All news with #agentcore tag

Amazon Bedrock AgentCore Adds Policy and Evaluations

🛡️ Amazon Web Services' AgentCore introduces preview features — Policy and Evaluations — to help teams scale agents from prototypes into production. Policy intercepts real-time tool calls via AgentCore Gateway and converts natural-language rules into Cedar for auditability and compliance without custom code. Evaluations offers 13 built-in evaluators plus custom model-based scoring, with all quality metrics surfaced in an Amazon CloudWatch dashboard to simplify continuous testing and monitoring.

Bedrock AgentCore Runtime Adds Bi-Directional Streaming

🔁 Amazon Bedrock AgentCore Runtime now supports bi-directional streaming, enabling real-time, continuous conversations where agents listen and respond simultaneously and handle interruptions or context shifts mid-turn. This removes stop-start friction in voice and text agents and preserves context across exchanges. Built into AgentCore Runtime, the capability reduces months of engineering work required to implement streaming infrastructure, letting developers focus on agent experiences rather than plumbing. Available in nine AWS Regions with consumption-based pricing.

CloudWatch AgentCore Evaluations: Automated AI Agent Quality

🧭 Amazon CloudWatch now offers AgentCore Evaluations, an automated capability for assessing AI agent quality using real-world interactions. The feature includes 13 pre-built evaluators that measure dimensions such as helpfulness, tool selection, and response accuracy, and it also supports custom model-based scoring. Teams can access unified quality metrics, agent telemetry, and end-to-end traces in CloudWatch dashboards to correlate evaluations with prompts, logs, and traces for faster diagnosis and improvement.

Amazon Bedrock AgentCore Runtime Adds Code Upload Options

🧰 Amazon Bedrock AgentCore Runtime now supports two deployment methods: direct code-zip upload and container-based deployment. Developers can use drag-and-drop code-zip uploads for rapid prototyping or opt for container images when they need custom runtime configurations and dependencies. The serverless, model-agnostic runtime is designed to scale for production while maintaining enterprise security. This capability is available across nine AWS Regions with consumption-based pricing and no upfront costs.

AWS Marketplace: Flexible Pricing and Deployment for Agents

🤖 AWS Marketplace now offers flexible pricing and simplified deployment for AI agents and tools, including contract-based and usage-based options for Amazon Bedrock AgentCore Runtime containers. The update also streamlines OAuth credential management via Quick Launch for API-based agents and allows supported remote MCP servers procured through Marketplace to be used as MCP targets on AgentCore Gateway. These enhancements reduce deployment complexity and give partners more pricing flexibility while improving scalability for customers.

Amazon Bedrock AgentCore GA: Secure Agent Platform

🔐 Amazon Bedrock AgentCore is now generally available, offering an agentic platform to build, deploy, and operate agents securely at scale without infrastructure management. It adds VPC support, extended eight-hour runtimes, session isolation, and initial Agent-to-Agent (A2A) protocol support. Identity, Gateway, and Observability features provide secure authorization, tool discovery, and CloudWatch/OTEL monitoring.

Open-Source MCP Server for Amazon Bedrock AgentCore

🚀 The open-source Model Context Protocol (MCP) Server is now available for Amazon Bedrock AgentCore, providing a standardized interface that enables developers to analyze, transform, and deploy production-ready AI agents within their preferred development environments. The release includes one-click installation and integrates with agentic IDEs like Kiro and AI coding assistants such as Claude Code, Cursor, and the Amazon Q Developer CLI. Developers can use natural language to iteratively build agents, convert agent logic to the AgentCore SDK, and deploy into development accounts. Documentation and installation instructions are published in the MCP Server GitHub repository, with additional implementation guidance and pricing details available in the AgentCore documentation and pricing resources.