- Generative AI
- Amazon Bedrock
- Managed Agents
Amazon Bedrock Managed Agents, powered by OpenAI (Limited preview)
Optimized for the latest OpenAI frontier models on trusted AWS infrastructure
Meet Bedrock Managed Agents, powered by OpenAI
Bedrock Managed Agents combines frontier AI models with trusted AWS infrastructure, enabling customers to quickly and easily build production-ready OpenAI-powered agents in the cloud. It is built with the OpenAI harness, which is engineered to unlock the full potential of OpenAI frontier models, delivering faster execution, sharper reasoning, and reliable steering of long-running tasks.
Quickly deploy production-ready agents powered by OpenAI
With the OpenAI harness at its core, the managed runtime handles inference, memory, and skills within your environment so you ship faster.
What makes Bedrock Managed Agents different?
Frontier intelligence
Bedrock Managed Agents is built with the OpenAI harness and engineered to unlock the full potential of OpenAI frontier models, delivering faster execution, sharper reasoning, and reliable steering of long-running tasks.
Secure from day one
Security and governance are built in from the moment you deploy. Every agent operates with its own identity and logs every action for auditability. Agents run inside your environment. All inference runs on Amazon Bedrock and your data never leaves AWS.
The breadth and scale of AWS
As agent deployments scale enterprise-wide, they need to run on scalable infrastructure close to the data and systems they access. Bedrock Managed Agents connects directly to AWS compute and data services you already use and rely on.
Designed to work with AgentCore
Bedrock AgentCore is the open platform to build, connect, and optimize agents at scale using any model and framework, and serves as the default compute environment for Bedrock Managed Agents. As your agent footprint expands across your enterprise, AgentCore and Bedrock Managed Agents will provide additional capabilities such as authorization policy enforcement, agent and agent tool discovery, and observability and evaluation capabilities.
