# How AstraZeneca uses AWS Bedrock

**1,000 users**: “is scaling the solution to over 1,000 users”

As published on [aws.amazon.com](https://aws.amazon.com/solutions/case-studies/astrazeneca-case-study/). Captured by usedby on 2026-10-09.

- Company: [AstraZeneca](https://www.usedby.ai/companies/astrazeneca.md)
- Tool: [AWS Bedrock](https://www.usedby.ai/tools/aws-bedrock.md)
- Industry: [Biotech & Pharma](https://www.usedby.ai/companies/industry/biotech-pharma.md)
- Teams: clinical, regulatory, patient safety, quality

## What the story says

AstraZeneca built Development Assistant, a multi-agent tool on Amazon Bedrock Agents that lets clinical, regulatory, safety and quality teams ask natural language questions and get answers from structured and unstructured data. A supervisor agent routes each query to specialized subagents, and the system uses text-to-SQL generation with retrieval-augmented generation.

Summary written by usedby from the source page, in English. The figures are those of AWS Bedrock and AstraZeneca, not ours.

> Working alongside the AWS team, AstraZeneca moved Development Assistant from concept to production in only 6 months, including cybersecurity and AI governance checks, and is scaling the solution to over 1,000 users.

- **6 months**: “AstraZeneca moved Development Assistant from concept to production in only 6 months”

> Amazon Bedrock provided a multi-agent architecture that essentially gives us the flexibility and scalability we were lacking before
>
> Vaishali Goyal, senior director of R&D IT

Source: [aws.amazon.com](https://aws.amazon.com/solutions/case-studies/astrazeneca-case-study/), captured 2026-10-09.

## What usedby checked

We compared the story with its live page on 2026-10-09.

- Checked: the figure 1,000 users is printed word for word on the page, near the name of AstraZeneca.
- Checked: the passage quoted above is copied word for word from the page, near the name of AstraZeneca.
- Checked: AstraZeneca uses AWS Bedrock. Confirmed line. Latest check across sources: 2026-10-09.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/astrazeneca-case-study · How we check: https://www.usedby.ai/methodology