Build an AI-powered AWS support companion with Amazon Bedrock AgentCore
AWS just showed how to build AI agents that actually work—a support companion that handles CloudWatch logs, docs, and case creation in one interface.
Why it matters
This is a production-ready reference architecture showing how enterprises can deploy agentic workflows at scale using Bedrock. It signals AWS's pivot toward agent-as-a-service infrastructure and demonstrates practical orchestration patterns (Strands + MCP) that developers will copy across support, ops, and automation use cases.
The key facts
12 to knowAmazon Bedrock AgentCore launch/feature availability
Strands Agents as orchestration framework integration
Model Context Protocol (MCP) connection to AWS services
Multi-capability agent: CloudWatch analysis, documentation search, community query, support case creation
Single-script CloudFormation deployment
AWS Amplify web frontend included
Published July 7, 2026 on AWS ML blog
Amazon Bedrock AgentCore integration
Strands Agents orchestration framework
Model Context Protocol (MCP) for AWS service connections
Agent capabilities: CloudWatch log analysis, AWS documentation search, re:Post community knowledge, support case creation
Use case: autonomous AWS support workflows
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: In this post, you build an AWS Support Companion using Amazon Bedrock AgentCore. The agent uses Strands Agents as the orchestration framework and connects to AWS services through the Model Context Protocol (MCP). By the end, you have a working agent that can analyze CloudWatch logs, search AWS…