For one of Europe's largest pharmaceutical companies, Modulai built a production-oriented multi-agent RAG solution that answers questions about clinical trial outcomes. The system retrieves evidence, runs analysis, and returns results in the right format, whether text, visualizations, or aggregated downloads, while maintaining traceability and regulatory compliance.
Challenge
Clinical design data is spread across tabular trial databases, graph relationships, and unstructured reports. Teams needed faster access to design elements and supporting rationale without manual cross-checking across systems. Any solution had to be traceable, compliant, and robust in a regulated setting.
Solution
Modulai implemented a multi-agent workflow that plans the task, retrieves relevant sources, generates validated queries, and performs analysis before responding. The system returns open-format answers with citations to retrieved material, produces tables when appropriate, and enables data exports for downstream work. Guardrails enforce scope, reduce prompt-injection risk, and ensure results are compliant and aligned with regulatory standards.
Tools
Data was accessed through a combination of tabular stores, graph databases, and unstructured text retrieval. The graph layer enabled protocol relationship queries and comparison across related studies. Quality was maintained with automated evaluation in CI/CD and system monitoring, covering retrieval relevance, faithfulness, and end-to-end correctness, along with latency and cost tracking.
Value created
The system gives clinical teams direct answers about trial outcomes drawn from data that was previously spread across tabular databases, graph relationships, and unstructured reports, without manual cross-checking across systems. Because every answer carries citations to its source material and runs inside guardrails built for a regulated setting, teams get faster access to trial evidence while keeping the traceability and compliance that pharmaceutical work requires.
Learn more
