We introduce Research Assistant, an internal system developed at AstraZeneca to aid scientists and clinicians in exploring biomedical questions. The system utilizes a large language model (LLM) and provides a chat-style interface that aggregates evidence from various data sources, including scientific literature, knowledge graphs, chemistry, clinical trials, safety resources, expression data, and internal experimental systems. It supports both a fast mode for direct question answering and a multi-step mode for more complex research tasks. Responses are grounded in retrieved evidence and linked back to the original sources, allowing users to review and further explore the underlying data. This technical note outlines the system architecture, key design choices, and lessons learned from deploying it at scale to support day-to-day R&D workflows across AstraZeneca. Blogger's Review: The development of this system showcases the immense potential of artificial intelligence in biomedical research, significantly enhancing research efficiency and accuracy by integrating multi-source data and providing transparent evidence chains.