{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:52:54Z","timestamp":1770817974260,"version":"3.50.1"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3389\/frai.2025.1636809","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:19:44Z","timestamp":1755580784000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["From data silos to insights: the PRINCE multi-agent knowledge engine for preclinical drug development"],"prefix":"10.3389","volume":"8","author":[{"given":"Carlos Henrique","family":"Vieira-Vieira","sequence":"first","affiliation":[]},{"given":"Sarang Sanjay","family":"Kulkarni","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Zalewski","sequence":"additional","affiliation":[]},{"given":"Jobst","family":"L\u00f6ffler","sequence":"additional","affiliation":[]},{"given":"Jonas","family":"M\u00fcnch","sequence":"additional","affiliation":[]},{"given":"Annika","family":"Kreuchwig","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"ref2","doi-asserted-by":"publisher","first-page":"e65651","DOI":"10.2196\/65651","article-title":"Assessment of the efficiency of a ChatGPT-based tool, MyGenAssist, in an industry pharmacovigilance Department for Case Documentation: cross-over study","volume":"27","author":"Bena\u00efche","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1021\/acs.chemrestox.0c00317","article-title":"Leveraging the value of CDISC SEND data sets for cross-study analysis: incidence of microscopic findings in control animals","volume":"34","author":"Carfagna","year":"2021","journal-title":"Chem. Res. Toxicol."},{"key":"ref4","first-page":"6340","article-title":"AI-enabled language models (LMs) to large language models (LLMs) and multimodal large language models (MLLMs) in drug discovery and development","volume":"86","author":"Chakraborty","year":"2025","journal-title":"J. Adv. Res"},{"key":"ref5","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"150","DOI":"10.18653\/v1\/2024.eacl-demo.16","article-title":"RAGAs: Automated Evaluation of Retrieval Augmented Generation","author":"Es","year":"2024","journal-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"8048","DOI":"10.24963\/ijcai.2024\/890","article-title":"Large Language Model Based Multi-agents: A Survey of Progress and Challenges","author":"Guo","year":"2024","journal-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence Survey Track"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1111\/aor.14503","article-title":"FDA modernization act 2.0 allows for alternatives to animal testing","volume":"47","author":"Han","year":"2023","journal-title":"Artif. Organs"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"75735","DOI":"10.1109\/ACCESS.2024.3401547","article-title":"Applications, challenges, and future directions of human-in-the-loop learning","volume":"12","author":"Kumar","year":"2024","journal-title":"IEEE Access"},{"key":"ref11","year":"2025"},{"key":"ref12","year":"2025"},{"key":"ref14","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Lewis","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"10879","DOI":"10.18653\/v1\/2024.acl-long.586","article-title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","volume":"1","author":"Li","year":"2024","journal-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"105705","DOI":"10.1016\/j.yrtph.2024.105705","article-title":"The new paradigm in animal testing \u2013 \u201c3Rs alternatives\u201d","volume":"153","author":"Poh","year":"2024","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.18875","article-title":"Generative to agentic AI: survey","author":"Schneider","year":"2025","journal-title":"Conceptualization, and Challenges."},{"key":"ref18","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e55318","DOI":"10.2196\/55318","article-title":"An empirical evaluation of prompting strategies for large language models in zero-shot clinical natural language processing: algorithm development and validation study","volume":"12","author":"Sivarajkumar","year":"2024","journal-title":"JMIR Med. Inform."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"103642","DOI":"10.1016\/j.drudis.2023.103642","article-title":"Perspectives of data science in preclinical safety assessment","volume":"28","author":"Steger-Hartmann","year":"2023","journal-title":"Drug Discov. Today"},{"key":"ref21","first-page":"28201","article-title":"Many heads are better than one: improved scientific idea generation by a LLM-based multi-agent system","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics","author":"Su","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1093\/bib\/bbad493","article-title":"Opportunities and challenges for ChatGPT and large language models in biomedicine and health","volume":"25","author":"Tian","year":"2024","journal-title":"Brief. Bioinform."},{"key":"ref23","year":"2020"},{"key":"ref24","year":""},{"key":"ref25","article-title":"FDA announces completion of first AI-assisted scientific review pilot and aggressive agency-wide AI rollout timeline","year":""},{"key":"ref26","year":""},{"key":"ref27","first-page":"121101","article-title":"The rise and potential of large language model based agents: a survey","volume-title":"Sci. China Inf. Sci.","author":"Xi","year":"2023"},{"key":"ref1","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1145\/3626772.3657878","article-title":"C-Pack: Packaged Resources To Advance General Chinese Embedding","author":"Xiao","year":"2023","journal-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1636809\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:19:45Z","timestamp":1755580785000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1636809\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":25,"alternative-id":["10.3389\/frai.2025.1636809"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1636809","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"article-number":"1636809"}}