DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
The following non-is a final office action.
Claims 21-40 are currently pending and have been examined on their merits.
Claims 1-20 are currently cancelled see REMARKS January 28, 2026.
Claims 21-40 are newly added see REMARKS January 28, 2026.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 21-40 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Grinberg (US 2025/0061285).
Claim 21: Grinberg discloses A computer-implemented method for operating a multi-participant interface for a content collaboration platform, the method comprising: causing display, on a user device, of a graphical user interface including: a content panel including an editor depicting content of a current content item hosted by the content collaboration platform; a generative interface panel operated by a generative service, the generative interface panel comprising: an input region configured to receive user input; (Paragraph [0007-0008]; [0080-0083]; [0099]; [0120]; Fig. 5, embodiments consistent with the present disclosure involve systems, methods, and computer readable medium for building an application incorporating AI functionality. Exemplary operations may include receiving a selection of an AI assistant add-on and at least one of a plurality of SaaS platform elements, enabling implementation of permission for providing access to data from the at least one of the plurality of linked SaaS platform elements. Some embodiments involve performing selection operations for a plurality of distinct artificial intelligence agents. Exemplary embodiments include sending via the application, a prompt to a plurality of distinct AI agents, and receiving from each of the plurality of distinct AI agents a response to the prompt. The operation may further include comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents. A software application may include a user interface enabling users to interact with and access features and functionalities of the software application. User interface is consistent with use of the term as described herein. For example, displaying a user interface may be done by showing a message on a screen, such as a pop-up box, or a list of selectable options);
at least one received user input and one or more generative responses; and in response to receiving a natural language user input at the input region, causing display of the natural language user input in generative interface panel (Paragraph [0117-0121]; Fig. 4, in some embodiments disclosed herein, processes are described that explain ways to select an AI agent from a pool of AI agents. Embodiments may involve selection operations for a plurality of distinct AI agent. An AI agent may be distinct if it provides at least one functions, purpose, solution, task, or use that distinguishes it from other agents. For example, one AI agent may be used to analyze text, while another may be used to analyze audio. Based on a developer’s needs or requests. Some embodiments may involve accessing an application that employes AI functionality. Some examples involve sending a prompt to a plurality of distinct Ai agents. A prompt is a message, question, or indication presented to elicit a response or action. It can be a textual message, a dialog box, an input field where an entity is pinged);
analyzing the user input to determine an action intent and selecting a particular automated assistant service of a set of automated assistant services provided by the generative service; (Paragraph [0117-0121]; Fig. 4, in some embodiments disclosed herein, processes are described that explain ways to select an AI agent from a pool of AI agents. Embodiments may involve selection operations for a plurality of distinct AI agent. An AI agent may be distinct if it provides at least one functions, purpose, solution, task, or use that distinguishes it from other agents. For example, one AI agent may be used to analyze text, while another may be used to analyze audio. Based on a developer’s needs or requests. Some embodiments may involve accessing an application that employes AI functionality. Some examples involve sending a prompt to a plurality of distinct Ai agents. A prompt is a message, question, or indication presented to elicit a response or action. It can be a textual message, a dialog box, an input field where an entity is pinged);
causing display, in the generative interface panel, of a particular avatar icon corresponding to the particular automated assistant service; causing the particular automated assistant service to generate a prompt comprising: predefined query prompt text associated with a subject-matter expertise of the particular automated assistant service; at least a portion of the natural language user input (Paragraph [0123-0126]; [0129-0131]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user);
and text extracted from the content displayed in the content panel; providing the prompt to a generative output engine and, in response, obtaining a generative response from the generative output engine; and causing display, within the generative interface panel, of the generative response. (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose);
Claim 22: Grinberg discloses the computer-implemented method as per claim 21. Grinberg further discloses wherein subsequent to causing display of the generative response, the method further comprises: in response to receiving an additional user input with respect to the generative response, selecting an issue tracking system assistant service from the set of automated assistant services; causing the issue tracking system assistant service to extract, from an issue tracking system, a list of issues associated based on the additional user input; and causing display, within the generative interface panel, of the list of issues (Paragraph [0123-0126]; [0129-0131]; [0135-0137]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user. Consistent with some embodiments, selecting at least one AI agent from the plurality of distinct AI agents includes selecting at least two AI agents from the plurality of AI agents, and merging responses of the at least two selected AI agents to generate a merged response).
Claim 23: Grinberg discloses the computer-implemented method as per claim 22. Grinberg further discloses wherein causing display of the list of issues includes: causing display of a link associated with the list of issues; and in response to receiving a user selection of the link, causing display of the list of issues within the generative interface panel (Paragraph [0123-0126]; [0129-0131]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user).
Claim 24: Grinberg discloses the computer-implemented method as per claim 23. Grinberg further discloses wherein the method further comprises displaying an additional avatar icon associated with the issue tracking system assistant service within the generative interface panel (Paragraph [0007-0008]; [0080-0083]; [0099]; [0120]; Fig. 5, embodiments consistent with the present disclosure involve systems, methods, and computer readable medium for building an application incorporating AI functionality. Exemplary operations may include receiving a selection of an AI assistant add-on and at least one of a plurality of SaaS platform elements, enabling implementation of permission for providing access to data from the at least one of the plurality of linked SaaS platform elements. Some embodiments involve performing selection operations for a plurality of distinct artificial intelligence agents. Exemplary embodiments include sending via the application, a prompt to a plurality of distinct AI agents, and receiving from each of the plurality of distinct AI agents a response to the prompt. The operation may further include comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents. A software application may include a user interface enabling users to interact with and access features and functionalities of the software application. User interface is consistent with use of the term as described herein. For example, displaying a user interface may be done by showing a message on a screen, such as a pop-up box, or a list of selectable options).
Claim 25: Grinberg discloses the computer-implemented method as per claim 21. Grinberg further discloses wherein each automated assistant service of the set of automated assistant services is associated with at least one of: a respective content extraction plugin; a respective content parsing plugin; a respective structured query plugin; or a respective activity plugin (Paragraph [0034] Boards and widgets may be part of a platform that may enable users to interact with information in real-time in collaborative work systems involving electronic collaborative word-processing documents. Electronic collaborative word processing documents (and other variations of the term) as used herein are not limited to only digital files for word processing but may include any other processing document such as presentation slides, tables, databases, graphics, sound files, video files or any other digital document or file. Electronic collaborative word processing documents may include any digital file that may provide for input, editing, formatting, display, and/or output of text, graphics, widgets, objects, tables, links, animations, dynamically updated elements, or any other data object that may be used in conjunction with the digital file. Any information stored on or displayed from an electronic collaborative word processing document may be organized into blocks).
Claim 26: Grinberg discloses the computer-implemented method as per claim 21. Grinberg further discloses wherein the particular automated assistant service is associated with a corpus of electronic resources comprising: a set of question-answer pairs; and a set of knowledge base content (Paragraph [0034] Boards and widgets may be part of a platform that may enable users to interact with information in real-time in collaborative work systems involving electronic collaborative word-processing documents. Electronic collaborative word processing documents (and other variations of the term) as used herein are not limited to only digital files for word processing but may include any other processing document such as presentation slides, tables, databases, graphics, sound files, video files or any other digital document or file. Electronic collaborative word processing documents may include any digital file that may provide for input, editing, formatting, display, and/or output of text, graphics, widgets, objects, tables, links, animations, dynamically updated elements, or any other data object that may be used in conjunction with the digital file. Any information stored on or displayed from an electronic collaborative word processing document may be organized into blocks. Blocks may include static or dynamic information and may be linked to other sources of data for dynamic updates).
Claim 27: Grinberg discloses the computer-implemented method as per claim 26. Grinberg further discloses wherein determining the action intent includes evaluating a degree of correlation between the user input and a set of subject matter resources associated with respective automated assistant services of the set of automated assistant services (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose).
Claim 28: Grinberg discloses the computer-implemented method as per claim 21. Grinberg further discloses wherein: the generative interface panel is communicably coupled to an additional user device; the at least one received user input includes at least one user input received via the additional user device; and the generative interface panel includes a user avatar icon associated with a user account authenticated with respect to the additional user device (Paragraph [0047-0048]; [0074-0077]; [0083-0084]; Fig. 12, in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose).
Claim 29: Grinberg discloses the computer-implemented method as per claim 28. Grinberg further discloses wherein: the generative interface panel is communicably coupled to an additional user device; the at least one received user input includes at least one user input received via the additional user device; and the generative interface panel includes a user avatar icon associated with a user account authenticated with respect to the additional user device (Paragraph [0123-0126]; [0129-0131]; [0135-0137]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user. Consistent with some embodiments, selecting at least one AI agent from the plurality of distinct AI agents includes selecting at least two AI agents from the plurality of AI agents, and merging responses of the at least two selected AI agents to generate a merged response).
Claim 30: Grinberg discloses A computer-implemented method for operating a multi-participant interface for a content collaboration platform, the method comprising: causing display, on a user device, of a generative interface panel communicably coupled to a generative service, the generative interface panel comprising: an input region configured to receive user input; at least one received user input and one or more generative responses; and in response to receiving a natural language user input at the input region, evaluating the natural language user input to identify an action intent; (Paragraph [0007-0008]; [0080-0083]; [0099]; [0120]; Fig. 5, embodiments consistent with the present disclosure involve systems, methods, and computer readable medium for building an application incorporating AI functionality. Exemplary operations may include receiving a selection of an AI assistant add-on and at least one of a plurality of SaaS platform elements, enabling implementation of permission for providing access to data from the at least one of the plurality of linked SaaS platform elements. Some embodiments involve performing selection operations for a plurality of distinct artificial intelligence agents. Exemplary embodiments include sending via the application, a prompt to a plurality of distinct AI agents, and receiving from each of the plurality of distinct AI agents a response to the prompt. The operation may further include comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents. A software application may include a user interface enabling users to interact with and access features and functionalities of the software application. User interface is consistent with use of the term as described herein. For example, displaying a user interface may be done by showing a message on a screen, such as a pop-up box, or a list of selectable options);
selecting a set of automated assistant services provided by the generative service based on the action intent; causing a first automated assistant service of the set of automated assistant services to generate a first prompt comprising: (Paragraph [0117-0121]; Fig. 4, in some embodiments disclosed herein, processes are described that explain ways to select an AI agent from a pool of AI agents. Embodiments may involve selection operations for a plurality of distinct AI agent. An AI agent may be distinct if it provides at least one functions, purpose, solution, task, or use that distinguishes it from other agents. For example, one AI agent may be used to analyze text, while another may be used to analyze audio. Based on a developer’s needs or requests. Some embodiments may involve accessing an application that employes AI functionality. Some examples involve sending a prompt to a plurality of distinct Ai agents. A prompt is a message, question, or indication presented to elicit a response or action. It can be a textual message, a dialog box, an input field where an entity is pinged);
first predefined prompt text associated with the first automated assistant service; and at least a portion of the natural language user input; providing the first prompt to a generative output engine and, in response, obtaining a first generative response from the generative output engine; executing a first structured query to a first external system based on the first generative response to obtain first external content (Paragraph [0123-0126]; [0129-0131]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user);
causing a second automated assistant service of the set of automated assistant services to generate a second prompt comprising: second predefined prompt text associated with the second automated assistant service; and at least a portion of the first external content (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose);
providing the second prompt to generative output engine and, in response, obtaining a second generative response from the generative output engine; executing a second structured query to a second external system based on the second generative response to cause generation of second external content at the second external system; and causing display, in the generative interface panel, of an indication of the second external content (Paragraph [0123-0126]; [0129-0131]; [0135-0137]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user. Consistent with some embodiments, selecting at least one AI agent from the plurality of distinct AI agents includes selecting at least two AI agents from the plurality of AI agents, and merging responses of the at least two selected AI agents to generate a merged response).
Claim 31: Grinberg discloses the computer-implemented method as per claim 30. Grinberg further discloses wherein: the user input indicates a code object maintained by a source code management system; the first automated assistant service is a coding assistant service; the first external system is the source code management system; the first external content includes a link to a code artifact; the second automated assistant service is an issue tracking system assistant service; the second external system is the issue tracking system; and the second external content is an issue associated with the code artifact (Paragraph [0118-0120] some embodiments of the present disclosure may involve selection operation for a plurality of distinct AI agents. Selection operation in this context refers to choosing, picking, or distinguishing one or more AI agents from a group. A distinct AI agent is one that has a characteristic or behavior that distinguishes it from other agents. A UI may include any icon or link that facilitates a connection to access AI agents for AI functionality. This may allow a user to simply access AI services).
Claim 32: Grinberg discloses the computer-implemented method as per claim 30. Grinberg further discloses wherein: the user input indicates an issue maintained by an issue tracking system; the first automated assistant service is an issue tracking system assistant service; the first external content includes an indicator of a code object maintained by a source code management system; the second automated assistant service is a coding assistant service; the second external system is the source code management system; and the second external content is a code artifact associated with the issue (Paragraph [0007-0008]; [0080-0083]; [0099]; [0120]; Fig. 5, embodiments consistent with the present disclosure involve systems, methods, and computer readable medium for building an application incorporating AI functionality. Exemplary operations may include receiving a selection of an AI assistant add-on and at least one of a plurality of SaaS platform elements, enabling implementation of permission for providing access to data from the at least one of the plurality of linked SaaS platform elements. Some embodiments involve performing selection operations for a plurality of distinct artificial intelligence agents. Exemplary embodiments include sending via the application, a prompt to a plurality of distinct AI agents, and receiving from each of the plurality of distinct AI agents a response to the prompt. The operation may further include comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents. A software application may include a user interface enabling users to interact with and access features and functionalities of the software application. User interface is consistent with use of the term as described herein. For example, displaying a user interface may be done by showing a message on a screen, such as a pop-up box, or a list of selectable options).
Claim 33: Grinberg discloses the computer-implemented method as per claim 30. Grinberg further discloses wherein the method further comprises displaying, in the generative interface panel: a first avatar icon associated with the first automated assistant service; and a second avatar icon associated with the second automated assistant service (Paragraph [0007-0008]; [0080-0083]; [0099]; [0120]; Fig. 5, embodiments consistent with the present disclosure involve systems, methods, and computer readable medium for building an application incorporating AI functionality. Exemplary operations may include receiving a selection of an AI assistant add-on and at least one of a plurality of SaaS platform elements, enabling implementation of permission for providing access to data from the at least one of the plurality of linked SaaS platform elements. Some embodiments involve performing selection operations for a plurality of distinct artificial intelligence agents. Exemplary embodiments include sending via the application, a prompt to a plurality of distinct AI agents, and receiving from each of the plurality of distinct AI agents a response to the prompt. The operation may further include comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents. A software application may include a user interface enabling users to interact with and access features and functionalities of the software application. User interface is consistent with use of the term as described herein. For example, displaying a user interface may be done by showing a message on a screen, such as a pop-up box, or a list of selectable options).
Claim 34: Grinberg discloses the computer-implemented method as per claim 33. Grinberg further discloses wherein the first avatar icon and the second avatar icon are each selectable to cause display of a respective automated assistant service indicator (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose).
Claim 35: Grinberg discloses the computer-implemented method as per claim 30. Grinberg further discloses wherein the first automated assistant service and the second automated assistant service are each associated with a respective set of question-answer pairs and a respective set of knowledge base content (Paragraph [0031] a board may further contain cell comments, hidden rows and columns, formulas, data validation rules, filters, specific formatting, audits logs, version history, cross-referencing with different boards, external linking with data sources, permissions of access or a combination thereof. Boards may include sub-boards that may have a separate structure from a board. Sub-boards may be tables with sub-items that may be related to the items of a board. Columns intersecting with rows of items may together define cells in which data associated with each item may be maintained. Each column may have a heading or label defining one or more associated data types and may further include metadata (e.g., validation rules, ranges, hyperlinks, macros).
Claim 36: Grinberg discloses A computer-implemented method for operating a multi-participant interface for a content collaboration platform, the method comprising: causing display of a graphical user interface having a content panel depicting content of a content item managed by a content collaboration system, the graphical user interface displayed on a display of a client device; causing display, within the graphical user interface, of a generative interface panel including an input region configured to receive user input; in response to receiving a natural language user input at the input region, causing display of the natural language user input in generative interface panel (Paragraph [0007-0008]; [0080-0083]; [0099]; [0120]; Fig. 5, embodiments consistent with the present disclosure involve systems, methods, and computer readable medium for building an application incorporating AI functionality. Exemplary operations may include receiving a selection of an AI assistant add-on and at least one of a plurality of SaaS platform elements, enabling implementation of permission for providing access to data from the at least one of the plurality of linked SaaS platform elements. Some embodiments involve performing selection operations for a plurality of distinct artificial intelligence agents. Exemplary embodiments include sending via the application, a prompt to a plurality of distinct AI agents, and receiving from each of the plurality of distinct AI agents a response to the prompt. The operation may further include comparing information associated with each of the received responses, and selecting at least one AI agent from the plurality of distinct AI agents. A software application may include a user interface enabling users to interact with and access features and functionalities of the software application. User interface is consistent with use of the term as described herein. For example, displaying a user interface may be done by showing a message on a screen, such as a pop-up box, or a list of selectable options);
analyzing the user input to select a particular automated assistant service of a set of automated assistant services (Paragraph [0117-0121]; Fig. 4, in some embodiments disclosed herein, processes are described that explain ways to select an AI agent from a pool of AI agents. Embodiments may involve selection operations for a plurality of distinct AI agent. An AI agent may be distinct if it provides at least one functions, purpose, solution, task, or use that distinguishes it from other agents. For example, one AI agent may be used to analyze text, while another may be used to analyze audio. Based on a developer’s needs or requests. Some embodiments may involve accessing an application that employes AI functionality. Some examples involve sending a prompt to a plurality of distinct Ai agents. A prompt is a message, question, or indication presented to elicit a response or action. It can be a textual message, a dialog box, an input field where an entity is pinged);
causing the particular automated assistant service to generate a prompt comprising: predefined query prompt text associated with a subject-matter expertise of the particular automated assistant service; at least a portion of the natural language user input; and text extracted from the content displayed in the content panel (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose);
providing the prompt to a generative output engine and, in response, obtaining a generative response from the generative output engine; generating a query based on the generative response; (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose);
executing the query at an external system associated with the particular automated assistant service, and in response, obtaining external system content (Paragraph [0123-0126]; [0129-0131]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user);
causing display, in the generative interface panel, of an avatar icon corresponding to the particular automated assistant service; and causing display, within the generative interface panel, of a portion of the external system content. (Paragraph [0129-0131]; [0138-0139]; Fig. 4, upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user. An AI agent may generate and/or provide automatic replies, or rephrasing of text, for a conversation, such as a chat box or emails. The operations further include outputting the response of the at least one selected AI agent. The output may be received by a system or device associated with a user or sender of the query).
Claim 37: Grinberg discloses the computer-implemented method as per claim 36. Grinberg further discloses wherein: the particular automated assistant service is an issue tracking system automated assistant service; the external system content includes a list of issue items extracted from the external system; displaying the portion of the external system content includes displaying one or more selectable elements associated with respective issue items of the list of issue items; and in response to receiving a user selection of a selectable element of the one or more selectable elements, causing display of the respective issue item. (Paragraph [0123-0126]; [0129-0131]; Fig. 4, receiving from each of a plurality of distinct AI agents a response to the prompt. A response refers to a piece of information that is sent as a reply to a request, query, or preliminary information. The queried AI agents send responses that may provide instructions, information, or data to be further analyzed in the application. Some embodiments may involve comparing information associated with each of the received responses. Comparing information refers to examining two or more sets of data, facts, or details to identify similarities, differences, patterns, and/or relationships. A comparison could be made by analyzing segments or portions of information associated with each of the received responses or by analyzing the entirety of the data. Each Ai agent may send differing sets of information which are then compared to determine the most suitable. The information may contain data in an answer to a user query. Analyzing information associated with each of the received responses include evaluating qualify of content of each of the response, determining a response time, or combination thereof. Following ranking of the plurality of AI agents according to the determining scores, the operation further include saving the determined scores in a database. Selecting at least one Ai agent from the plurality of distinct AI agents based on the comparison. Upon selection the Ai agent may be assigned to further process and address one or more tasks of the query. For example, a prompt may be “complete task” and after the AI agent send responses to this query, one or more agent may generate and/or provide a response to the query or prompt to a device associated with the user).
Claim 38: Grinberg discloses the computer-implemented method as per claim 36. Grinberg further discloses wherein: the particular automated assistant service is a coding automated assistant service; the external system content includes a portion of a code object extracted from the external system; in response to receiving an additional user input associated with the portion of the code object, the coding automated assistant service is configured to generate an additional prompt comprising: predefined coding query prompt text; at least a portion of the additional user input; and the portion of the code object; and the method further comprises providing the additional prompt to a generative output engine and, in response, obtaining an additional generative response from the generative output engine (Paragraph [0047-0048]; [0074-0077]; [0083-0084] in some embodiments, machine learning algorithms may be trained using training examples. Within the context of this disclosure the platform may refer to any kind of cloud-based software delivery model where service providers host software applications and make them accessible to users over the internet. AI agent response may be shaped to align with desired objectives or outcomes by setting preferences such as language preferences, users may instruct the AI agent to respond in a particular language, adopt certain terminologies, or emulate a particular tone or style; formatting preferences; and task specific preferences: users may offer instructions to the AI agent for responding to a specific task. Some embodiments of the present disclosure may include building an application incorporating AI functionality. Building an application refers to generation of code, a software program, and/or a system that serves a specific purpose).
Claim 39: Grinberg discloses the computer-implemented method as per claim 38. Grinberg further discloses wherein: the additional generative response is displayed in the generative interface panel; and in response to receiving a user confirmation input with respect to the additional generative response, the method further comprises causing the external system to store at least a portion of the additional generative response (Paragraph [0118-0120] some embodiments of the present disclosure may involve selection operation for a plurality of distinct AI agents. Selection operation in this context refers to choosing, picking, or distinguishing one or more AI agents from a group. A distinct AI agent is one that has a characteristic or behavior that distinguishes it from other agents. A UI may include any icon or link that facilitates a connection to access AI agents for AI functionality. This may allow a user to simply access AI services).
Claim 40: Grinberg discloses the computer-implemented method as per claim 36. Grinberg further discloses wherein: the generative interface panel is communicably coupled to an additional user device; causing display of the generative interface panel includes causing display of at least one previous user input received via the additional user device in the generative interface panel; and the generative interface panel includes a user avatar icon associated with a user account authenticated with respect to the additional user device (Paragraph [0118-0120] some embodiments of the present disclosure may involve selection operation for a plurality of distinct AI agents. Selection operation in this context refers to choosing, picking, or distinguishing one or more AI agents from a group. A distinct AI agent is one that has a characteristic or behavior that distinguishes it from other agents. A UI may include any icon or link that facilitates a connection to access AI agents for AI functionality. This may allow a user to simply access AI services).
Therefore, claim 21-40 are rejected under U.S.C. 102.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Ferrydiansyah (US 2018/0052824) Task identification and completion based on natural language query.
Evermann (US 2014/0365209) System and method for inferring user intent form speech inputs.
Peng (US 2025/0138852) Task processing.
Missig (US 2014/0218372) Intelligent digital assistant in a desktop environment.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to COREY RUSS whose telephone number is (571)270-5902. The examiner can normally be reached on M-F 7:30-4:30.
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, Lynda Jasmin can be reached on 5712726782. 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.
/COREY RUSS/Primary Examiner, Art Unit 3629
Prosecution Insights