From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development

The pharmaceutical industry faces pressure to improve the drug development process while reducing costs in an evolving regulatory landscape. This paper presents the Preclinical Information Center (PRINCE), a cloud-hosted data integration platform developed by Bayer AG in collaboration with Thoughtwo...

Full description

Saved in:
Bibliographic Details
Main Authors: Carlos Henrique Vieira-Vieira, Sarang Sanjay Kulkarni, Adam Zalewski, Jobst Löffler, Jonas Münch, Annika Kreuchwig
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1636809/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849339033141903360
author Carlos Henrique Vieira-Vieira
Sarang Sanjay Kulkarni
Adam Zalewski
Jobst Löffler
Jonas Münch
Annika Kreuchwig
author_facet Carlos Henrique Vieira-Vieira
Sarang Sanjay Kulkarni
Adam Zalewski
Jobst Löffler
Jonas Münch
Annika Kreuchwig
author_sort Carlos Henrique Vieira-Vieira
collection DOAJ
description The pharmaceutical industry faces pressure to improve the drug development process while reducing costs in an evolving regulatory landscape. This paper presents the Preclinical Information Center (PRINCE), a cloud-hosted data integration platform developed by Bayer AG in collaboration with Thoughtworks. PRINCE integrates decades of structured and unstructured safety study reports, leveraging a multi-agent architecture based on Large Language Models (LLMs) and advanced data retrieval methodologies, such as Retrieval-Augmented Generation and Text-to-SQL. In this paper, we describe the three-step evolution of PRINCE from a data search tool based on keyword matching to a resourceful research assistant capable of answering complex questions and drafting regulatory-critical documents. We highlight the iterative development process, guided by user feedback, that ensures alignment with evolving research needs and maximizes utility. Finally, we discuss the importance of building trust-based solutions and how transparency and explainability have been integrated into PRINCE. In particular, the integration of a human-in-the-loop approach enhances the accuracy and retains human accountability. We believe that the development and deployment of the PRINCE chatbot demonstrate the transformative potential of AI in the pharmaceutical industry, significantly improving data accessibility and research efficiency, while prioritizing data governance and compliance.
format Article
id doaj-art-013ed62ceaff46dbbdfdba0b5ec2792f
institution Kabale University
issn 2624-8212
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-013ed62ceaff46dbbdfdba0b5ec2792f2025-08-20T03:44:14ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-08-01810.3389/frai.2025.16368091636809From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug developmentCarlos Henrique Vieira-Vieira0Sarang Sanjay Kulkarni1Adam Zalewski2Jobst Löffler3Jonas Münch4Annika Kreuchwig5Bayer Research and Development, Pharmaceuticals, Preclinical Development, Berlin, GermanyThoughtworks Technologies (India) Private Ltd., Pune, IndiaBayer Research and Development, Pharmaceuticals, Preclinical Development, Berlin, GermanyBayer Pharma Drug Innovation, Technology and Engineering, Leverkusen, GermanyBayer Digital Transformation and IT Pharma, Berlin, GermanyBayer Research and Development, Pharmaceuticals, Preclinical Development, Berlin, GermanyThe pharmaceutical industry faces pressure to improve the drug development process while reducing costs in an evolving regulatory landscape. This paper presents the Preclinical Information Center (PRINCE), a cloud-hosted data integration platform developed by Bayer AG in collaboration with Thoughtworks. PRINCE integrates decades of structured and unstructured safety study reports, leveraging a multi-agent architecture based on Large Language Models (LLMs) and advanced data retrieval methodologies, such as Retrieval-Augmented Generation and Text-to-SQL. In this paper, we describe the three-step evolution of PRINCE from a data search tool based on keyword matching to a resourceful research assistant capable of answering complex questions and drafting regulatory-critical documents. We highlight the iterative development process, guided by user feedback, that ensures alignment with evolving research needs and maximizes utility. Finally, we discuss the importance of building trust-based solutions and how transparency and explainability have been integrated into PRINCE. In particular, the integration of a human-in-the-loop approach enhances the accuracy and retains human accountability. We believe that the development and deployment of the PRINCE chatbot demonstrate the transformative potential of AI in the pharmaceutical industry, significantly improving data accessibility and research efficiency, while prioritizing data governance and compliance.https://www.frontiersin.org/articles/10.3389/frai.2025.1636809/fullpharmaceutical industrypreclinicallarge-language modelchatbotretrieval-augmented generationgenerative artificial intelligence
spellingShingle Carlos Henrique Vieira-Vieira
Sarang Sanjay Kulkarni
Adam Zalewski
Jobst Löffler
Jonas Münch
Annika Kreuchwig
From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development
Frontiers in Artificial Intelligence
pharmaceutical industry
preclinical
large-language model
chatbot
retrieval-augmented generation
generative artificial intelligence
title From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development
title_full From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development
title_fullStr From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development
title_full_unstemmed From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development
title_short From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development
title_sort from data silos to insights the prince multi agent knowledge engine for preclinical drug development
topic pharmaceutical industry
preclinical
large-language model
chatbot
retrieval-augmented generation
generative artificial intelligence
url https://www.frontiersin.org/articles/10.3389/frai.2025.1636809/full
work_keys_str_mv AT carloshenriquevieiravieira fromdatasilostoinsightstheprincemultiagentknowledgeengineforpreclinicaldrugdevelopment
AT sarangsanjaykulkarni fromdatasilostoinsightstheprincemultiagentknowledgeengineforpreclinicaldrugdevelopment
AT adamzalewski fromdatasilostoinsightstheprincemultiagentknowledgeengineforpreclinicaldrugdevelopment
AT jobstloffler fromdatasilostoinsightstheprincemultiagentknowledgeengineforpreclinicaldrugdevelopment
AT jonasmunch fromdatasilostoinsightstheprincemultiagentknowledgeengineforpreclinicaldrugdevelopment
AT annikakreuchwig fromdatasilostoinsightstheprincemultiagentknowledgeengineforpreclinicaldrugdevelopment