DETAILED ACTION
This action is in response to the application filed on December 30th, 2024. Claims 1-20 are pending and have been examined.
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 Objections
Claims 6, 7, 12, and 20 objected to because of the following informalities:
Claim 6 reads “the third automative assistant” in lines 2 and 4, but should read “the third automated assistant”.
Claim 7 reads “the third automative assistant” in line 4, but should read “the third automated assistant”.
Claim 12 reads “the third automative assistant” in lines 2 and 4, but should read “the third automated assistant”.
Claim 20 reads “collaboration platform” in line 2, but should read “the collaboration platform”.
Appropriate correction is required.
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 (i.e., changing from AIA to pre-AIA ) 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.
Claim(s) 1, 2, and 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal et al. (US Pat. Pub. No. 2025/0291583 A1 hereinafter Agarwal), in view of Vikramathithan et al. (US Pat. Pub. No. 2026/0093507 A1 hereinafter Vikramathithan), Zhou et al. (US Pat. Pub. No. 2026/0079682 A1 hereinafter Zhou), and Aghajanyan et al. (US Pat. Pub. No. 2025/0117410 A1 hereinafter Aghajanyan).
Regarding claim 1, Agarwal discloses a computer-implemented method for invoking multiple automated assistant services using an automation rule within a collaboration platform, the method comprising: in response to a first user input to the automation generation user interface, generating a first automation component (Agarwal, Fig. 4A, 402; [0050]: "Attention now turns to an exemplary flow of the autonomous processing for the generation of a unit test case 400. Turning to FIGS. 4A and 4B, a user enters the task “Write a pytest test case for the method read_atom from the file <file path><read_atom.py>. The test case should be placed in the new file <new file path>” (step 402)."), the first automation component including: reference to a first automated assistant service of a set of automated assistant services (Agarwal, Fig. 4A, 404-406; [0051]: "The conversation manager receives the task and creates a conversation with a single message which includes the user task (step 404). The conversation is transmitted to the AI-agent scheduler (step 404) which determines, based on the scheduling algorithm, which AI-agent should be invoked at this step (step 406)."); and reference to a first natural language command to be used by the first automated assistant service to generate a first prompt, execution of the first automation component causes the first automated assistant service to provide the first prompt to a generative output engine thereby causing the first automated assistant service to generate a first generative response (Agarwal, Fig. 4A, 406-410; [0052]: "The AI-agent scheduler transmits the conversation to the AI-agent (step 406). The AI-agent constructs a prompt including its system prompt, instructions, available actions, and the current state of the conversation, and sends this prompt to the generative neural model to generate the command needed to perform the task (step 408). The generative neural model responds with a pytest test case for the method read_atom and the command “write <new filename>:<new file location>” (step 410)."); generating a second automation component, the second automation component including: reference to a second automated assistant service of the set of automated assistant services, execution of the second automation component causes the second automated assistant service to generate a second prompt including the first generative response and provide the second prompt to the generative output engine thereby causing the second automated assistant service to generate a second generative response (Agarwal, Fig. 4A, 418-422; [0053]: "The conversation manager transmits the conversation to the AI-agent scheduler (step 418) which transmits it to an appropriate AI-agent (step 420). The AI-agent creates a prompt to the generative neural model to determine a follow-on task (step 420). The prompt includes the AI-agent system prompt, instructions, available actions and the current state of the conversation (step 420). The generative neural model responds with the follow-on task “Syntax <new filename><new file location>” (step 422)."); and generating a third automation component, the third automation component including: reference to a third automated assistant service of the set of automated assistant services, execution of the third automation component causes the third automated assistant service to generate a third prompt including the structured data object of the second generative response and provide the third prompt to the generative output engine thereby causing the third automated assistant service to generate a third generative response, execution of the third automation component is configured to cause the automation rule to generate content within the collaboration platform, the content based on the third generative response (Agarwal, Fig. 4A and Fig. 4B, 430-436; [0055]-[0056]: "The conversation manager interacts with the AI-agent scheduler for a follow-on task given the current state of the conversation (step 430). The AI-agent scheduler finds an appropriate AI-agent (step 432) and the AI-agent generates a prompt to the generative neural model for commands for a follow-on task given the current state of the conversation (step 432). The prompt includes the AI-agent's system prompt, instructions, available actions, and the current state of the conversation (step 432). The generative neural model responds with the instruction to test the new file with “test-file <join_mp4_test.py>” (step 434). The parser extracts the command from the model's response and invokes the testing API to perform the test (step 436)."). However, Agarwal fails to expressly recite causing display of an automation generation user interface in a frontend of the collaboration platform; a second user input to the automation generation user interface; a structured data object representation of the first generative response; and a third user input to the automation generation user interface.
Vikramathithan teaches causing display of an automation generation user interface in a frontend of the collaboration platform (Vikramathithan, [0007]: "The AI powered assistant engine provides a co-pilot guided experience and automation using contextual knowledge. The method includes receiving, by the AI powered assistant engine, one or more inputs from a user via a user interface initiating a conversation; providing, by the AI powered assistant engine, one or more AI models based on the one or more inputs").
Agarwal and Vikramathithan are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal to incorporate the teachings of Vikramathithan to include a frontend user interface with various controls. This allows the system to collect numerous inputs from a user as well as display various information for the user (Vikramathithan, [0132]). This creates a better experience for the user when interacting with the system. However, Agarwal, in view of Vikramathithan, fails to expressly recite a second user input to the automation generation user interface; a structured data object representation of the first generative response; and a third user input to the automation generation user interface.
Zhou teaches a second user input to the automation generation user interface; and a third user input to the automation generation user interface (Zhou, Fig. 2; [0038]: "A user 220 may approve a proposed task in at least some cases, and a corresponding task approval 222 may be sent to an automated task implementation fleet 230."; "The updates to the target service data sources may in turn result in the generation of additional optimization tasks, causing a new round of operations shown in FIG. 2.").
Agarwal, Vikramathithan, and Zhou, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, to incorporate the teachings of Zhou to collect multiple user inputs throughout the system’s processing. Collecting additional inputs can be used for user approvals at various steps of the processing (Zhou, [0016]), thus improving the systems performance overtime by integrating user feedback. However, Agarwal, in view of Vikramathithan and Zhou, fails to expressly recite a structured data object representation of the first generative response.
Aghajanyan teaches a structured data object representation of the first generative response (Aghajanyan, [0069]: "The techniques discussed in connection with FIG. 4 and elsewhere herein enable building AI agents with configurable workflows to process natural language queries. The submitted queries are analyzed and the system assembles a customized toolchain of models and data into a structured workflow that is generated (e.g., optimized) for that query. Based on analysis of a query's goals and context (e.g., using natural language processing/understanding techniques), the system selects a sequence of states to form a structured workflow to answer that given query."; [0074]: "In certain example embodiments, the ordering may be determined by constructing a prompt with the states that have been determined from 402 and then submitting that prompt to LLM 104 to determine the ordering to use for those states. For example, “Given [the states from 402], what is the optimal sequence of execution to achieve the [goal of the query]?” Note that the [goal of the query] may be retrieved from the initial determination of the “goal” as discussed above. The resulting ordering that is returned from the LLM 104 for the provided states may then be used to order those states for the to-be-executed workflow.").
Agarwal, Vikramathithan, Zhou, and Aghajanyan, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan and the service task automation system of Zhou, to incorporate the teachings of Aghajanyan to generate a structured data object as a response. This enables the system to operate effectively with an automated workflow, wherein each response is formatted in a way that can be seamlessly used in continued processing (Aghajanyan, [0069]). As such, the system can operate efficiently and effectively.
Regarding claim 2, the rejection of claim 1 is incorporated. Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, discloses all of the elements of the claimed invention as stated above. Agarwal further discloses in response to a natural language user input provided to the input region, selecting the first automated assistant service from the set of automated assistant services based on an analysis of the natural language user input (Agarwal, Fig. 4A, 404-406; [0051]: "The conversation manager receives the task and creates a conversation with a single message which includes the user task (step 404). The conversation is transmitted to the AI-agent scheduler (step 404) which determines, based on the scheduling algorithm, which AI-agent should be invoked at this step (step 406)."); causing the first automated assistant service to generate a fourth prompt comprising: predetermined query prompt text associated with the first automated assistant service; and at least a portion of the natural language user input (Agarwal, Fig. 4A, 406-410; [0052]: "The AI-agent scheduler transmits the conversation to the AI-agent (step 406). The AI-agent constructs a prompt including its system prompt, instructions, available actions, and the current state of the conversation, and sends this prompt to the generative neural model to generate the command needed to perform the task (step 408). The generative neural model responds with a pytest test case for the method read_atom and the command “write <new filename>:<new file location>” (step 410)."; [0033]-[0034]: "In an aspect, the rules and actions are specified in a Yet Another Markup Language (YAML) file shown in FIG. 2. The YAML file defines the available actions that an AI-agent can initiate. Users can leverage the default settings or fine-grained permissions by enabling or disabling specific actions thereby tailoring the system to a specific configuration. The user can define the number and behavior of the AI-agents, assign specific responsibilities, permissions and available actions.Agarwal, Fig. 4A, 404-406; [0051]: "The conversation manager receives the task and creates a conversation with a single message which includes the user task (step 404). The conversation is transmitted to the AI-agent scheduler (step 404) which determines, based on the scheduling algorithm, which AI-agent should be invoked at this step (step 406)."); and causing display of a fourth generative response in the generative interface panel, the fourth generative response produced by the generative output engine in response to providing the second prompt to the generative output engine (Agarwal, Fig. 4A , 414; [0052]: "The file edit API is executed by the evaluation engine and the output is the message “Content successfully written to <new file location>” (step 414)."). However, Agarwal fails to expressly recite causing display of a generative interface panel within the frontend of the collaboration platform, the generative interface panel having an input region.
Vikramathithan further teaches causing display of a generative interface panel within the frontend of the collaboration platform, the generative interface panel having an input region (Vikramathithan, [0007]: "The AI powered assistant engine provides a co-pilot guided experience and automation using contextual knowledge. The method includes receiving, by the AI powered assistant engine, one or more inputs from a user via a user interface initiating a conversation; providing, by the AI powered assistant engine, one or more AI models based on the one or more inputs"). The same motivation of claim 1 applies equally to claim 2.
Regarding claim 4, the rejection of claim 1 is incorporated. Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, discloses all of the elements of the claimed invention as stated above. Aghajanyan further teaches the first automated assistant service is configured to generate a summary of one or more content items identified by the automation rule (Aghajanyan, [0024]: "In certain example embodiments, prompt configuration structures (e.g., as defined in a configuration file) may be used to dynamically extract and analyze information from the collection of documents and/or data. In certain examples, the structure of the prompts within the file (e.g., the pipeline created by using successive prompts) validates the responses received from LLMs, cross-checks, and/or guards against invalid responses, and produces a natural language summary that can be displayed to a user."); and the one or more content items are user-generated electronic documents managed by the collaboration platform (Aghajanyan, [0034]: "Databases 106 of system 100 include a documents repository 140 that stores original documents and/or text searchable versions thereof. In certain example embodiments, the documents repository 140 may store sustainability reports generated by companies and/or organizations. Documents repository 140 may store other types of environmental, social, and corporate governance (ESG) documents. Documents repository 140 may be flexibly used for different types of data and/or documents depending on application need of system 100. For example, documents repository 140 may store news reports, financial reports, weather reports, sports reports, product reviews (e.g., for consumer products and the like), service reviews (e.g., movies, restaurants, etc.), and other documents. In some examples, documents repository 140 may be supplemented by access to one or more external databases that store such documents."). The same motivation of claim 1 applies equally to claim 4.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, as applied to claims 1, 2, and 4 above, and further in view of Kishan et al. (US Pat. Pub. No. 2026/0099792 A1 hereinafter Kishan).
Regarding claim 3, the rejection of claim 1 is incorporated. Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, fails to expressly recite the second prompt of the second automated assistant service includes the first generative response and instructions regarding a format schema for the structured data object; and execution of the second automation component causes data of the first generative response to be converted into the structured data object in accordance with the format schema of the second prompt.
Kishan teaches the second prompt of the second automated assistant service includes the first generative response and instructions regarding a format schema for the structured data object; and execution of the second automation component causes data of the first generative response to be converted into the structured data object in accordance with the format schema of the second prompt (Kishan, [0058]: "In any of the examples herein, prompts can be provided, in real time, to LLMs to generate responses...For example, prompts can include instructions and/or examples to encourage the LLMs to provide results in a desired style and/or format.").
Agarwal, Vikramathithan, Zhou, Aghajanyan, and Kishan, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, the service task automation system of Zhou, and the prompt engineering system of Aghajanyan, to incorporate the teachings of Kishan to include format schema instructions in a prompt. This helps guide model behavior to output the desired results (Kishan, [0058]), and therefore improving the accuracy and quality of the system’s results.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, as applied to claims 1, 2, and 4 above, and further in view of Carrera et al. (US Pat. Pub. No. 2025/0085931 A1 hereinafter Carrera).
Regarding claim 5, the rejection of claim 1 is incorporated. Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, fails to expressly recite the third automated assistant service is configured to generate the content as a comment with respect to a content item hosted by the collaboration platform; and the comment includes at least a portion of the third generative response.
Carrera teaches the third automated assistant service is configured to generate the content as a comment with respect to a content item hosted by the collaboration platform; and the comment includes at least a portion of the third generative response (Carrera, [0129]: "in some embodiments, the generative AI model 226 can be trained to examine submitted control code 1502a and generate plain language comments to be assigned to specific lines (e.g., ladder logic rungs) or sections of the code. These comments serve as human-readable descriptors that provide a functional summary or label for their corresponding lines or section of code.").
Agarwal, Vikramathithan, Zhou, Aghajanyan, and Carrera, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, the service task automation system of Zhou, and the prompt engineering system of Aghajanyan, to incorporate the teachings of Carrera to generate a comment relating to collaboration content. Generating comments can improve the readability of the content by providing a summary or labels for different portions of the content (Carrera, [0129]). As such, a better experience is provided for users interacting with the content.
Claim(s) 6 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, as applied to claims 1, 2, and 4 above, and further in view of Grinberg et al. (US Pat. Pub. No. 2025/0061404 A1 hereinafter Grinberg) and Prividori et al. (US Pat. Pub. No. 2024/0289540 A1 hereinafter Prividori).
Regarding claim 6, the rejection of claim 1 is incorporated. Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan, Zhou, and Aghajanyan, fails to expressly recite the content generated by the third automative assistant service is generated in accordance with a permissions profile of a user that generated the automation rule; and the content has an author attribution associated with the third automative assistant service.
Grinberg teaches the content generated by the third automative assistant service is generated in accordance with a permissions profile of a user that generated the automation rule (Grinberg, [0097]: "A permission refers to an access right or privilege granted to users, groups, or processes, allowing them to perform certain actions or access specific resources on a computer system or network. By way of a few non-limiting examples, permissions may refer to filters, access control, rights, credentials, or anything that acts as a barrier or presents some level of restriction of access to data or data assets to some, yet permits it to at least one other.").
Agarwal, Vikramathithan, Zhou, Aghajanyan, and Grinberg, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, the service task automation system of Zhou, and the prompt engineering system of Aghajanyan, to incorporate the teachings of Grinberg to generate content based on permissions of a user. It is important to protect the privacy of users (Grinberg, [0005]), and incorporating user permissions helps protect the privacy of the users. However, Agarwal, in view of Vikramathithan, Zhou, Aghajanyan, and Grinberg, fails to expressly recite the content has an author attribution associated with the third automative assistant service.
Prividori teaches the content has an author attribution associated with the third automative assistant service (Prividori, [0027]: "In particular, the academic editor engine allows for use of a content generator, such as large language model (LLM), examples of which include generative pre-trained transformer (GPT) models or multimodal generative models, to revise sections of a scholarly manuscript. Unlike conventional use of AI systems to draft scholarly manuscripts, the academic editor engine generates an author attribution for content within the manuscript, clearly delineating what is drafted by the content generator and what is drafted by the scholar across numerous revisions.").
Agarwal, Vikramathithan, Zhou, Aghajanyan, Grinberg, and Prividori, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, the service task automation system of Zhou, the prompt engineering system of Aghajanyan, and the digital processing systems of Grinberg, to incorporate the teachings of Prividori to include author attribution. This ensures that generated content is clearly attributed (Prividori, [0027]). As such, future readers will be able to tell which portions of a document where written or generated by different authors.
Regarding claim 7, the rejection of claim 6 is incorporated. Agarwal, in view of Vikramathithan, Zhou, Aghajanyan, Grinberg, and Prividori, discloses all of the elements of the claimed invention as stated above. Grinberg further teaches wherein in accordance with the user having a permissions profile that does not permit at least write permissions with respect to a particular content item, the collaboration platform blocks content creation by the third automative assistant service with respect to the particular content item (Grinberg, [0097]: "A permission refers to an access right or privilege granted to users, groups, or processes, allowing them to perform certain actions or access specific resources on a computer system or network. By way of a few non-limiting examples, permissions may refer to filters, access control, rights, credentials, or anything that acts as a barrier or presents some level of restriction of access to data or data assets to some, yet permits it to at least one other."). The same motivation for claim 6 applies equally to claim 7.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan and Aghajanyan.
Regarding claim 8, Agarwal discloses a computer-implemented method for executing an automation rule having multiple automated assistant services within a collaboration platform, the method comprising: causing execution of the automation rule, the execution comprising: causing execution of a first automation component, the first automation component causing execution of a first automated assistant, which provides a first prompt to a generative output engine to generate a first generative response, the first prompt including a natural language command text string defined by the first automation component (Agarwal, Fig. 4A, 406-410; [0052]: "The AI-agent scheduler transmits the conversation to the AI-agent (step 406). The AI-agent constructs a prompt including its system prompt, instructions, available actions, and the current state of the conversation, and sends this prompt to the generative neural model to generate the command needed to perform the task (step 408). The generative neural model responds with a pytest test case for the method read_atom and the command “write <new filename>:<new file location>” (step 410)."); causing execution of a second automation component, the second automation component causing execution of a second automated assistant, which provides a second prompt to the generative output engine to generate a second generative response, the second prompt including the first generative response (Agarwal, Fig. 4A, 418-422; [0053]: "The conversation manager transmits the conversation to the AI-agent scheduler (step 418) which transmits it to an appropriate AI-agent (step 420). The AI-agent creates a prompt to the generative neural model to determine a follow-on task (step 420). The prompt includes the AI-agent system prompt, instructions, available actions and the current state of the conversation (step 420). The generative neural model responds with the follow-on task “Syntax <new filename><new file location>” (step 422)."); causing execution of a third automation component, the third automation component causing execution of a third automated assistant, which provides a third prompt to the generative output engine to generate a third generative response; and causing generation of content within the collaboration platform, the content based on the third generative response (Agarwal, Fig. 4A and Fig. 4B, 430-436; [0055]-[0056]: "The conversation manager interacts with the AI-agent scheduler for a follow-on task given the current state of the conversation (step 430). The AI-agent scheduler finds an appropriate AI-agent (step 432) and the AI-agent generates a prompt to the generative neural model for commands for a follow-on task given the current state of the conversation (step 432). The prompt includes the AI-agent's system prompt, instructions, available actions, and the current state of the conversation (step 432). The generative neural model responds with the instruction to test the new file with “test-file <join_mp4_test.py>” (step 434). The parser extracts the command from the model's response and invokes the testing API to perform the test (step 436)."). However, Agarwal fails to expressly recite in response to an event of the collaboration platform satisfying an automation initiation criteria; the second generative response including a structured data object representation of the first generative response; and the third prompt including the structured data object representation of the second generative response.
Vikramathithan teaches in response to an event of the collaboration platform satisfying an automation initiation criteria (Vikramathithan, [0057]: "Once a workflow is developed in designer 210, execution of business processes is orchestrated by conductor 220, which orchestrates one or more robots 230 that execute the workflows developed in designer 210."; [0058]: "Attended robots 232 are triggered by user events and operate alongside a human on the same computing system. Attended robots 232 may be used with conductor 220 for a centralized process deployment and logging medium. Attended robots 232 may help the human user accomplish various tasks, and may be triggered by user events.").
Agarwal and Vikramathithan are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal to incorporate the teachings of Vikramathithan to include a frontend user interface with various controls. This allows the system to collect numerous inputs from a user as well as display various information for the user (Vikramathithan, [0132]). This creates a better experience for the user when interacting with the system. However, Agarwal, in view of Vikramathithan, fails to expressly recite the second generative response including a structured data object representation of the first generative response; and the third prompt including the structured data object representation of the second generative response.
Aghajanyan teaches the second generative response including a structured data object representation of the first generative response; and the third prompt including the structured data object representation of the second generative response (Aghajanyan, [0069]: "The techniques discussed in connection with FIG. 4 and elsewhere herein enable building AI agents with configurable workflows to process natural language queries. The submitted queries are analyzed and the system assembles a customized toolchain of models and data into a structured workflow that is generated (e.g., optimized) for that query. Based on analysis of a query's goals and context (e.g., using natural language processing/understanding techniques), the system selects a sequence of states to form a structured workflow to answer that given query."; [0074]: "In certain example embodiments, the ordering may be determined by constructing a prompt with the states that have been determined from 402 and then submitting that prompt to LLM 104 to determine the ordering to use for those states. For example, “Given [the states from 402], what is the optimal sequence of execution to achieve the [goal of the query]?” Note that the [goal of the query] may be retrieved from the initial determination of the “goal” as discussed above. The resulting ordering that is returned from the LLM 104 for the provided states may then be used to order those states for the to-be-executed workflow.").
Agarwal, Vikramathithan, and Aghajanyan, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, to incorporate the teachings of Aghajanyan to generate a structured data object as a response. This enables the system to operate effectively with an automated workflow, wherein each response is formatted in a way that can be seamlessly used in continued processing (Aghajanyan, [0069]). As such, the system can operate efficiently and effectively.
Claim(s) 9 and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan and Aghajanyan, as applied to claim 8 above, and further in view of Kishan.
Regarding claim 9, the rejection of claim 8 is incorporated. Agarwal, in view of Vikramathithan and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan and Aghajanyan, fails to expressly recite the second prompt of the second automated assistant service includes the first generative response and instructions regarding a format schema for the structured data object representation; and execution of the second automation component causes data of the first generative response to be converted into the structured data object representation in accordance with the format schema of the second prompt.
Kishan teaches the second prompt of the second automated assistant service includes the first generative response and instructions regarding a format schema for the structured data object representation; and execution of the second automation component causes data of the first generative response to be converted into the structured data object representation in accordance with the format schema of the second prompt (Kishan, [0058]: "In any of the examples herein, prompts can be provided, in real time, to LLMs to generate responses...For example, prompts can include instructions and/or examples to encourage the LLMs to provide results in a desired style and/or format.").
Agarwal, Vikramathithan, Aghajanyan, and Kishan, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan and the prompt engineering system of Aghajanyan, to incorporate the teachings of Kishan to include format schema instructions in a prompt. This helps guide model behavior to output the desired results (Kishan, [0058]), and therefore improving the accuracy and quality of the system’s results.
Regarding claim 10, the rejection of claim 9 is incorporated. Agarwal, in view of Vikramathithan, Aghajanyan, and Kishan, discloses all of the elements of the claimed invention as stated above. Aghajanyan further teaches the format schema defines a list-based schema; the structured data object representation includes a list of items returned in the first generative response (Aghajanyan, [0069]: "The techniques discussed in connection with FIG. 4 and elsewhere herein enable building AI agents with configurable workflows to process natural language queries. The submitted queries are analyzed and the system assembles a customized toolchain of models and data into a structured workflow that is generated (e.g., optimized) for that query. Based on analysis of a query's goals and context (e.g., using natural language processing/understanding techniques), the system selects a sequence of states to form a structured workflow to answer that given query."; [0074]: "In certain example embodiments, the ordering may be determined by constructing a prompt with the states that have been determined from 402 and then submitting that prompt to LLM 104 to determine the ordering to use for those states. For example, “Given [the states from 402], what is the optimal sequence of execution to achieve the [goal of the query]?” Note that the [goal of the query] may be retrieved from the initial determination of the “goal” as discussed above. The resulting ordering that is returned from the LLM 104 for the provided states may then be used to order those states for the to-be-executed workflow."); and the third automation component processes each item of the list of items in the structured data object representation in sequence (Aghajanyan, [0075]: "Next, at 406, the process determined which sub-agent(s) to use in connection with each of the states for the given workflow. In some example embodiments, as with the generation of the states, the determination of which sub-agent to use for a given state may also use LLM 104 (which may be the same or a different LLM that those prompted previously in connection with 402 and 404)."). The same motivation for claim 8 applies equally to claim 10.
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan and Aghajanyan, as applied to claim 8 above, and further in view of Carrera.
Regarding claim 11, the rejection of claim 8 is incorporated. Agarwal, in view of Vikramathithan and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan and Aghajanyan, fails to expressly recite the third automated assistant service is configured to generate the content as at least a portion of an electronic document hosted by the collaboration platform; and the electronic document includes at least a portion of the third generative response.
Carrera teaches the third automated assistant service is configured to generate the content as at least a portion of an electronic document hosted by the collaboration platform; and the electronic document includes at least a portion of the third generative response (Carrera, [0129]: "in some embodiments, the generative AI model 226 can be trained to examine submitted control code 1502a and generate plain language comments to be assigned to specific lines (e.g., ladder logic rungs) or sections of the code. These comments serve as human-readable descriptors that provide a functional summary or label for their corresponding lines or section of code.").
Agarwal, Vikramathithan, Aghajanyan, and Carrera, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan and the prompt engineering system of Aghajanyan, to incorporate the teachings of Carrera to generate a comment relating to collaboration content. Generating comments can improve the readability of the content by providing a summary or labels for different portions of the content (Carrera, [0129]). As such, a better experience is provided for users interacting with the content.
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan and Aghajanyan, as applied to claim 8 above, and further in view of Grinberg and Prividori.
Regarding claim 12, the rejection of claim 8 is incorporated. Agarwal, in view of Vikramathithan and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan and Aghajanyan, fails to expressly recite the content generated by the third automative assistant is generated in accordance with a permissions profile of a user that generated the automation rule; and the content has an author attribution associated with the third automative assistant.
Grinberg teaches the content generated by the third automative assistant is generated in accordance with a permissions profile of a user that generated the automation rule (Grinberg, [0097]: "A permission refers to an access right or privilege granted to users, groups, or processes, allowing them to perform certain actions or access specific resources on a computer system or network. By way of a few non-limiting examples, permissions may refer to filters, access control, rights, credentials, or anything that acts as a barrier or presents some level of restriction of access to data or data assets to some, yet permits it to at least one other.").
Agarwal, Vikramathithan, Aghajanyan, and Grinberg, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan and the prompt engineering system of Aghajanyan, to incorporate the teachings of Grinberg to generate content based on permissions of a user. It is important to protect the privacy of users (Grinberg, [0005]), and incorporating user permissions helps protect the privacy of the users. However, Agarwal, in view of Vikramathithan, Aghajanyan, and Grinberg, fails to expressly recite the content has an author attribution associated with the third automative assistant.
Prividori teaches the content has an author attribution associated with the third automative assistant (Prividori, [0027]: "In particular, the academic editor engine allows for use of a content generator, such as large language model (LLM), examples of which include generative pre-trained transformer (GPT) models or multimodal generative models, to revise sections of a scholarly manuscript. Unlike conventional use of AI systems to draft scholarly manuscripts, the academic editor engine generates an author attribution for content within the manuscript, clearly delineating what is drafted by the content generator and what is drafted by the scholar across numerous revisions.").
Agarwal, Vikramathithan, Aghajanyan, Grinberg, and Prividori, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan, the prompt engineering system of Aghajanyan, and the digital processing systems of Grinberg, to incorporate the teachings of Prividori to include author attribution. This ensures that generated content is clearly attributed (Prividori, [0027]). As such, future readers will be able to tell which portions of a document where written or generated by different authors.
Claim(s) 13 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Vikramathithan and Aghajanyan, as applied to claim 8 above, and further in view of Medford, Wesley (US Pat. Pub. No. 2025/0165890 A1 hereinafter Medford).
Regarding claim 13, the rejection of claim 8 is incorporated. Agarwal, in view of Vikramathithan and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan and Aghajanyan, fails to expressly recite the first automated assistant service is configured to execute a query on an issue tracking platform distinct from the collaboration platform; and the first generative response includes a summary of a set of issues returned by the query.
Medford teaches the first automated assistant service is configured to execute a query on an issue tracking platform distinct from the collaboration platform; and the first generative response includes a summary of a set of issues returned by the query (Medford, [0031]: "The plan, as output by the Planner Agent, is then reviewed by the Critic Agent, which evaluates its feasibility and robustness, suggesting improvements or identifying potential issues.").
Agarwal, Vikramathithan, Aghajanyan, and Medford, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan and the prompt engineering system of Aghajanyan, to incorporate the teachings of Medford to identify and correct issues within content. Doing so allows the system to improve its outputs overtime and avoid giving bad outputs to a user (Medford, [0031]). As such, the systems accuracy can be improved so it can provide better outputs to the user.
Regarding claim 14, the rejection of claim 8 is incorporated. Agarwal, in view of Vikramathithan and Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Vikramathithan and Aghajanyan, fails to expressly recite wherein the execution of the automation rule further comprises: subsequent to the execution of the third automation component and prior to causing generation of the content, causing execution of a fourth automation component; the fourth automation component modifies the third generative response; and the content includes the modified third generative response.
Medford teaches wherein the execution of the automation rule further comprises: subsequent to the execution of the third automation component and prior to causing generation of the content, causing execution of a fourth automation component; the fourth automation component modifies the third generative response (Medford, [0060]: "The Critic Agent 206 in the multi-agent AI system functions as a semi-adversarial reviewer of both the plans generated by the Planner Agent 204 and the software code produced by the Engineer Agent 208."); and the content includes the modified third generative response (Medford, [0064]: "The semi-adversarial nature of the Critic Agent 206 allows for maintaining a high standard within the project lifecycle. It not only checks for errors or issues but also challenges the assumptions and decisions made by other agents, fostering a dynamic of continuous improvement. After its review, the Critic Agent 206 provides detailed feedback, which can be used to refine the project plan or the code.").
Agarwal, Vikramathithan, Aghajanyan, and Medford, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the software assistant of Vikramathithan and the prompt engineering system of Aghajanyan, to incorporate the teachings of Medford to identify and correct issues within content. Doing so allows the system to improve its outputs overtime and avoid giving bad outputs to a user (Medford, [0031]). As such, the systems accuracy can be improved so it can provide better outputs to the user.
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Aghajanyan.
Regarding claim 15, Agarwal discloses a computer-implemented method generating an automation rule within a collaboration platform, the method comprising: generating a first automation component including specifying a first automated assistant service of a set of automated assistant services, execution of the first automation component causes the first automated assistant service to provide a first prompt to a generative output engine thereby causing the first automated assistant service to generate a first generative response (Agarwal, Fig. 4A, 406-410; [0052]: "The AI-agent scheduler transmits the conversation to the AI-agent (step 406). The AI-agent constructs a prompt including its system prompt, instructions, available actions, and the current state of the conversation, and sends this prompt to the generative neural model to generate the command needed to perform the task (step 408). The generative neural model responds with a pytest test case for the method read_atom and the command “write <new filename>:<new file location>” (step 410)."); generating a second automation component including specifying a second automated assistant service of the set of automated assistant services, execution of the second automation component causes the second automated assistant service to generate a second prompt including the first generative response and provide the second prompt to the generative output engine thereby causing the second automated assistant service to generate a second generative response (Agarwal, Fig. 4A, 418-422; [0053]: "The conversation manager transmits the conversation to the AI-agent scheduler (step 418) which transmits it to an appropriate AI-agent (step 420). The AI-agent creates a prompt to the generative neural model to determine a follow-on task (step 420). The prompt includes the AI-agent system prompt, instructions, available actions and the current state of the conversation (step 420). The generative neural model responds with the follow-on task “Syntax <new filename><new file location>” (step 422)."); and generating a third automation component by specifying a third automated assistant service of the set of automated assistant services, execution of the third automation component causes the third automated assistant service to generate a third prompt including the structured data object of the second generative response and provide the third prompt to the generative output engine thereby causing the third automated assistant service to generate a third generative response, execution of the automation rule is configured to cause generation of content within the collaboration platform, the content based, at least in part, on the third generative response (Agarwal, Fig. 4A and Fig. 4B, 430-436; [0055]-[0056]: "The conversation manager interacts with the AI-agent scheduler for a follow-on task given the current state of the conversation (step 430). The AI-agent scheduler finds an appropriate AI-agent (step 432) and the AI-agent generates a prompt to the generative neural model for commands for a follow-on task given the current state of the conversation (step 432). The prompt includes the AI-agent's system prompt, instructions, available actions, and the current state of the conversation (step 432). The generative neural model responds with the instruction to test the new file with “test-file <join_mp4_test.py>” (step 434). The parser extracts the command from the model's response and invokes the testing API to perform the test (step 436)."). However, Agarwal fails to expressly recite which is a structured data object that corresponds to the first generative response.
Aghajanyan teaches which is a structured data object that corresponds to the first generative response (Aghajanyan, [0069]: "The techniques discussed in connection with FIG. 4 and elsewhere herein enable building AI agents with configurable workflows to process natural language queries. The submitted queries are analyzed and the system assembles a customized toolchain of models and data into a structured workflow that is generated (e.g., optimized) for that query. Based on analysis of a query's goals and context (e.g., using natural language processing/understanding techniques), the system selects a sequence of states to form a structured workflow to answer that given query."; [0074]: "In certain example embodiments, the ordering may be determined by constructing a prompt with the states that have been determined from 402 and then submitting that prompt to LLM 104 to determine the ordering to use for those states. For example, “Given [the states from 402], what is the optimal sequence of execution to achieve the [goal of the query]?” Note that the [goal of the query] may be retrieved from the initial determination of the “goal” as discussed above. The resulting ordering that is returned from the LLM 104 for the provided states may then be used to order those states for the to-be-executed workflow.").
Agarwal and Aghajanyan, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal to incorporate the teachings of Aghajanyan to generate a structured data object as a response. This enables the system to operate effectively with an automated workflow, wherein each response is formatted in a way that can be seamlessly used in continued processing (Aghajanyan, [0069]). As such, the system can operate efficiently and effectively.
Claim(s) 16 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Aghajanyan, as applied to claim 15 above, and further in view of Vikramathithan.
Regarding claim 16, the rejection of claim 15 is incorporated. Agarwal, in view of Aghajanyan, discloses all of the elements of the claimed invention as stated above. Agarwal further discloses in response to a natural language user input provided to the generative interface, selecting a particular automated assistant service from a set of automated assistant services including the first, second, and third automated assistant services, the selection based on an intent analysis of the natural language user input (Agarwal, Fig. 4A, 404-406; [0051]: "The conversation manager receives the task and creates a conversation with a single message which includes the user task (step 404). The conversation is transmitted to the AI-agent scheduler (step 404) which determines, based on the scheduling algorithm, which AI-agent should be invoked at this step (step 406)."); causing the particular automated assistant service to generate a fourth prompt comprising: predetermined query prompt text associated with the particular automated assistant service; and at least a portion of the natural language user input (Agarwal, Fig. 4A, 406-410; [0052]: "The AI-agent scheduler transmits the conversation to the AI-agent (step 406). The AI-agent constructs a prompt including its system prompt, instructions, available actions, and the current state of the conversation, and sends this prompt to the generative neural model to generate the command needed to perform the task (step 408). The generative neural model responds with a pytest test case for the method read_atom and the command “write <new filename>:<new file location>” (step 410)."; [0033]-[0034]: "In an aspect, the rules and actions are specified in a Yet Another Markup Language (YAML) file shown in FIG. 2. The YAML file defines the available actions that an AI-agent can initiate. Users can leverage the default settings or fine-grained permissions by enabling or disabling specific actions thereby tailoring the system to a specific configuration. The user can define the number and behavior of the AI-agents, assign specific responsibilities, permissions and available actions.Agarwal, Fig. 4A, 404-406; [0051]: "The conversation manager receives the task and creates a conversation with a single message which includes the user task (step 404). The conversation is transmitted to the AI-agent scheduler (step 404) which determines, based on the scheduling algorithm, which AI-agent should be invoked at this step (step 406)."); and causing display of a fourth generative response in the generative interface, the fourth generative response produced by the generative output engine in response to providing the second prompt to the generative output engine (Agarwal, Fig. 4A , 414; [0052]: "The file edit API is executed by the evaluation engine and the output is the message “Content successfully written to <new file location>” (step 414)."). However, Agarwal, in view of Aghajanyan, fails to expressly recite causing display of a generative interface within a frontend of the collaboration platform.
Vikramathithan teaches causing display of a generative interface within a frontend of the collaboration platform (Vikramathithan, [0007]: "The AI powered assistant engine provides a co-pilot guided experience and automation using contextual knowledge. The method includes receiving, by the AI powered assistant engine, one or more inputs from a user via a user interface initiating a conversation; providing, by the AI powered assistant engine, one or more AI models based on the one or more inputs").
Agarwal, Aghajanyan, and Vikramathithan are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the prompt engineering system of Aghajanyan, to incorporate the teachings of Vikramathithan to include a frontend user interface with various controls. This allows the system to collect numerous inputs from a user as well as display various information for the user (Vikramathithan, [0132]). This creates a better experience for the user when interacting with the system.
Regarding claim 18, the rejection of claim 15 is incorporated. Agarwal, in view of Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Aghajanyan, fails to expressly recite the first automation component is generated in a control region of a graphical user interface; the control region includes a set of input controls; the set of input controls comprises: a first control for specifying the first automated assistant service of a set of available automated assistant services; and a text entry region configured to receive a natural language command; and the first prompt includes the natural language command.
Vikramathithan teaches the first automation component is generated in a control region of a graphical user interface; the control region includes a set of input controls (Vikramathithan, [0007]: "The AI powered assistant engine provides a co-pilot guided experience and automation using contextual knowledge. The method includes receiving, by the AI powered assistant engine, one or more inputs from a user via a user interface initiating a conversation; providing, by the AI powered assistant engine, one or more AI models based on the one or more inputs"); the set of input controls comprises: a first control for specifying the first automated assistant service of a set of available automated assistant services; and a text entry region configured to receive a natural language command (Vikramathithan, [0139]: "The first frame 1110 presents a plurality of AI models, as well as an icon 1132 to create a new model. Examples of the plurality of AI models includes a first model 1134 for an human resources brain, a second model 1136 for a legal brain, a third model 1136 for a migration chatbot, and a fourth model 1140 for a personal brain. The first frame 1110 also presents one or more fields 1142, 1144, 1146, and 148 for configuring names, prompts schemas, and plugins. The second frame 1120 can includes a chat window 1152 and a message box 1154."); and the first prompt includes the natural language command (Vikramathithan, [0051]: "Chatbots (e.g., UiPath Chatbots™), social messaging applications, and/or voice commands may enable users to run automations.").
Agarwal, Aghajanyan, and Vikramathithan are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the prompt engineering system of Aghajanyan, to incorporate the teachings of Vikramathithan to include a frontend user interface with various controls. This allows the system to collect numerous inputs from a user as well as display various information for the user (Vikramathithan, [0132]). This creates a better experience for the user when interacting with the system.
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Aghajanyan, as applied to claim 15 above, and further in view of Grinberg.
Regarding claim 17, the rejection of claim 15 is incorporated. Agarwal, in view of Aghajanyan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Aghajanyan, fails to expressly recite wherein the intent analysis of the natural language user input predicts a type of action associated with the natural language user input.
Grinberg teaches wherein the intent analysis of the natural language user input predicts a type of action associated with the natural language user input (Grinberg, [0148]: "Some embodiments involve analyzing the query for determining a context. Analyzing a context for a query refers to examination or consideration of surrounding information and/or relevant factors to better understand the meaning and/or intent of the query. Computer software may be used to analyze or assess a query. In some examples, analyzing a received query may include interpreting, parsing, saving, storing, processing, modifying, or configuring the query for further or future use. The analysis may involve the use of at least one AI agent which may include the use of natural language processing, machine learning, long short-term memory network, recurrent neural network, recursive neural network, convolutional neural network, or other types of deep learning or AI models. ").
Agarwal, Aghajanyan, and Grinberg, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the prompt engineering system of Aghajanyan, to incorporate the teachings of Grinberg to predict a type of action based on user input. This helps the system choose the correct agent to use to provide a response to the user (Grinberg, [0148]). As such, the system can ensure it provides the correct response for the user.
Claim(s) 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Aghajanyan and Vikramathithan, as applied to claims 16 and 18 above, and further in view of Cox et al. (US Pat. Pub. No. 2026/0030269 A1 hereinafter Cox) and Prasad et al. (US Pat. Pub. No. 2026/0154493 A1 hereinafter Prasad).
Regarding claim 19, the rejection of claim 18 is incorporated. Agarwal, in view of Aghajanyan and Vikramathithan, discloses all of the elements of the claimed invention as stated above. However, Agarwal, in view of Aghajanyan and Vikramathithan, fails to expressly recite a second control for adjusting a variability of the first generative response produced by the generative output engine; and a third control for adjusting a tone of the first generative response produced by the generative output engine.
Cox teaches a second control for adjusting a variability of the first generative response produced by the generative output engine (Cox, [0077]: "The API call may also include an identification of the language model or LLM to be accessed and/or parameters for adjusting outputs generated by the language model or LLM, such as, for example, one or more of a temperature parameter (which may control the amount of randomness or “creativity” of the generated output) (and/or, more generally some form of random seed as serves to introduce variability or variety into the output of the LLM)").
Agarwal, Aghajanyan, Vikramathithan, and Cox, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the prompt engineering system of Aghajanyan and the software assistant of Vikramathithan, to incorporate the teachings of Cox to control the variability of generated content. This can help control how “creative” the system gets when responding to a user (Cox, [0077]). As such, the user can control if the responses will more strictly follow the prompt or give more varied answers, depending on the user’s preferences.
However, Agarwal, in view of Aghajanyan, Vikramathithan, and Cox, fails to expressly recite a third control for adjusting a tone of the first generative response produced by the generative output engine.
Prasad teaches a third control for adjusting a tone of the first generative response produced by the generative output engine (Prasad, [0026]: "In some implementations, one or more adjustable interface elements 152 can be utilized to modify one or more parameters for creating the generative content. In some implementations, a parameter that is modifiable by the adjustable interface element 152 can influence how many words are in a snippet of generative text. Alternatively, or additionally, adjusting the parameter can modify a tone parameter and/or linguistic profile parameter of the generative text.").
Agarwal, Aghajanyan, Vikramathithan, Cox, and Prasad, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the prompt engineering system of Aghajanyan, the software assistant of Vikramathithan, and the information gap detection system of Cox, to incorporate the teachings of Prasad to include a control to adjust the tone of a response. This allows the user to receive content generated to be more or less professional depending on their preferences (Prasad, [0008]). This ensures that content is generated to the user’s liking.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Agarwal, in view of Aghajanyan, as applied to claim 15 above, and further in view of Prividori.
Regarding claim 20, the rejection of claim 15 is incorporated. Agarwal, in view of Aghajanyan, discloses all of the elements of the claimed invention as stated above. Agarwal further discloses collaboration platform is a documentation platform (Agarwal, [0011]: "Aspects of the present disclosure pertain to the autonomous processing of a software engineering task without manual intervention. A software engineering task comprises a sequence of operations to be performed to generate, build, test, or maintain software, such as without limitation, code generation, code design, code documentation generation, code completion, software bug classification, software bug repair, software vulnerability detection, software vulnerability correction, application build, software optimization, software testing, code maintenance, and combinations thereof."); the documentation platform hosts a body of electronic documents of user-generated content (Agarwal, [0024]: "In an aspect, the code repository 118 is a file archive and web hosting facility that stores large amounts of artifacts, such as source code files, test files, script files, etc. Programmers (i.e., developers, users, end users, etc.) often utilize a shared code repository 118 to store source code and other programming artifacts that can be shared among different programmers."). However, Agarwal, in view of Aghajanyan, fails to expressly recite the content produced by the automation rule is added to one or more electronic documents of the body of electronic documents; and authorship of the content is attributed to the third automated assistant service.
Prividori teaches the content produced by the automation rule is added to one or more electronic documents of the body of electronic documents (Prividori, [0078]: "Each revised draft that is generated is stored by the academic editor engine 202 in a database 226. Each revised draft is stored separately from a previous instance or draft such that the history of revisions for each section can be clearly followed and reviewed."); and authorship of the content is attributed to the third automated assistant service (Prividori, [0027]: "In particular, the academic editor engine allows for use of a content generator, such as large language model (LLM), examples of which include generative pre-trained transformer (GPT) models or multimodal generative models, to revise sections of a scholarly manuscript. Unlike conventional use of AI systems to draft scholarly manuscripts, the academic editor engine generates an author attribution for content within the manuscript, clearly delineating what is drafted by the content generator and what is drafted by the scholar across numerous revisions.").
Agarwal, Aghajanyan, and Prividori, are analogous arts because they each belong to the same field of artificial intelligence systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the automated software development system of Agarwal, as modified by the prompt engineering system of Aghajanyan, to incorporate the teachings of Prividori to include author attribution. This ensures that generated content is clearly attributed (Prividori, [0027]). As such, future readers will be able to tell which portions of a document where written or generated by different authors.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chen et al. (US Pat. Pub. No. 2026/0105395 A1) discloses a system for workflow automation.
Monteleone et al. (US Pat. Pub. No. 2025/0190703 A1) discloses an intelligent interface for automation multitasking.
Pearl et al. (US Pat. Pub. No. 2015/0082197 A1) discloses a system for event-based automation in collaboration platforms.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TYLER J BECKER whose telephone number is (703)756-1271. The examiner can normally be reached M-Th, 7:15am-5:45pm PT.
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, Daniel Washburn can be reached at (571) 272-5551. 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.
/TYLER BECKER/ Examiner, Art Unit 2657
/DANIEL C WASHBURN/ Supervisory Patent Examiner, Art Unit 2657
Prosecution Insights