Amazon Bedrock Managed Agents, Powered by OpenAI, Now in Limited Preview | Amazon Web Services

Amazon Bedrock Managed Agents, powered by OpenAI, is now in limited preview. Building production-grade AI agents and applications require more than intelligence. It requires enterprise infrastructure, security, and the operational foundation to run reliably at scale, plus memory that persists across sessions, skills that encode procedures, identity that enforces the right permissions, and compute options appropriate for the task. Bedrock Managed Agents combines OpenAI frontier models and agentic capabilities with the global infrastructure, security, and breadth of services on AWS. Deploying production-ready OpenAI-powered agents on AWS is fast and straightforward, so you can focus on what your agents should do, not the infrastructure behind them. Built with the OpenAI agent harness, Bedrock Managed Agents is engineered to unlock the full potential of OpenAI frontier models, delivering faster execution, sharper reasoning, and reliable steering of long-running tasks. Security and governance are built in from the moment you deploy: every agent operates with its own identity, logs every action for auditability, and runs inside your environment with all model inference on Amazon Bedrock. Bedrock Managed Agents and Bedrock AgentCore are a natural complement. AgentCore is the open platform to build, connect, and optimize agents at scale using any model and framework, and provides the default compute environment for Bedrock Managed Agents. As your agent footprint expands, AgentCore and Bedrock Managed Agents will provide additional capabilities such as authorization policy enforcement, agent and agent tool discovery, and observability and evaluation. Learn more about Amazon Bedrock Managed Agents, powered by OpenAI: https://go.aws/managed-agents-openai Subscribe to AWS: https://go.aws/subscribe Create a free AWS account: https://go.aws/signup Try AWS for free: https://go.aws/free Connect with an expert: https://go.aws/contact Explore more: https://go.aws/more Next