Amazon Bedrock FAQs changed AWS, May 1, 2026
AWS · May 1, 2026 · 11 added, 4 removed · found in an Internet Archive capture
- Added: AgentCore enables developers to accelerate AI agents into production with the scale, reliability, and security, critical to real-world deployment. AgentCore provides tools and capabilities to make agents more effective and capable, purpose-built infrastructure to securely scale agents, and controls to operate trustworthy agents. AgentCore capabilities are composable and work with popular open-source frameworks and any model, so you don't have to choose between open-source flexibility and enterprise-grade security and reliability. Learn more about AgentCore.
- Removed: Amazon Bedrock Agents is a fully managed capability that makes it easier for developers to create generative-AI based applications that can complete complex tasks for a wide range of use cases and deliver up-to-date answers based on proprietary knowledge sources. In just a few short steps, Amazon Bedrock Agents automatically breaks down tasks and creates an orchestration plan-without any manual coding. Agents created in Bedrock can securely connect to company data through an API, automatically converting data into a machine-readable format, and augmenting the request with relevant information to generate the most accurate response. Agents can then automatically call APIs to fulfill a user's request. As a fully managed capability, Amazon Bedrock Agents removes the undifferentiated lifting of managing system integration and infrastructure provisioning, allowing developers to use generative AI to its full extent throughout their organization.
- Removed: AgentCore enables developers to accelerate AI agents into production with the scale, reliability, and security, critical to real-world deployment. AgentCore provides tools and capabilities to make agents more effective and capable, purpose-built infrastructure to securely scale agents, and controls to operate trustworthy agents. AgentCore capabilities are composable and work with popular open-source frameworks and any model, so you don't have to choose between open-source flexibility and enterprise-grade security and reliability. Learn more visit Amazon Bedrock AgentCore .
- Added: Policy: Gives you deterministic control over what your agents can do. Define fine-grained rules using natural language or Cedar that authorize every tool call at the gateway, ensuring agents operate within defined boundaries without slowing them down.
- Added: Browser : Provides a fast, secure, cloud-based browser runtime to enable AI agents to interact with websites at scale.
- Removed: Browser tool : Provides a fast, secure, cloud-based browser runtime to enable AI agents to interact with websites at scale.
- Added: Evaluations : Provides automated, continuous quality assessment for AI agents in production. Run built-in or custom evaluators against production traffic to measure performance, catch regressions early, and optimize based on real usage patterns.
- Added: AWS Agent Registry : A centralized catalog to discover, share, and reuse agents, tools, and skills across your organization. Governed publishing workflows and semantic search ensure teams find what already exists before building from scratch.
- Added: Amazon Bedrock Managed Agents, powered by OpenAI, combines OpenAI frontier reasoning models and OpenAI harness with the reliability, security, and richness of AWS services that millions of organizations already rely on. Everything your agent needs is included from the start: memory, skills, identity, security, and compute. The agent harness works with the model to manage the full reasoning cycle: understanding tasks, calling tools, observing results, and continuing until the work is done. Because memory persists across sessions, every interaction builds on the last, and your agents only get more effective over time. All model inference runs on Amazon Bedrock and your data never leaves AWS.
- Added: Learn more on the Bedrock Managed Agents overview page .
- Added: Bedrock Managed Agents is currently in preview. To be kept in the loop on latest developments, sign up through the interest form.
- Added: They are designed to work together. Bedrock Managed Agents is optimized for building with OpenAI frontier models and agentic capabilities. AgentCore is the open platform to build, connect, and optimize agents at scale using any model and framework. AgentCore provides the managed execution environments for Bedrock Managed Agents, and 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.
- Added: Learn more about Bedrock Managed Agents and AgentCore.
- Added: Amazon Bedrock Guardrails provides the ability to implement cross-account safeguards within an organization. You can specify a Guardrail ARN that contains the required safety controls to be enforced across accounts and organization units within your Bedrock policy of your organization. Once this policy is established, all inference calls to Amazon Bedrock across accounts will automatically enforce the safety controls without explicitly calling Guardrails for each call. This organization-wide implementation enables consistent application of safety controls, reduces operational overhead, and supports the flexibility to apply account-level and application-specific guardrails for individual use case requirements. See here for details.
- Removed: Amazon Bedrock Guardrails provides the ability to establish mandatory guardrails for every inference call using IAM policy-based enforcement capabilities. See here for details.
About this change
- Page
- aws.amazon.com/bedrock/faqs/
- Kind
- Help article
- Text hash
- 7da6bfe3285e to b5df2193047c
- Dated by
- the first Internet Archive capture sampled that shows the new text; the change happened on or before this date