Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Cheng et al (20240303473).
As per claim 1, Cheng et al (20240303473) teaches a method, comprising:
receiving, at a computing system implementing a large language model and associated with an organization, a data set associated with one or more projects of the organization (as, developing a generative AI creation framework to customize generative AI stack using user prompts, natural language descriptions, and domain adaption – abstract; wherein, in para 0004, ; part of this framework is to generate a customize generative AI stack that can generate a plurality/fullspectrum of domain-adaptive prompts to enable a plurality of adaptive AI chat applications – para 0023; using LLM’s – para 0025; for different enterprising type companies – para 0005);
determining, using an application programming interface (API) library to provide the data set to the large language model, one or more tasks associated with each of the one or more projects (as, in API’s, using LLM’s and then performing domain adaptation – para 0025);
selecting one or more software agents for executing the one or more tasks based at least in part on determining the one or more tasks, the one or more software agents managed by the organization and selected from a database, wherein each software agent of the one or more software agents is configured for a respective type of task associated with the one or more tasks (as choosing the trained/updated chatbot – para 0121, based on the domain adaptation according to tasks – para 0025, using a library of prompt templates, commo-use cases, and subtasks – para 0025, and custom tuned LLM for a data source or task – para 0026);
and executing the one or more tasks using the selected one or more software agents (as the AI agent executes the task – para 0031).
As per claim 2, Cheng et al (20240303473) teaches the method of claim 1, further comprising:
identifying the respective type of task associated with each task of the one or more tasks using a software orchestrator of the computing system (as using a domain adapted AI agent – para 0031, in view of customized data processing for a customer in business analytics – para 0025),
wherein selecting the one or more software agents comprises associating each task of the one or more tasks with a respective software agent of the one or more software agents based at least in part on the respective type of task associated with each task (and, repeating, the AI agents are domain specified-tailored to handle certain tasks – see para 0025/0026, for custom-tune LLM optimization, to enable differing LLM’s based on the task/domain at hand – para 0027).
As per claim 3, Cheng et al (20240303473) teaches the method of claim 1, further comprising:
storing metadata associated with the one or more projects to a database managed by the computing system (as storing metadata for the plurality of projects/applications – para 0067).
As per claim 4, Cheng et al (20240303473) teaches the method of claim 1, wherein the data set comprises:
a transcript of a meeting (as, storing/updating ground-truth spoken dialogs and responses – para 0093, this is a stored transcript of previous dialogues; regarding the claim scope of ‘meetings’, examiner notes the use of the techniques in a ‘dialog’ environment, which includes meetings, as well as AI chat applications – para 0023, and in customer management applications -- para 0025; one of ordinary skill in the art of chatbot apps would easily recognize that these systems are usable in a meeting environment),
and determining the one or more tasks comprises identifying the one or more tasks within the transcript using the large language model (as parsing and determining the task request – para 0043/0044, which is used as a ‘prompt’ into the LLM – para 0043).
As per claim 5, Cheng et al (20240303473) teaches the method of claim 4, further comprising:
identifying, using the large language model, a first project of the one or more projects and a second project of the one or more projects; and associating, using the large language model, a first subset of the one or more tasks with the first project and a second subset of the one or more tasks with the second project (examiner notes, in para 0004, the intent of Cheng et al (20240303473) is to build a customized generative artificial intelligent platform; part of this framework is to generate a customize generative AI stack that can generate a plurality/fullspectrum of domain-adaptive prompts to enable a plurality of adaptive AI chat applications – para 0023; some of the prompts contain examples of the job to be done, or others having step-by-step instructions – para 0026; clearly, both can exist, and therefore, in view of “generating a plurality/fullspecturm of domain-adaptive prompts in para 0023, one project can be a domain-specific type projects of a certain job to be done, and a second project where step-by-step instruction are required (para 0026) wherein the domain-adaptation operates on sub-tasks as well - para 0025). .
As per claim 6, Cheng et al (20240303473) teaches the method of claim 4, further comprising:
determining, using the large language model, that a first representative of one or more representatives associated with the meeting corresponds to a first task of the one or more tasks (as, explained above regarding ‘meeting’, using large language models – either specific vendor LLM or a custom tuned LLM – para 0026; mapped by tasks/subtasks during the domain adaptation phase – para 0025);
determining, using the large language model, that a second representative of the one or more representatives corresponds to a second task of the one or more tasks; and storing an indication that the first representative corresponds to the first task and the second representative corresponds to the second task based at least in part on the first representative corresponding to the first task and the second representative corresponding to the second task (as, through ‘domain adaptation’, performing content indexing, which is in the format of ‘example-common-use-cases’, the listing includes tasks/subtasks – para 0025; further to the tasks – the prompt module creates and stores a plurality of prompts for different tasks – para 0033, reading back on para 0032, to the LLM).
As per claim 7, Cheng et al (20240303473) teaches the method of claim 6, wherein executing the one or more tasks comprises:
transmitting, using a software agent of the one or more software agents (as a chatbot user interface – para 0121), a first message associated with the first task to the first representative and a second message associated with the second task to the second representative (as sending messages/prompts to the NLP model – para 0121);
refraining from transmitting the second message to the first representative; and refraining from transmitting the first message to the second representative (examiner notes that the first/second representative are mappings/labels to a task – see above; as such, Cheng et al (20240303473) teaches generating one or more responses – see para 0121; see para 0088, wherein different values are generated by indicating data characteristics correspond to a task; one of ordinary skill in the art of evaluating/scoring neural networks that if a certain value threshold is not met, then that particular characteristic is not emphasized – see table US 00002, between para 0058, and para 0059).
As per claim 8, Cheng et al (20240303473) teaches the method of claim 1, wherein the data set comprises:
a transcript of an interaction between a representative of the organization and a user of the organization (as, storing/updating ground-truth spoken dialogs and responses – para 0093, this is a stored transcript of previous dialogues; regarding the claim scope of ‘meetings’, examiner notes the use of the techniques in a ‘dialog’ environment, which includes meetings, as well as AI chat applications – para 0023, and in customer management applications -- para 0025; one of ordinary skill in the art of chatbot apps would easily recognize that these systems are usable in a meeting environment),
and determining the one or more tasks comprises identifying one or more updates to an account managed by the organization and associated with the user (as updating the data based on user feedback – para 0074).
As per claim 9, Cheng et al (20240303473) teaches the method of claim 8, further comprising:
providing, by the computing system, an indication of the one or more updates to a software agent of the one or more software agents; and updating, by the software agent, one or more parameters of the account based at least in part on the indication of the one or more updates (as, supervised tuning used to predict a field value or update the deployed model – para 0074; see also para 0075 wherein the LLM is updated, and producing a small specific self-contained LLM – para 0075; and generating a message indicating a system response – para 0101).
Claims 10-18 are non-transitory computer readable medium claim whose steps are performed by method claims 1-9 above and as such, claims 10-18 are similar in scope and content to claims 1-9 above; therefore, claims 10-18 are rejected under similar rationale as presented against claims 1-9 above, Furthermore, Cheng et al (20240303473) teaches storage mediums storing executable steps performing the disclosed functions -- see para 0079.
Claims 19-20 are system claims performing the steps found in claims 1-9 above and as such, claims 19-20 are similar in scope and content to claims 1-9 above; therefore, claims 19-20 are rejected under similar rationale as presented against claims 1-9 above, Furthermore, Cheng et al (20240303473) teaches memories and processors executing the disclosed steps – see para 0078, and para 0079.
Response to Arguments
Applicant's arguments filed 02/06/2026 have been fully considered but they are not persuasive. Commencing on page 8 of the response, applicants allege that the Cheng reference does not teach/disclose certain claim features (copy/pasted on the bottom of pp 8), and continuing on pp 9 of the response, applicant presents a generalized summary of Cheng by referring to the abstract and para 0121 of Cheng. Applicants present a compare/contrast on the bottom one-third of pp 9; examiner argues that the claim scope of “software agent”, is, according to applicants spec (para 0006, 0022, 0031), is software cord that when executed, instructs the processor to perform the task. As such, the recited section of Cheng, to the selection of different prompts, are software instructions that when directed to the machine learning models performing the execution of the software; the stored prompts of Cheng are customized to the task to be performed, as well as, domain adaptation of the desired task. On pp 10-top11 of the response, applicants replicate claim features found in dependent claims 2/11, and the recited portions of Cheng (para 0025); with the initiating compare/contrast presented on the top of pp 11, wherein “this discussion of generating and modifying different prompts using customer data is not the same as ‘selecting the one or more software agents [b][ associated each task of the one or more tasks with a respective software agent of the one or more software agent…tasks”, “Cheng does not select any software agent by associating different tasks…in a database” – examiner argues, as presented above, that the ‘software agent’ is software code that is selected, executed by a processor, to execute/generate a result; Cheng’s modified prompts performs such steps. The remainer of Pg 11 of the response concludes with summary statements.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Please see related art listed on the PTO-892 form.
Furthermore, please see the following references that teach certain features found in applicants specification/claims:
El Hattami et al (20230385026) teaches the building of text-to-text models for specific API’s – fig. 1; and creating issue tasks based on the interpretation – fig. 5b.
Lavallee (20160070696) teaches agents selector based on NLU derivation of tasks and semantic re-ranker – fig. 1)
Subramanya et al (20150205782) teaches App UI/URL based on task classification via a grammar engine (Fig. 3)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael Opsasnick, telephone number (571)272-7623, who is available Monday-Friday, 9am-5pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Mr. Richemond Dorvil, can be reached at (571)272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/Michael N Opsasnick/Primary Examiner, Art Unit 2658 05/27/2026
Prosecution Insights