United KingdomHealthcare and life sciences2026 – ongoingAstraZeneca
Research Assistant for biomedical evidence search
AstraZeneca's Research Assistant reached 15,000 unique internal users within a year
Problem
Scientists needed programming skills to query AstraZeneca's biomedical data services. This limited direct access by scientific and clinical experts.
Approach
AstraZeneca built a chat interface that searched internal resources and external biomedical evidence. Specialized agents retrieved information for citation-linked answers. A deeper research mode planned and executed dependent questions.
Results
Takeaway
The assistant gave domain experts access to existing data services through natural-language questions. Users could follow citations to assess the supporting evidence.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AIAI agents
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
AstraZeneca's authors described an internally deployed biomedical assistant. They reported growth from a small pilot to 15,000 unique internal users within one year.
Full details are in the original sources.
