Prosecution Insights
Last updated: November 04, 2026
Application No. 18/634,939

DUAL-LAYERED ARTIFICIAL INTELLIGENCE SYSTEM WITH LARGE LANGUAGE MODELS AND DIFFERENT VIRTUAL AGENTS

Non-Final OA §112
Filed
Apr 13, 2024
Examiner
PHILLIPS, III, ALBERT M
Art Unit
2159
Tech Center
2100 — Computer Architecture & Software
Assignee
Bithuman Inc.
OA Round
1 (Non-Final)
82%
Grant Probability
Favorable
1-2
OA Rounds
4m
Est. Remaining
94%
With Interview

Examiner Intelligence

Grants 82% — above average
82%
Career Allowance Rate
598 granted / 734 resolved
+26.5% vs TC avg
Moderate +13% lift
Without
With
+12.9%
Interview Lift
resolved cases with interview
Typical timeline
2y 11m
Avg Prosecution
12 currently pending
Career history
760
Total Applications
across all art units

Statute-Specific Performance

§101
14.3%
-25.7% vs TC avg
§103
41.2%
+1.2% vs TC avg
§102
19.5%
-20.5% vs TC avg
§112
16.5%
-23.5% vs TC avg
Black line = Tech Center average estimate • Based on career data from 734 resolved cases

Office Action

§112
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 . Claim Rejections - 35 USC § 112 The following is a quotation of the first paragraph of 35 U.S.C. 112(a): (a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112: The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention. Claims 1-3 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention. The following is Examiner’s analysis of why claims 1-3 are rejected: Claim 1 Wands factor Analysis All elements (A)The breadth of the claims With respect to the breadth of a claim, the relevant concern is whether the scope of enablement provided to one skilled in the art by the disclosure is commensurate with the scope of protection sought by the claims. "[a]lthough a specification does not need to describe how to make and use every possible variant of the claimed invention, when a range is claimed, there must be reasonable enablement of the scope of the range." MPEP 2164.08 There are no variants discussed in the specification at all with respect to any of the elements in claim 1. The specification merely repeats the claim language. This factor does not favor enablement. A leading virtual agent with a first large language model, wherein the first large language model is trained with datasets that include goal setting, progress tracking, ethical guidelines, brand voice, and regulatory compliance, (B) The nature of the invention; (C) State of the prior art Whether the specification would have been enabling as of the filing date involves consideration of the nature of the invention, the state of the prior art, and the level of skill in the art. The initial inquiry is into the nature of the invention, i.e., the subject matter to which the claimed invention pertains. The nature of the invention becomes the backdrop to determine the state of the art and the level of skill possessed by one skilled in the art The state of the prior art is what one skilled in the art would have known, at the time the application was filed, about the subject matter to which the claimed invention pertains. The relative skill of those in the art refers to the skill of those in the art in relation to the subject matter to which the claimed invention pertains at the time the application was filed. The state of the prior art provides evidence for the degree of predictability in the art and is related to the amount of direction or guidance needed in the specification as filed to meet the enablement requirement. The state of the prior art is also related to the need for working examples in the specification. The specification need not disclose what is well-known to those skilled in the art and preferably omits that which is well-known to those skilled and already available to the public. 2164.05(a) Examiner finds the nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the models are trained and/or how the goal setting, progress tracking, ethical guidelines, brand voice, and regulatory compliance datasets are formed. This factor does not favor enablement wherein the first large language model is trained with a second set of datasets that encompass general knowledge, specific domain ability, and user interaction protocols, wherein the leading virtual agent with the first large language model is trained to be an expert for high-level tasks (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the models is trained with a second set of datasets that encompass general knowledge, specific domain ability, and user interaction protocols and/or how leading virtual agent with the first large language model is trained to be an expert for high-level tasks. This factor does not favor enablement wherein the leading virtual agent is only one virtual agent that is informed that the leading virtual agent is configured to guide other agents to a higher-level task within the dual-layered artificial intelligence system, wherein the leading virtual agent is only virtual agent that is configured to interface with any customer, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the leading virtual agent is to guide the other agents within the system, and/or how the virtual agent interface is configured to interface with any customer. This factor does not favor enablement wherein the leading virtual agent is configured to perform any higher-level task that leads other task-specific agents; (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the leading virtual agent performs any higher-level task that leads other task-specific agents. This factor does not favor enablement a set of other virtual agents with a set of large language models individually, each of the set of other virtual agents is trained by a specified large language model of the set of large language models, wherein the set of large language models are trained with specialized focuses that are called upon at any given moment from the leading virtual agent, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how agents are trained by the LLMs and/or how the LLMs are trained with specialized focuses that are called upon at any given moment from the leading virtual agent. This factor does not favor enablement wherein the process is configured to serve as guardrails to ensure that outputs stay within predefined parameters, wherein a set of predefined parameters comprise brand consistency, ethical considerations, and other overarching goals, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the process is configured to serve as guardrails to ensure that outputs stay within predefined parameters and/or what makes up the parameters that comprise brand consistency, ethical considerations, and other overarching goals. This factor does not favor enablement wherein the set of other virtual agents are configured to have no knowledge that another virtual agent is guiding them, wherein the set of other agents are configured to communicate their interactions with users regularly to the leading virtual agent, wherein the leading virtual agent is configured to drives the set of other virtual agents to deliver optimal solutions, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how virtual agents are configured to have no knowledge that another virtual agent is guiding them and/or how the set of other agents are configured to communicate their interactions with users regularly to the leading virtual agent and/or how the leading virtual agent is configured to drive[] the set of other virtual agents to deliver optimal solutions. This factor does not favor enablement an artificial intelligence engine coupled to both the leading virtual agent and the set of other virtual agents, wherein the artificial intelligence engine is configured to adjust input datasets and parameters of the first large language model, the second large language model and the set of large language models, wherein the artificial intelligence engine is configured to convey instructions from the leading virtual agent to the set of other virtual agents. (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how to adjust input datasets and parameters of the first large language model, the second large language model and the set of large language models, and/or how the artificial intelligence engine is configured to convey instructions from the leading virtual agent to the set of other virtual agents. This factor does not favor enablement All elements in claim 1 (D) The level of one of ordinary skill; Examiner finds the level of ordinary skill in the art of multi agent LLM prompting/programming is relatively high. This factor favors enablement All elements in claim 1 (E) The level of predictability in the art; Examiner finds the level of predictability in the art is moderate to high as of the filing date of the invention. This factor favors enablement All elements in claim 1. (F) The amount of direction provided by the inventor; The amount of guidance or direction needed to enable the invention is inversely related to the amount of knowledge in the state of the art as well as the predictability in the art. . . . The "amount of guidance or direction" refers to that information in the application, as originally filed, that teaches exactly how to make or use the invention. The more that is known in the prior art about the nature of the invention, how to make, and how to use the invention, and the more predictable the art is, the less information needs to be explicitly stated in the specification. 2164.03 Even though the art is relatively predictable, Examiner finds that at least some direction must be given in order to make and use the invention. Examiner finds the inventor provides zero direction with respect to any of the elements in claim 1. The specification merely repeats the claim language. This factor does not favor enablement All elements in claim 1. (G) The existence of working examples Examiner finds specification fails to disclose any working examples for any of the elements in claim 1. The specification merely repeats the claim language. This factor does not favor enablement All elements of claim 1 (H)The quantity of experimentation needed to make or use the invention based on the content of the disclosure. The first category of such block diagram cases involves systems which include a computer as well as other system hardware and/or software components. In order to meet the burden of establishing a reasonable basis for questioning the adequacy of such disclosure, the examiner should initiate a factual analysis of the system by focusing on each of the individual block element components. More specifically, such an inquiry should focus on the diverse functions attributed to each block element as well as the teachings in the specification as to how such a component could be implemented. While no specific universally applicable rule exists for recognizing an insufficiently disclosed application involving computer programs, an examining guideline to generally follow is to challenge the sufficiency of disclosures that fail to include the programmed steps, algorithms or procedures that the computer performs necessary to produce the claimed function. These can be described in any way that would be understood by one of ordinary skill in the art, such as with a reasonably detailed flowchart which delineates the sequence of operations the program must perform. In programming applications where the software disclosure only includes a flowchart, as the complexity of functions and the generality of the individual components of the flowchart increase, the basis for challenging the sufficiency of such a flowchart becomes more reasonable because the likelihood of more than routine experimentation being required to generate a working program from such a flowchart also increases 2164.06(c) (Emphasis added). Examiner finds the specification does not teach how to implement any of the elements of claim 1, even at a high level. There are no prompts, code, pseudo-code, flowcharts, etc. that describe in any detail how to make and use any of the elements in claim 1. The flowcharts are nothing more than a reproduction of the claim language. This factor does not favor enablement Claim 2 Wands factor Analysis All elements except: “wherein the set of other virtual agents are configured to be displayed in LED/OLED displays, Android/iOS tablets, Laptops/PCs, smartphones, or VR/AR goggles “wherein any of the set of other virtual agents is configured to be displayed in full body or half body portrait mode” (A)The breadth of the claims With respect to the breadth of a claim, the relevant concern is whether the scope of enablement provided to one skilled in the art by the disclosure is commensurate with the scope of protection sought by the claims. "[a]lthough a specification does not need to describe how to make and use every possible variant of the claimed invention, when a range is claimed, there must be reasonable enablement of the scope of the range." MPEP 2164.08 There are no variants discussed in the specification at all with respect to this claim language. The specification merely repeats the claim language. The only variants described are the ones taught in Figs. 4-10 (i.e. displaying agents on various devices). This factor does not favor enablement. A method for providing services via a leading virtual agent and a set of other virtual agents with artificial intelligence, the method comprising: detecting, by one or more processors, a request from a first user, wherein the request could be a request to be educated with a specifically tailored class with a set of other virtual agents with artificial intelligence, wherein a specifically tailored class is configured to execute a specific plan for the user for the education (B) The nature of the invention; (C) State of the prior art Whether the specification would have been enabling as of the filing date involves consideration of the nature of the invention, the state of the prior art, and the level of skill in the art. The initial inquiry is into the nature of the invention, i.e., the subject matter to which the claimed invention pertains. The nature of the invention becomes the backdrop to determine the state of the art and the level of skill possessed by one skilled in the art The state of the prior art is what one skilled in the art would have known, at the time the application was filed, about the subject matter to which the claimed invention pertains. The relative skill of those in the art refers to the skill of those in the art in relation to the subject matter to which the claimed invention pertains at the time the application was filed. The state of the prior art provides evidence for the degree of predictability in the art and is related to the amount of direction or guidance needed in the specification as filed to meet the enablement requirement. The state of the prior art is also related to the need for working examples in the specification. The specification need not disclose what is well-known to those skilled in the art and preferably omits that which is well-known to those skilled and already available to the public. 2164.05(a) Examiner finds The nature of the invention requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the detecting of the request is performed and/or what “a request to be educated with a specifically tailored class with a set of other virtual agents with artificial intelligence” is and/or how a specifically tailored class executes a specific plan for the user for the education. This factor does not favor enablement wherein the leading virtual agent is trained with datasets that include goal setting, progress tracking, ethical guidelines, brand voice, and regulatory compliance, wherein the leading virtual agent with the first large language model is trained to be an expert for high-level tasks, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the datasets are formed and/or how the model is trained to be an expert for high-level tasks. This factor does not favor enablement wherein the leading virtual agent is only one virtual agent that is informed that the leading virtual agent is configured to guide other agents to a higher-level task, wherein the leading virtual agent is only one virtual agent interfacing with users, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the leading virtual agent is to guide the other agents to a higher-level task, and/or how the virtual agent interfaces with user. This factor does not favor enablement wherein the leading virtual agent is configured to monitor the set of other virtual agents, wherein the leading virtual agent is configured to ensure the set of other virtual agents to adhere to a broader set of goals; (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the leading virtual agent is to monitor the set of other virtual agents and/or ensure the set of other virtual agents to adhere to a broader set of goals. This factor does not favor enablement activating a first other virtual agent of the set of other virtual agents with artificial intelligence, wherein the first other virtual agent is picked by the leading virtual agent with leading artificial intelligence, wherein the pick of the first other virtual agent is determined by specifics and configurations of the first other virtual agent and specific needs from the first user, wherein the first other virtual agent is configured to give educational information and specific material to the leading virtual agent (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how a first other virtual agent of the set of other virtual agents with artificial intelligence is activated and/or how the virtual agent is determined by specifics and configurations of the first other virtual agent and specific needs from the first user and/or how the virtual agent gives educational information and specific material to the leading virtual agent. This factor does not favor enablement wherein the leading virtual agent is configured to [perform] educational service that comprises teaching the first user, interacting with the first user, answering questions from the first user, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the leading virtual agent is to perform teaching the first user, interacting with the first user, and/or answering questions from the first user. This factor does not favor enablement wherein the wherein the set of other virtual agents are configured to collaborate with each other, wherein the first other customer-facing virtual agent is interacting with the leading virtual agent, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the other virtual agents are to collaborate with each other and/or how the first other customer-facing virtual agent interacts with the leading virtual agent. This factor does not favor enablement wherein an artificial intelligence engine is coupled to the one or more processors and a server and to the leading virtual agent and the set of customer-facing virtual agents (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the coupling is implemented. This factor does not favor enablement wherein the artificial intelligence engine is trained by human experts in the field, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the engine is trained by human experts in the field. This factor does not favor enablement wherein the set of other virtual agents are configured to be displayed in LED/OLED displays, Android/iOS tablets, Laptops/PCs, smartphones, or VR/AR goggles, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The drawings (e.g. Figs 4-10 ) provide some minimal guidance as to how the agents are displayed on various devices. This factor does favor enablement for this element. wherein a set of multi-layer info panels coupled to the one or more processors are configured to overlay graphics on top of the set of virtual agents, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the set of multi-layer info panels are configured to overlay graphics on top of the set of virtual agents. This factor does not favor enablement wherein any of the set of other virtual agents are configured to be displayed with an appearance of a real human or a humanoid or a cartoon character, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The drawings provide minimal guidance as to how a human is displayed (e.g. Fig. 9), however, the specification fails to provide guidance on “cartoon character” or “humanoid.” This factor does not favor enablement wherein any of the set of virtual agents’ gender, age and ethnicity is determined by the artificial Intelligence’s analysis on input from the user, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the AI’s analysis of a user’s input determines the virtual agents’ gender age, and ethnicity. This factor does not favor enablement wherein any of the set of other virtual agents is configured to be displayed in full body or half body portrait mode, (B) The nature of the invention; (C) State of the prior art The factor for this specific element does favor enablement. See Applicant’s Figs. 4-6. wherein the artificial intelligence engine is configured for real-time speech recognition, speech to text generation, real-time dialog generation, text to speech generation, voice-driven animation, and human avatar generation (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the AI’s engine is configured/programmed for real-time speech recognition, speech to text generation, real-time dialog generation, text to speech generation, voice-driven animation, and human avatar generation. This factor does not favor enablement wherein the artificial intelligence engine is configured to emulate different voices and use different languages (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the AI’s engine is configured/programmed to emulate different voices and use different languages. This factor does not favor enablement modifying education activities from the first other virtual agent based on guidelines and input from the leading virtual agent with communication between the first other virtual agent and the leading virtual agent; recording the modification and feedback from the first user; and training other virtual agents of the set of other virtual agents based on the recording. (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how to modify education activities from the first other virtual agent based on guidelines and input from the leading virtual agent with communication between the first other virtual agent and the leading virtual agent; and/or how to record the modification and feedback from the first user; and/or how to train other virtual agents of the set of other virtual agents based on the recording. This factor does not favor enablement All elements in claim 2 (D) The level of one of ordinary skill; Examiner finds the level of ordinary skill in the art of multi agent LLM prompting/programming is relatively high. This factor favors enablement All elements in claim 2 (E) The level of predictability in the art; Examiner finds the level of predictability in the art is moderate to high as of the filing date of the invention. This factor favors enablement All elements in claim 2 except displaying agents on devices. See above. (F) The amount of direction provided by the inventor; The amount of guidance or direction needed to enable the invention is inversely related to the amount of knowledge in the state of the art as well as the predictability in the art. . . . The "amount of guidance or direction" refers to that information in the application, as originally filed, that teaches exactly how to make or use the invention. The more that is known in the prior art about the nature of the invention, how to make, and how to use the invention, and the more predictable the art is, the less information needs to be explicitly stated in the specification. 2164.03 Even though the art is relatively predictable, Examiner finds that at least some direction must be given in order to enable the invention. With the exception of Figs. 4-10 and corresponding claim elements, Examiner finds the inventor provides zero direction with respect to any of the remaining elements in claim 2. The specification merely repeats the claim language. This factor does not favor enablement All elements in claim 2 except displaying agents on devices. See above. (G) The existence of working examples Examiner finds specification fails to disclose any working examples for any of the elements in claim 2 except the elements corresponding to Figs. 4-10. See above. The specification merely repeats the claim language for the rest of the claim elements. This factor does not favor enablement All elements of claim 2 except displaying agents on devices. See above. (H)The quantity of experimentation needed to make or use the invention based on the content of the disclosure. The first category of such block diagram cases involves systems which include a computer as well as other system hardware and/or software components. In order to meet the burden of establishing a reasonable basis for questioning the adequacy of such disclosure, the examiner should initiate a factual analysis of the system by focusing on each of the individual block element components. More specifically, such an inquiry should focus on the diverse functions attributed to each block element as well as the teachings in the specification as to how such a component could be implemented. While no specific universally applicable rule exists for recognizing an insufficiently disclosed application involving computer programs, an examining guideline to generally follow is to challenge the sufficiency of disclosures that fail to include the programmed steps, algorithms or procedures that the computer performs necessary to produce the claimed function. These can be described in any way that would be understood by one of ordinary skill in the art, such as with a reasonably detailed flowchart which delineates the sequence of operations the program must perform. In programming applications where the software disclosure only includes a flowchart, as the complexity of functions and the generality of the individual components of the flowchart increase, the basis for challenging the sufficiency of such a flowchart becomes more reasonable because the likelihood of more than routine experimentation being required to generate a working program from such a flowchart also increases 2164.06(c) (Emphasis added). Examiner finds the specification does not teach how to implement any of the elements of claim 2, except the elements corresponding to Fig. 4-10. There are no prompts, code, pseudo-code, flowcharts, etc. that describe in any detail how to make and use any of the elements in claim 2 except for the few displaying elements corresponding to Figs. 4-10. The flowcharts, for example, are nothing more than a reproduction of the claim language. This factor does not favor enablement Claim 3 Wands factor Analysis Claim 3 recites all the elements of claim 2. As such, the analysis for those elements apply to claim 3 also. All elements except wherein the set of other virtual agents are configured to be displayed in LED/OLED displays, Android/iOS tablets, Laptops/PCs, smartphones, or VR/AR goggles wherein any of the set of other virtual agents is configured to be displayed in full body or half body portrait mode (A)The breadth of the claims With respect to the breadth of a claim, the relevant concern is whether the scope of enablement provided to one skilled in the art by the disclosure is commensurate with the scope of protection sought by the claims. "[a]lthough a specification does not need to describe how to make and use every possible variant of the claimed invention, when a range is claimed, there must be reasonable enablement of the scope of the range." MPEP 2164.08 There are no variants discussed in the specification at all with respect to this claim language. The specification merely repeats the claim language. The only variants described are the ones taught in Figs. 4-10 (i.e. displaying agents on various devices). This factor does not favor enablement. activating a second other virtual agent of the set of other virtual agents with artificial intelligence, wherein the second other virtual agent is picked by the leading virtual agent with leading artificial intelligence, wherein the pick of the second other virtual agent is determined by specifics and configurations of the second other virtual agent and specific needs from the second user, wherein the second other virtual agent is configured to give educational information and specific material to the leading virtual agent (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how a second other virtual agent of the set of other virtual agents with artificial intelligence is activated and/or how the virtual agent is determined by specifics and configurations of the second other virtual agent and specific needs from the second user and/or how the virtual agent gives educational information and specific material to the leading virtual agent. This factor does not favor enablement wherein the leading virtual agent is configured to [perform] educational service that comprises teaching the second user, interacting with the second user, answering questions from the second user, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the leading virtual agent is to perform teaching the second user, interacting with the second user, and/or answering questions from the second user. This factor does not favor enablement wherein the wherein the set of other virtual agents are configured to collaborate with each other, wherein the second other customer-facing virtual agent is interacting with the leading virtual agent, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the other virtual agents are to collaborate with each other and/or how the second other customer-facing virtual agent interacts with the leading virtual agent. This factor does not favor enablement wherein an artificial intelligence engine is coupled to the one or more processors and a server and to the leading virtual agent and the set of customer-facing virtual agents (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the coupling is implemented. This factor does not favor enablement wherein the artificial intelligence engine is trained by human experts in the field, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how the engine is trained by human experts in the field. This factor does not favor enablement wherein the set of other virtual agents are configured to be displayed in LED/OLED displays, Android/iOS tablets, Laptops/PCs, smartphones, or VR/AR goggles, wherein a set of multi-layer info panels coupled to the one or more processors are configured to overlay graphics on top of the set of virtual agents, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The drawings (e.g. Figs 4-10 ) provide some minimal guidance as to how the agents are displayed on various devices. However, the specification provides no guidance as to how the set of multi-layer info panels are configured to overlay graphics on top of the set of virtual agents. This factor does not favor enablement wherein any of the set of other virtual agents are configured to be displayed with an appearance of a real human or a humanoid or a cartoon character, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The drawings provide minimal guidance as to how a human is displayed (e.g. Fig. 9), however, the specifications fails to provide guidance on “cartoon character” or “humanoid.” This factor does not favor enablement wherein any of the set of virtual agents’ gender, age and ethnicity is determined by the artificial Intelligence’s analysis on input from the user, (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the AI’s analysis of a user’s input determines the virtual agents’ gender age, and ethnicity. This factor does not favor enablement wherein any of the set of other virtual agents is configured to be displayed in full body or half body portrait mode, (B) The nature of the invention; (C) State of the prior art The factor for this specific element does favor enablement. See Applicant’s Figs. 4-6. wherein the artificial intelligence engine is configured for real-time speech recognition, speech to text generation, real-time dialog generation, text to speech generation, voice-driven animation, and human avatar generation (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the AI’s engine is configured/programmed for real-time speech recognition, speech to text generation, real-time dialog generation, text to speech generation, voice-driven animation, and human avatar generation. This factor does not favor enablement wherein the artificial intelligence engine is configured to emulate different voices and use different languages (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. The specification provides no guidance as to how the AI’s engine is configured/programmed to emulate different voices and use different languages. This factor does not favor enablement modifying education activities from the second other virtual agent based on guidelines and input from the leading virtual agent with communication between the second other virtual agent and the leading virtual agent; recording the modification and feedback from the second user; and training other virtual agents of the set of other virtual agents based on the recording. (B) The nature of the invention; (C) State of the prior art Examiner finds The nature of the invention (multi agent LLMs) requires at least some guidance as to how to make and use the invention. Here, the specification provides no guidance as to how to modify education activities from the second other virtual agent based on guidelines and input from the leading virtual agent with communication between the second other virtual agent and the leading virtual agent; and/or how to record the modification and feedback from the second user; and/or how to train other virtual agents of the set of other virtual agents based on the recording. This factor does not favor enablement All elements in claim 3 (D) The level of one of ordinary skill; Examiner finds the level of ordinary skill in the art of multi agent LLM prompting/programming is relatively high. This factor favors enablement All elements in claim 3 (E) The level of predictability in the art; Examiner finds the level of predictability in the art is moderate to high as of the filing date of the invention. This factor favors enablement All elements in claim 3 except displaying agents on devices. See above. (F) The amount of direction provided by the inventor; The amount of guidance or direction needed to enable the invention is inversely related to the amount of knowledge in the state of the art as well as the predictability in the art. . . . The "amount of guidance or direction" refers to that information in the application, as originally filed, that teaches exactly how to make or use the invention. The more that is known in the prior art about the nature of the invention, how to make, and how to use the invention, and the more predictable the art is, the less information needs to be explicitly stated in the specification. 2164.03 Even though the art is relatively predictable, Examiner finds that at least some direction must be given in order to enable the invention. With the exception of Figs. 4-10 and corresponding claim elements, Examiner finds the inventor provides zero direction with respect to any of the remaining elements in claim 2. The specification merely repeats the claim language. This factor does not favor enablement All elements in claim 3 except displaying agents on devices. See above. (G) The existence of working examples Examiner finds specification fails to disclose any working examples for any of the elements in claim 2 except the elements corresponding to Figs. 4-10. See above. The specification merely repeats the claim language for the rest of the claim elements. This factor does not favor enablement All elements of claim 3 except displaying agents on devices. See above. (H)The quantity of experimentation needed to make or use the invention based on the content of the disclosure. The first category of such block diagram cases involves systems which include a computer as well as other system hardware and/or software components. In order to meet the burden of establishing a reasonable basis for questioning the adequacy of such disclosure, the examiner should initiate a factual analysis of the system by focusing on each of the individual block element components. More specifically, such an inquiry should focus on the diverse functions attributed to each block element as well as the teachings in the specification as to how such a component could be implemented. While no specific universally applicable rule exists for recognizing an insufficiently disclosed application involving computer programs, an examining guideline to generally follow is to challenge the sufficiency of disclosures that fail to include the programmed steps, algorithms or procedures that the computer performs necessary to produce the claimed function. These can be described in any way that would be understood by one of ordinary skill in the art, such as with a reasonably detailed flowchart which delineates the sequence of operations the program must perform. In programming applications where the software disclosure only includes a flowchart, as the complexity of functions and the generality of the individual components of the flowchart increase, the basis for challenging the sufficiency of such a flowchart becomes more reasonable because the likelihood of more than routine experimentation being required to generate a working program from such a flowchart also increases 2164.06(c) (Emphasis added). Examiner finds the specification does not teach how to implement any of the elements of claim 2, except the elements corresponding to Fig. 4-10. There are no prompts, code, pseudo-code, flowcharts, etc. that describe in any detail how to make and use any of the elements in claim 2 except for the few displaying elements corresponding to Figs. 4-10. The flowcharts, for example, are nothing more than a reproduction of the claim language. This factor does not favor enablement Thus, for the reasons above, claims 1-3 is rejected under 35 USC 112(a). Examiner recommends filing a continuation in part application and amending the specification to cure the deficiencies of this patent application. Conclusion The following prior art is pertinent to Applicant’s disclosure: Mukherjee, Polaris: A Safety-focused LLM Constellation Architecture for Healthcare 20 Mar 2024 p. 4; Fig. 1(a) (Primary Agent is first layer and “support agents” are second layer); abstract p. 5 Such a system will allow the human healthcare providers to focus on top-of-license diagnostic and clinical tasks, thereby helping to alleviate staffing shortages. The agents are designed with built-in safety guardrails that ensure appropriate human supervision p .6 The primary agent is trained to be aligned with nurse-like conversations geared for building trust, rapport and empathy with patients, as well as accomplishing healthcare-specific tasks typically performed by nurses, medical assistants, social workers, and nutritionists. We develop techniques to make the primary agent stateful to navigate through a long checklist of care protocols p. 9 The internal state of Polaris evolves as a result of the primary agent’s interactions with the user and the message passing conducted by the support agents. To explain this more clearly we adopt the following notation for the system components: Polaris mediates the message passing between agents with deterministic imperative programming. This allows us to keep the output space of the support agents well-constrained and implement control-flow logic to support customized protocols. The tasks which are given to the primary agent are systematically formatted and use synthesized information from multiple agents when applicable. This framework facilitates a cooperative approach to complex dialogue generation, where multiple agents contribute to the overall conversation dynamics. An overall step of the constellation system is described in Algorithm (primary agent can call upon p. 17 section 4 first paragraph p. 11 section 3.1.1 We first train our foundation model on a massive collection of proprietary data including clinical care plans, healthcare regulatory documents, medical manuals, drug databases, and other high-quality medical reasoning documents. The objective of this phase is to incorporate fine-grained medical knowledge, reasoning and specialized numerical reasoning (e.g., dosage calculations). We further annotated some of the medical datasets with reasoning chains to further enhance the medical reasoning capabilities of the model. p.16, Fig. 5 They are shown here simply to illustrate how the primary agent assimilates distinct tasks inserted by the various support agents to form a cogent response that is safe, informative and relevant to the utterance Lee, You’ve Got an Enterprise LLM – Now What?, Feb 2, 2024 pages 4-5: An enterprise LLM may be trained on thousands of data sets. But a one-size-fits-all model doesn’t automatically reflect your brand voice and definitely does not include your company’s proprietary data. That’s why any AI project must start with a solid data foundation What’s the secret to making this happen? Integrations that connect your data and applications from any system, whether cloud or on-premise. In this scenario, CRM, payment and logistics systems work in harmony to create a better customer experience. “You’ve got to figure out the data sources you need to unlock, how they will feed your LLM,and how you can create a 360-degree view of your customer,” said Egts. Without addressing systems integration challenges, your AI relies on generic data that doesn’t benefit your business or your customers. Cheng, Exploring Large Language Model Based Intelligent Agents: Definitions, Methods, And Prospects 7 Jan 2024 p. 21 In the CPDE paradigm, a centralized LLM is responsible for planning on behalf of all agents encompassed within the system. This requires the LLM to consider all agents’ objectives, capabilities, and constraints to devise appropriate action plans for them. As highlighted in Gong et al. [181], the planner must concurrently manage multiple agents, circumvent potential conflicts, and coordinate them to accomplish a shared goal necessitating intricate collaborations. Upon finalizing the planning, each agent independently carries out its designated tasks without further interaction with the central LLM. The merit of this approach resides in optimizing overall performance at a global scale, as the central LLM can consider the needs and resources of all agents. Li et al. [72] develops SAMA in both overcooked [182] and MiniRTS [183] multi-agent environments by employing a centralized LLM to facilitate goal generation, goal decomposition, goal allocation, and replanning with self-reflection Everest US 12,242,945 Col. 51:49-col. 52:2 Fig. 2 (Examiner finds one or more dialog boxes 216 teaches multi-layer info panels overlaid on top of the set of virtual agents (model 212)) SAPIEN: Affective Virtual Agents Powered by Large Language Models Fig. 1 page 1 Users can choose from a wide range of virtual agent avatars that reflect a diverse array of ages, gender, and ethnicities. Going further, users can select the desired personality, background, and conversational context of a virtual agent, creating an experience tailored to their specific needs or preferences. Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALBERT M PHILLIPS, III whose telephone number is (571)270-3256. The examiner can normally be reached 10a-6:30pm EST M-F. 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, Ann J Lo can be reached at (571) 272-9767. 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. /ALBERT M PHILLIPS, III/Primary Examiner, Art Unit 2159
Read full office action

Prosecution Timeline

Apr 13, 2024
Application Filed
Aug 18, 2026
Non-Final Rejection mailed — §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12784052
ALERT REVIEW USING MACHINE LEARNING AND INTERACTIVE VISUALIZATIONS
4y 2m to grant Granted Nov 03, 2026
Patent 12783949
ADAPTIVELY TRAINING A MACHINE LEARNING MODEL FOR ESTIMATING ENERGY CONSUMPTION IN A CLOUD COMPUTING SYSTEM
3y 5m to grant Granted Nov 03, 2026
Patent 12775526
TECHNIQUES FOR MAINTAINING SNAPSHOT DATA CONSISTENCY DURING FILE SYSTEM CROSS-REGION REPLICATION
1y 5m to grant Granted Oct 27, 2026
Patent 12762118
System and Method for Database Command Query Migration
1y 10m to grant Granted Oct 13, 2026
Patent 12762162
Identifying Missing Nodes Within a Graphically Represented Family
1y 3m to grant Granted Oct 13, 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
82%
Grant Probability
94%
With Interview (+12.9%)
2y 11m (~4m remaining)
Median Time to Grant
Low
PTA Risk
Based on 734 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