35 U.S.C. § 101 rejections because: for 101 analysis purpose, this is just stating (corresponding to the numberings above): the procedure involves using a particular chat template that is suitable for the task at hand; and another step in the procedure that call a software procedure and necessary data when it is needed; These are abstract ideas. There is nothing technical about it. Note that the technical element “Al model” is recited at a high level of generality. It does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. In response to applicant's argument that: “claims integrate the abstract idea into a practical application of improving the performance of an artificial intelligence (Al) model,” the examiner respectfully disagrees. The examiner notes that the applicant is not improving the machine learning technology/device. Rather the applicant is using machine learning in a business process – i.e., when data is available and received, the software updates its equations/algorithms. The claims mentioned using relevant data to train the AI model. That is necessary for all software to function properly. The machine learning appears to be recited more in a descriptive way of how the machine learning are trained/created, as opposed to how machine learning are performing actions in the body of the claim. They are operating as any generic computer would operate, recited at a high level of generality and are considered tools for performing the abstract idea. In response to applicant's argument that: “Applicant respectfully submits that the claimed solution, which utilizes prompt templates that are external to an AI model to enable the AI model to "know" how to obtain the required information from users and to communicate with other external modules (e.g., by constructing a function call in a corresponding format, etc.), improves the functionality of the AI-based systems by allowing the AI model to communicate with any external modules e.g., new external modules that are added to the AI system, modified external modules, etc.) without requiring reconfiguration and/or retraining of the AI model,” the examiner respectfully disagrees. The claims use the chat data to determine what is the best-fit chat template to use. Also, the claims do not clearly specify if the external modules is external to the system, or just part of the system but called “external” to the AI software (like a subroutine to a software). Again, the claims do not improve AI technology in anyway. In response to applicant's argument that: “claim 3 in Example 47,” the examiner respectfully disagrees. The claimed invention is not the same as Example 47, claim 3. Conducting a transaction based on user’s chats/answers by determine which template to use is not the same as detecting and dropping “malicious network packets”, and blocking future traffic from the source address. Example 47, claim 3 focuses on the technology of blocking anomaly network packets. The claimed invention does not have the elements and the steps recited in example 47, claim 3. One must read example 47, claim 3 narrowly in deference to the Alice Court’s emphatic prohibition against patenting abstract ideas that lack genuine innovation beyond the use of generic computers. Implementing a business process/idea by processing data using generic computers is not patentable. Conclusion Accordingly, THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARK H GAW whose telephone number is (571)270-0268. The examiner can normally be reached Mon-Fri: 9am -5pm. 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, Mike Anderson can be reached on 571 270-0508. 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. /MARK H GAW/Examiner, Art Unit 3693
Read full office action

Prosecution Timeline

Jun 28, 2024
Application Filed
Oct 23, 2025
Non-Final Rejection — §101
Nov 19, 2025
Interview Requested
Nov 25, 2025
Examiner Interview Summary
Nov 25, 2025
Applicant Interview (Telephonic)
Jan 26, 2026
Response Filed
Feb 09, 2026
Final Rejection — §101
Mar 10, 2026
Interview Requested
Apr 10, 2026
Response after Non-Final Action

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12591930
TRANSACTIONALLY DETERMINISTIC HIGH SPEED FINANCIAL EXCHANGE HAVING IMPROVED, EFFICIENCY, COMMUNICATION, CUSTOMIZATION, PERFORMANCE, ACCESS, TRADING OPPORTUNITIES, CREDIT CONTROLS, AND FAULT TOLERANCE
2y 5m to grant Granted Mar 31, 2026
Patent 12586126
METHODS AND APPARATUSES FOR GENERATING A NEW CREDIT FILE AND ADDING TRADELINES
2y 5m to grant Granted Mar 24, 2026
Patent 12579585
SYSTEMS AND METHODS FOR MAINTAINING A DISTRIBUTED LEDGER PERTAINING TO AUTONOMOUS VEHICLES
2y 5m to grant Granted Mar 17, 2026
Patent 12555439
VIRTUAL CHIP PURCHASE VOUCHERS
2y 5m to grant Granted Feb 17, 2026
Patent 12536587
TRANSACTIONALLY DETERMINISTIC HIGH SPEED FINANCIAL EXCHANGE HAVING IMPROVED, EFFICIENCY, COMMUNICATION, CUSTOMIZATION, PERFORMANCE, ACCESS, TRADING OPPORTUNITIES, CREDIT CONTROLS, AND FAULT TOLERANCE
2y 5m to grant Granted Jan 27, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
50%
Grant Probability
99%
With Interview (+60.2%)
3y 3m
Median Time to Grant
Moderate
PTA Risk
Based on 292 resolved cases by this examiner. Grant probability derived from career allow 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