Building Reliable Agentic AI Systems

This article presents a detailed case study of the Preclinical Information Center (PRINCE), a cloud-hosted platform developed by Bayer AG with Thoughtworks to address pharmaceutical industry challenges in drug development. It leverages Agentic Retrieval-Augmented Generation (RAG) and Text-to-SQL to integrate decades of safety study reports, evolving from keyword-based search to an intelligent research assistant. The article covers key engineering decisions around context engineering, harness engineering, orchestration, recovery, observability, and building trust through transparency, explainability, and human-in-the-loop integration. It demonstrates AI's transformative potential in pharmaceuticals, improving data accessibility and research efficiency while ensuring governance and compliance.