Amazon Bedrock Agents

Amazon Bedrock Agents enables generative AI applications to automate multistep tasks by seamlessly connecting with company systems, APIs and data sources. It uses the reasoning of foundation models to break down user requests, gather relevant information, and complete tasks, with features including multi-agent collaboration, retrieval augmented generation, memory retention and code interpretation. Amazon Bedrock Agents Classic is no longer available to new customers; AWS points new customers to Amazon Bedrock AgentCore for similar capabilities.

Official product page

1published use cases

1industry

0countries on record

Agentic AI

top AI capability

Evidence mix: High 1 · Medium 0 · Low 0 — bands are computed from each record's evidence signals.

PharmaceuticalsAgentic AIGenerative AIRetrieval-Augmented GenerationNatural Language Processing

Using Amazon Bedrock Agents to Accelerate Decisions Across Drug Development at AstraZeneca

AstraZeneca built Development Assistant, a multi-agent AI tool using Amazon Bedrock Agents, that lets clinical, regulatory, safety and quality teams ask natural language questions and get insights from structured and unstructured data in seconds via text-to-SQL generation and retrieval-augmented generation. A supervisor agent routes queries to specialized subagents (terminology, clinical, regulatory, database). Built on AstraZeneca's Drug Development Data Platform (3DP), the tool moved from concept to production in 6 months, including cybersecurity and AI governance checks, and is scaling to over 1,000 users.

AstraZenecaAmazon Bedrock Agents · Amazon Bedrock · Text-to-SQL