Abstract: A system and method for contesting outcomes of AI models, such as generative AI models, by a contestability feature. The system and method may also provide a remediation process when an AI model response is contested.
Type:
Application
Filed:
December 29, 2025
Publication date:
July 23, 2026
Applicant:
Seekr Technologies, Inc.
Inventors:
Stefanos Poulis, Andrew J. Bauer, Diego A. Mesa, Robin J. Clark, Patrick C. Condo
Abstract: A system and method aligns generative artificial intelligence (a large language model (LLM) or a large multimodal model (LMM) with the principles of a specific domain so that the generative artificial intelligence is better able to respond to a user query in the specific domain. The system and method may post-train an already trained generative artificial intelligence system. The domains may include a standard, an industry vertical, a set of enterprise internal documents, a set of personal data on a device and a blogpost.
Type:
Application
Filed:
December 27, 2024
Publication date:
April 30, 2026
Applicant:
SEEKR Technologies, Inc.
Inventors:
Stefanos Poulis, Robin J. Clark, Patrick C. Condo
Abstract: An agentic workflow system and method generate question and answer pairs and prompts that may be used to aligns generative artificial intelligence (a large language model (LLM) or a large multimodal model (LMM)) with the principles of a specific domain so that the generative artificial intelligence is better able to respond to a user query in the specific domain. The system and method may also generate aligning processes that may be used to post-train an already trained generative artificial intelligence system or fine tune the training of the generative artificial intelligence system to align that generative artificial intelligence system with the principles of the specific domain. The system and method may be used to align the generative artificial intelligence system to a plurality of different domains.
Type:
Application
Filed:
March 20, 2025
Publication date:
October 16, 2025
Applicant:
SEEKR Technologies, Inc.
Inventors:
Stefanos Poulis, Andrew J. Bauer, Diego A. Mesa, Robin J. Clark, Patrick C. Condo
Abstract: A system and method aligns generative artificial intelligence (a large language model (LLM) or a large multimodal model (LMM) with the principles of a specific domain so that the generative artificial intelligence is better able to respond to a user query in the specific domain. The system and method may post-train an already trained generative artificial intelligence system or fine tune the training of the generative artificial intelligence system to align that generative artificial intelligence system with the principles of the specific domain. The system and method may be used to align the generative artificial intelligence system to a plurality of different domains.
Type:
Application
Filed:
October 21, 2024
Publication date:
September 11, 2025
Applicant:
SEEKR Technologies, Inc.
Inventors:
Stefanos Poulis, Robin J. Clark, Patrick C. Condo
Abstract: A quality score system and method for a piece of content. The system and method may use artificial intelligence/machine learning to determine the one or more scores for each piece of content. In one embodiment, the quality scoring system and method may incorporate source and industry score factors, use a transformer model to generate the quality score and adjust the quality score based on scenarios.
Type:
Application
Filed:
December 30, 2024
Publication date:
June 19, 2025
Applicant:
SEEKR Technologies, Inc.
Inventors:
Stefanos Poulis, Robin J Clark, Patrick C Condo
Abstract: An agentic workflow system and method generate question and answer pairs and prompts that may be used to aligns generative artificial intelligence (a large language model (LLM) or a large multimodal model (LMM)) with the principles of a specific domain so that the generative artificial intelligence is better able to respond to a user query in the specific domain. The system and method may also generate aligning processes that may be used to post-train an already trained generative artificial intelligence system or fine tune the training of the generative artificial intelligence system to align that generative artificial intelligence system with the principles of the specific domain. The system and method may be used to align the generative artificial intelligence system to a plurality of different domains.
Type:
Grant
Filed:
January 2, 2025
Date of Patent:
May 6, 2025
Assignee:
SEEKR Technologies, Inc.
Inventors:
Stefanos Poulis, Andrew J. Bauer, Diego A. Mesa, Robin J. Clark, Patrick C. Condo
Abstract: A quality score system and method for a piece of content. The system and method may use artificial intelligence/machine learning to determine the one or more scores for each piece of content. In one embodiment, the quality scoring system and method may use a SAAS architecture, may incorporate source and industry score factors and use a transformer model to generate the quality score.
Type:
Application
Filed:
December 30, 2024
Publication date:
May 1, 2025
Applicant:
SEEKR Technologies, Inc.
Inventors:
Stefanos Poulis, Robin J. Clark, Patrick C. Condo
Abstract: A scoring system and method identifies personal attacks in a piece of audio content and generates a civility score for the piece of audio content that can differentiate between personal attacks and vernacular/casual banter. The piece of audio content may be a podcast.
Type:
Application
Filed:
November 19, 2024
Publication date:
March 6, 2025
Applicant:
SEEKR Technologies, Inc.
Inventors:
Robin J. Clark, Ali Taleb Zadeh Kasgari, Stefanos Poulis
Abstract: One or more techniques and/or systems are provided for implementing a pipeline used to generate, train, test, and implement a document scoring model for assigning document scores to documents. Features from various sources are combined to create a joined page level feature set, a joined domain level feature set, and a host level feature set. Numerical features and content features are extracted from ground truth documents and random documents. The numerical features are joined with the joined feature sets to create a set of joined features. The document scoring model is trained using the set of joined features and a training technique. A document is scored with a document score using the document scoring model based upon the content features and the set of joined features with document scores obtained during training.
Abstract: One or more techniques and/or systems are provided for implementing a pipeline used to generate, train, test, and implement a document scoring model for assigning document scores to documents. Features from various sources are combined to create a joined page level feature set, a joined domain level feature set, and a host level feature set. Numerical features and content features are extracted from ground truth documents and random documents. The numerical features are joined with the joined feature sets to create a set of joined features. The document scoring model is trained using the set of joined features and a training technique. A document is scored with a document score using the document scoring model based upon the content features and the set of joined features with document scores obtained during training.