AWS published a technical deep-dive on the system prompt optimizer in Amazon Bedrock AgentCore optimization, explaining how reflector agents turn production traces into prompt recommendations validated via offline evaluation and A/B testing. The post reports benchmark results showing the reflectors beating GEPA and MIPROv2 on AppWorld and WebShop in both quality and cost. The experimental Sub-Agent Reflector is open-sourced in the Strands repository.
Amazon Bedrock AgentCore now offers observability for AI agents built with Strands Agents, LangGraph, and CrewAI, running on EKS, ECS, Lambda, on-premises, or other clouds like GCP and Azure. This extends monitoring beyond AWS to help practitioners track agent performance across hybrid environments.
Amazon Bedrock AgentCore now offers observability for AI agents built with Strands Agents, LangGraph, and CrewAI, running on EKS, ECS, Lambda, on-premises, or other clouds like GCP and Azure. This extends monitoring beyond AWS to help practitioners track agent performance across hybrid environments.
AWS published a technical walkthrough of evaluating multi-agent systems using Amazon Bedrock AgentCore Evaluations with built-in and custom evaluators. The reference implementation is a supply chain decisioning system with an orchestrator and four specialized sub-agents built on Strands Agents SDK, showing how teams can measure accuracy, business validity, and explainability from development through production.
AWS published a technical walkthrough of evaluating multi-agent systems using Amazon Bedrock AgentCore Evaluations with built-in and custom evaluators. The reference implementation is a supply chain decisioning system with an orchestrator and four specialized sub-agents built on Strands Agents SDK, showing how teams can measure accuracy, business validity, and explainability from development through production.
An AWS guide shows how to build a CI/CD quality gate that deploys an agent on Amazon Bedrock AgentCore with role-based MCP tools, evaluates each change, and blocks PRs when evaluation scores drop. It gives practitioners a pattern for catching agent regressions before production.
An AWS guide shows how to build a CI/CD quality gate that deploys an agent on Amazon Bedrock AgentCore with role-based MCP tools, evaluates each change, and blocks PRs when evaluation scores drop. It gives practitioners a pattern for catching agent regressions before production.
AWS published a technical walkthrough of a production-grade airline reservation system built on Amazon Bedrock AgentCore, pairing AgentCore Evaluations for continuous agent-quality scoring with AWS DevOps Agent for autonomous infrastructure incident investigation. The post argues infrastructure metrics miss silent agent failures — degraded behavior, wrong-tool routing, and permission issues that never throw errors — so production multi-agent systems need separate quality and health monitoring layers. The full reference implementation is open-sourced on GitHub.
AWS published a technical walkthrough of a production-grade airline reservation system built on Amazon Bedrock AgentCore, pairing AgentCore Evaluations for continuous agent-quality scoring with AWS DevOps Agent for autonomous infrastructure incident investigation. The post argues infrastructure metrics miss silent agent failures — degraded behavior, wrong-tool routing, and permission issues that never throw errors — so production multi-agent systems need separate quality and health monitoring layers. The full reference implementation is open-sourced on GitHub.
Amazon Bedrock AgentCore payments is now generally available, enabling AI agents to autonomously discover and pay for APIs, MCP tools, and data sources during task execution. The service, built with Coinbase and Stripe, supports pay-per-use pricing models and safe pre-approved transactions.
Amazon Bedrock AgentCore payments is now generally available, enabling AI agents to autonomously discover and pay for APIs, MCP tools, and data sources during task execution. The service, built with Coinbase and Stripe, supports pay-per-use pricing models and safe pre-approved transactions.