Prosecution Insights
Last updated: November 20, 2026
Application No. 19/043,342

MULTI-AGENT SYSTEM FOR MODEL-BASED SEARCH APPLICATIONS

Final Rejection §103
Filed
Jan 31, 2025
Priority
Oct 21, 2024 — provisional 63/709,938
Examiner
SAMARA, HUSAM TURKI
Art Unit
2161
Tech Center
2100 — Computer Architecture & Software
Assignee
Microsoft Technology Licensing, LLC
OA Round
2 (Final)
56%
Grant Probability
Moderate
3-4
OA Rounds
1y 11m
Est. Remaining
74%
With Interview

Examiner Intelligence

Grants 56% of resolved cases
56%
Career Allowance Rate
99 granted / 178 resolved
+0.6% vs TC avg
Strong +19% interview lift
Without
With
+18.7%
Interview Lift
resolved cases with interview
Typical timeline
3y 8m
Avg Prosecution
13 currently pending
Career history
196
Total Applications
across all art units

Statute-Specific Performance

§101
17.0%
-23.0% vs TC avg
§103
57.9%
+17.9% vs TC avg
§102
15.9%
-24.1% vs TC avg
§112
6.6%
-33.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 178 resolved cases

Office Action

§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 . Response to Amendment Applicant’s Remarks, filed June 11th, 2026, has been fully considered and entered. Accordingly, claims 1-20 are pending in the case. Claims 1, 8, 11, 15, and 18 were amended. Claims 1, 11, and 18 are the independent claims. Information Disclosure Statement The information disclosure statement (IDS) submitted on June 11th, 2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. 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, 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. The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. Claims 1-6, 8-13, and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kulkarni et al. (US 2025/0348485 A1) in view of Bhat et al. (US 2025/0383970 A1), further in view of Wee et al. (US 2026/0094089 A1). Regarding claim 1, Kulkarni teaches a method comprising: providing a multi-agent system comprising a query input agent, an orchestrator agent, a query execution agent, and a query evaluation agent, each comprising an autonomous element executable asynchronously with autonomous elements of other agents of the multi-agent system; via the orchestrator agent, receiving a query input (see Kulkarni, Paragraph [0038], “At block 252, the system receives an input query.” [An input query may be received.]); However, Kulkarni does not explicitly teach: providing a multi-agent system comprising a query input agent, an orchestrator agent, a query execution agent, and a query evaluation agent, each comprising an autonomous element executable asynchronously with autonomous elements of other agents of the multi-agent system; via the orchestrator agent, receiving a query input; Bhat teaches: providing a multi-agent system comprising a query input agent, an orchestrator agent, a query execution agent, and a query evaluation agent, each comprising an autonomous element executable asynchronously with autonomous elements of other agents of the multi-agent system; via the orchestrator agent, receiving a query input (see Bhat, Paragraph [0046], “The environment 100 includes multiple semi-autonomous or autonomous agents 110 (a first agent 110 a, a second agent 110 b, a third agent 110 c, a fourth agent 110 d, and so forth) that process the sub-queries 108 and generate agent responses 116 (e.g., a first agent response 116 a, a second agent response 116 b, a third agent response 116 c, and so forth).” [An autonomous multi-agent system may be provided.]); It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Kulkarni (teaching generative model based decomposition of input query into sub-queries and generation of comprehensive response based on responses to sub-queries) in view of Bhat (teaching hierarchical cascade architecture of language models for multi-stage query classification and agent routing), and arrived at a method that incorporates a multi-agent system. One of ordinary skill in the art would have been motivated to make such a combination for the purposes of improving the security reliability, and modularity of data pipelines (see Bhat, Paragraph [0035]). In addition, both the references (Kulkarni and Bhat) teach features that are directed to analogous art and they are directed to the same field of endeavor, such as large language models. The close relation between both the references highly suggests an expectation of success. The combination of Kulkarni, and Bhat further teaches: via the orchestrator agent, providing the query input and a first instruction to a first generative machine learning model (GMLM), wherein the first instruction is to cause the first GMLM to identify a plurality of queries using the query input (see Kulkarni, Paragraph [0043], “At block 258, the system decomposes, using generative model(s), the input query to determine sub-queries and to determine corresponding tool(s) for each of the sub-queries.” [The input query is decomposed into subqueries using a generative model (i.e., first generative machine learning model).]); via the query execution agent, executing the plurality of queries in a respective execution thread using the query input (see Bhat, Paragraphs [0046], [0078], “Multiple independent classification levels 410 can be executed in parallel (e.g., if the dynamic bypass controller 416 determines that two or more levels will be engaged). The architecture 400 can implement batch processing for multiple queries to be processed in parallel. The architecture 400 can implement load balancing across multiple instances of a single model (e.g., where one of multiple instances of a model is chosen based on a queue depth of each instance).” [Multiple queries may be processed in parallel (i.e., executing the plurality of queries in a respective execution thread).]); via the query execution agent, sending a completion signal to the orchestration agent, wherein the completion signal indicates that the plurality of queries have finished executing (see Bhat, Paragraphs [0047], “either the orchestrator agent can initially invoke only the general agent, which then further delegates sub-tasks, or the orchestrator agent can choose to directly identify and route work to the specialized sub-agent. For instance, in a financial services context, the gateway router can divide a trading query into segments for agents handling treasuries, equities, and derivatives, and then aggregate the results to produce an overall response.” [The orchestrator agent delegates subtasks and then aggregates results to produce an overall response, thus, indicating the orchestrator agent receives a completion signal that indicates the pluralities of queries have finished executing.]); However, the combination of Kulkarni, and Bhat do not explicitly teach: responsive to the completion signal, via the orchestrator agent, invoking the query evaluation agent; Wee teaches: responsive to the completion signal, via the orchestrator agent, invoking the query evaluation agent (see Wee, Paragraph [0028], “utilizes an orchestration agent in combination with, for example, a set of task specific agents and a network intelligence engine (including system data, knowledge sets and external data), an evaluation agent, and a generation LLM to provide a refined response to an input prompt wherein the refined response is generated from multiple iterations and recursive analysis by user of the AI-powered engine.” Paragraph [0040], “the present invention will utilize an orchestration agent to determine based, for example on the context of the task, which agents the orchestration agent will call.” [An orchestrator agent may invoke an evaluation agent (i.e., query evaluation agent) to provide results to a generation LLM.]); It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Kulkarni (teaching generative model based decomposition of input query into sub-queries and generation of comprehensive response based on responses to sub-queries) in view of Bhat (teaching hierarchical cascade architecture of language models for multi-stage query classification and agent routing), further in view of Wee (teaching devai model and system) and arrived at a method that incorporates a query evaluation agent. One of ordinary skill in the art would have been motivated to make such a combination for the purposes of improving the accuracy of the AI powered engine (see Wee, Paragraph [0032]). In addition, the references (Kulkarni, Bhat, and Wee) teach features that are directed to analogous art and they are directed to the same field of endeavor, such as large language models. The close relation between the references highly suggests an expectation of success. The combination of Kulkarni, Bhat, and Wee further teaches: via the query evaluation agent, providing query results of execution of each query of the plurality of queries and a second instruction to a second GMLM, wherein the second instruction is to cause the second GMLM to generate, for each query result, a query result summary comprising an evaluation of alignment of a query result with the query input (see Kulkarni, Paragraph [0053], “At block 262, the system processes, using one or more generative models, sub-query responses from block 260 to generate a comprehensive response.” [The subqueries may be processed by a second generative model (i.e., second GMLM) in order to generate a comprehensive response (i.e., query result summary).]); and via the orchestrator agent, using the query result summaries to determine a subset of the query results for presentation via a device (see Kulkarni, Paragraph [0057], “the system proceeds to block 268 and provides the comprehensive response. For example, the system can cause the comprehensive response to be rendered (e.g., audibly and/or visually) at a client device, such as the client device via which the user interface input of block 252 was received.” [The comprehensive response (i.e., query results summaries) may be presented to the user.]). Regarding claim 2, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 1. Kulkarni further teaches: via the query input agent, receiving the query input from a user-preferred communication channel; and mapping the query input to a standardized query input (see Kulkarni, Paragraphs [0027], [0038], “The client device 110 can be, for example, one or more of: a desktop computer, a laptop computer, a tablet, a mobile phone, a computing device of a vehicle (e.g., an in-vehicle communications system, an in-vehicle entertainment system, an in-vehicle navigation system), a standalone interactive speaker (optionally having a display), a smart appliance such as a smart television, and/or a wearable apparatus of the user that includes a computing device (e.g., a watch of the user having a computing device, glasses of the user having a computing device, a virtual or augmented reality computing device). Additional and/or alternative client devices may be provided. … At block 252, the system receives an input query. The input query can be one formulated based on user interface input at a client device, such as typed input, voice input, input to cause an image to be captured or selected, etc. In some implementations, when the input includes content that is not in textual format, the system can convert the query to a textual format or other format.” [The query may be received from a plurality of user devices (i.e., a user-preferred communication channel). The system can convert the query to a textual format or other format (i.e., mapping the query input to a standardized query input).]). Regarding claim 3, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 1. Kulkarni further teaches: wherein the second instruction to the second GMLM is to cause the second GMLM to generate and include, in the query result summary, a first evaluation of the query input and the query result and a second evaluation of attributes of the query input and attributes of the query result (see Kulkarni, Paragraph [0053], “the system can process a prompt, that includes the sub-query responses and additional prompt text, using an LLM that is optionally fine-tuned based on comprehensive response generation data. For instance, the additional prompt text can include few shot example(s) of sub-queries and a corresponding comprehensive response and/or text such as “given [sub-query responses] create output that specifies a graphical user interface that conveys main components of the sub-query responses and that is organized in a logical manner. The comprehensive response can be determined based on LLM output generated by such processing.” [The subqueries may be processed by a second generative model (i.e., second GMLM) in order to generate a comprehensive response (i.e., query result summary). Additional prompt text (i.e., and a second evaluation of attributes of the query input and attributes of the query result) may be processed.]). Regarding claim 4, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 3. Kulkarni further teaches: wherein the second instruction is to cause the second GMLM to generate a comparison of the query input and the query result to a threshold (see Kulkarni, Paragraph [0057], “if a threshold quantity (e.g., 1, 2, 3 or other threshold) of iterations of blocks 264 and 266 have been performed, the system can proceed to block 268 after performing block 270 and cause, at block 268, the most recently generated refined comprehensive response to be provided.” [A threshold may be used to generate a refined comprehensive response based on a comparison between the input query and the comprehensive response.]). Regarding claim 5, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 3. Kulkarni further teaches: wherein the second instruction is to cause the second GMLM to classify an attribute of the query input into an input category of a plurality of input categories and use the input category to classify the attribute of the query result into an output category of a plurality of output categories (see Kulkarni, Paragraph [0092], “FIG. 3B2 illustrates the example client device 310 rendering a comprehensive response 365C1 and subsequent to the interaction of FIG. 3B1.” [Figure 3B2 shows a comprehensive response, which is categorized based on the input query.]). Regarding claim 6, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 5. Kulkarni further teaches: wherein the second GMLM is different from the first GMLM, and the second instruction comprises examples of query inputs and associated input categories, and examples of input categories and associated output categories (see Kulkarni, Paragraphs [0053], [0092], “the system can process a prompt, that includes the sub-query responses and additional prompt text, using an LLM that is optionally fine-tuned based on comprehensive response generation data. For instance, the additional prompt text can include few shot example(s) of sub-queries and a corresponding comprehensive response and/or text such as “given [sub-query responses] create output that specifies a graphical user interface that conveys main components of the sub-query responses and that is organized in a logical manner”. The comprehensive response can be determined based on LLM output generated by such processing. … FIG. 3B2 illustrates the example client device 310 rendering a comprehensive response 365C1 and subsequent to the interaction of FIG. 3B1.” [The LLM (i.e., second GMLM) may process additional information as well as output additional information, which is categorized as shown in Figure 3B2.]). Regarding claim 8, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 1. Kulkarni further teaches: the query execution agent determining whether a query of the plurality of queries is executing and messaging the orchestrator agent in response to determining that the query is finished executing; the orchestrator agent using the messaging to determine whether all queries of the plurality of queries are finished executing; and the orchestrator agent invoking the query evaluation agent in response to determining that all queries of the plurality of queries have finished executing (see Kulkarni, Paragraph [0057], “In some implementations, block 268 includes sub-block 268A where a push notification is provided to the client device to inform a user of availability of the comprehensive response. For example, the push notification can be provided if an application for rendering the comprehensive response is not active and selection of the push notification can cause the application to be launched in a state that renders the comprehensive response.” [A push notification may be provided to inform the user of the availability of the comprehensive response (i.e., determining that the query is finished executing).]). Regarding claim 9, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 1. Kulkarni further teaches: wherein the first instruction and the second instruction are included in one instruction to the GMLM (see Kulkarni, Paragraph [0037], “Turning now to FIG. 2 , a flowchart is depicted that illustrates an example method 200 of decomposing an input query into sub-queries and generating a comprehensive response based on responses to those subqueries.” [The method in Figure 2 decomposes an input query into sub-queries and generates a comprehensive response based on the sub-queries (i.e., wherein the first instruction and the second instruction are included in one instruction to the GMLM).]). Regarding claim 10, Kulkarni in view of Bhat, further in view of Wee teaches all the limitations of claim 1. Kulkarni further teaches: the query execution agent batching the query results per query of the plurality of queries; and the query evaluation agent causing the GMLM to generate the query result summaries per batch of query results (see Bhat, Paragraph [0046], “The architecture 400 can implement batch processing for multiple queries to be processed in parallel.” [Batch processing may be performed.]). Regarding claims 11-13, and 15-20, Kulkarni in view of Bhat, further in view of Wee teaches all of the limitations of claims 1-6 and 8-10, in method form rather than in system form and non-transitory computer-readable medium form. Kulkarni also discloses a system [0025] and non-transitory computer-readable medium [0115]. Therefore, the supporting rationale of the rejection to claims 1-6 and 8-10, applies equally as well to those elements of claims 11-13, and 15-20. Claims 7, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Kulkarni in view of Bhat in view of Wee, further in view of Gupta et al. (US 2025/0335795 A1). Regarding claim 7, Kulkarni in view of Bhat, further in view of Wee teaches all the teaches limitations of claim 1. However, the combination of Kulkarni, Bhat, and Wee do not explicitly teach: determining whether the query results comprise a threshold number of results; and in response to determining that the query results do not comprise the threshold number of results, iterating between the query execution agent and the query evaluation agent until the query results contain the threshold number of results. Gupta teaches: determining whether the query results comprise a threshold number of results; and in response to determining that the query results do not comprise the threshold number of results, iterating between the query execution agent and the query evaluation agent until the query results contain the threshold number of results (see Gupta, Paragraph [0064], “The query to the knowledge base can specify a threshold number of response query pairs to return and/or a threshold semantic similarity between the user query and corresponding queries in the query-response pairs to return.” [A threshold number of results may be incorporated in order to return a certain number of results.]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Kulkarni (teaching generative model based decomposition of input query into sub-queries and generation of comprehensive response based on responses to sub-queries) in view of Bhat (teaching Hierarchical cascade architecture of language models for multi-stage query classification and agent routing) in view of Wee (teaching devai model and system), further in view of Gupta (teaching unstructured data extraction with large language models for query resolution), and arrived at a method that incorporates a threshold number of results. One of ordinary skill in the art would have been motivated to make such a combination for the purposes of improving the quality of a large language model (see Gupta, Paragraph [0069]). In addition, the references (Kulkarni, Bhat, Wee, and Gupta) teach features that are directed to analogous art and they are directed to the same field of endeavor, such as large language models. The close relation between the references highly suggests an expectation of success. Regarding claim 14, Kulkarni in view of Bhat in view of Wee, further in view of Gupta teaches all of the limitations of claim 7, in method form rather than in system form and non-transitory computer-readable medium form. Kulkarni also discloses a system [0025] and non-transitory computer-readable medium [0115]. Therefore, the supporting rationale of the rejection to claim 7, applies equally as well to those elements of claim 14. Response to Arguments Applicant’s Arguments, filed June 11th, 2026, have been fully considered, but are not persuasive. Applicant argues on pages 8-9 of Applicant's Remarks that the cited references do not teach or suggest “via the query execution agent, executing the plurality of queries in a respective execution thread using the query input; via the query execution agent, sending a completion signal to the orchestration agent, wherein the completion signal indicates that the plurality of queries have finished executing.” The Examiner respectfully disagrees. Bhat discloses in paragraph [0061], “The query 402 can be a natural language query (or request, command) requesting generation of an output using one or more AI agents. The architecture 400 can be connected to multiple downstream AI agents (e.g., via a network connection, API interface), such as the AI agents 110 in FIG. 1 . Each AI agent can have a specific task or focus, such as managing inventory, making purchases, or providing customer service. The architecture 400 can be configured to route the query 402 to a set of one or more downstream AI agents that are chosen from multiple AI agents. The AI agents can be chosen such that the agents are capable of addressing the query (e.g., generating a response and/or performing an action according to a request of the query) and generating an output,” and paragraph [0062], “The architecture 400 includes a query preprocessing module 404. The query preprocessing module can perform an initial analysis on the query 402 and generate a query representation for use by the hierarchical model cascade 406, such as by transforming the query 402 into one or more representations used by models of the hierarchical model cascade 406. … The query representation (e.g., the query 402, the set of tokens, and/or a vector representation including one or more feature vectors) can be transmitted to the components of the architecture 400 (e.g., the levels 410) for processing and classification.” As shown, Bhat discloses processing a query by using one or more AI agents, and determining representations of the query to be processed by the hierarchical model cascade, which includes levels. Accordingly, Bhat discloses in paragraph [0078] “Multiple independent classification levels 410 can be executed in parallel (e.g., if the dynamic bypass controller 416 determines that two or more levels will be engaged). The architecture 400 can implement batch processing for multiple queries to be processed in parallel.” As shown, multiple independent classification levels may be executed in parallel, therefore a plurality of queries may be executed in a respective execution thread. Accordingly, Bhat discloses in paragraph [0047], “either the orchestrator agent can initially invoke only the general agent, which then further delegates sub-tasks, or the orchestrator agent can choose to directly identify and route work to the specialized sub-agent. … and then aggregate the results to produce an overall response.” As shown, the orchestrator agent delegates subtasks and then aggregates results to produce an overall response, therefore, indicating the orchestrator agent receives a completion signal that indicates the plurality of queries have finished executing. Applicant argues on pages 8-9 of Applicant's Remarks that the cited references do not teach or suggest “responsive to the completion signal, via the orchestrator agent, invoking the query evaluation agent.” The Examiner respectfully disagrees. Applicant’s Arguments, filed June 11th, 2026, have been fully considered, but are moot in light of the new grounds of rejection. For the above reasons, it is believed that the rejections should be sustained. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: 1.) Royer et al. (US 2026/0010768 A1), which discloses techniques for machine learning. 2.) Jones et al. (US 2025/0370909 A1), which discloses an optimization system for agentic applications. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 HUSAM TURKI SAMARA whose telephone number is (571)272-6803. The examiner can normally be reached on Monday - Thursday, Alternate Fridays. 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, Apu Mofiz can be reached on (571)-272-4080. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /HUSAM TURKI SAMARA/Examiner, Art Unit 2161 /APU M MOFIZ/Supervisory Patent Examiner, Art Unit 2161
Read full office action

Prosecution Timeline

Jan 31, 2025
Application Filed
Apr 08, 2026
Non-Final Rejection mailed — §103
May 18, 2026
Interview Requested
Jun 04, 2026
Applicant Interview (Telephonic)
Jun 04, 2026
Examiner Interview Summary
Jun 11, 2026
Response Filed
Oct 19, 2026
Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12762097
MIGRATING DEPLOYMENT INFRASTRUCTURE CONTAINERS ACROSS DIFFERENT DATABASES
4y 4m to grant Granted Oct 13, 2026
Patent 12737345
Quantization Error Compensation for Vector Computing
2y 6m to grant Granted Sep 15, 2026
Patent 12730796
CUSTOMIZING REPOSITORY IN A TABLE BASED CUSTOMIZING SCENARIO
3y 9m to grant Granted Sep 08, 2026
Patent 12724779
SYSTEMS METHODS AND APPARATUS FOR GENERATION OF A DATABASE OBJECT
7y 2m to grant Granted Sep 01, 2026
Patent 12675448
METHOD AND SYSTEM FOR LINKING DATA EVENTS AND STREAMS
2y 5m to grant Granted Jul 07, 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

3-4
Expected OA Rounds
56%
Grant Probability
74%
With Interview (+18.7%)
3y 8m (~1y 11m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 178 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