Improving and Validating Multi-Agent Prompts with Bedrock AgentCore Optimization

This article is an AI-assisted translation of a Japanese technical article. Introduction In April 2026, Amazon Bedrock AgentCore added a new capability called Optimization , which takes real agent traces and proposes prompt improvements based on them. https://aws.amazon.com/about-aws/whats-new/2026/05/bedrock-agentcore-optimization-preview/ In this article, I apply AgentCore Optimization to a Strands Agents-as-Tools setup (a main agent that wraps sub-agents as @tool s) and walk through what actu