Announcing AWS Well-Architected Agent, an AI-powered intelligence to optimize your cloud environment (preview)

Summary

• AWS announces the public preview of the AWS Well-Architected Agent, an AI-powered service that analyzes AWS environments to deliver targeted recommendations for cost, security, performance, & resilience.
• The agent evaluates infrastructure by correlating utilization metrics, resource configurations, & application topology against best practices across 65+ AWS services without relying on manual audits.
• Goal-aligned intelligence replaces flat findings with context-aware, prioritized recommendations generated by impact & effort against declared business objectives.
• The service provides three levels of recommendations: individual resource findings with dollar impact & step-by-step remediation, consolidated findings across multiple resources, & broad architectural patterns with Infrastructure as Code (IaC) changes.
• Users have optionality in remediation by choosing between console walk-throughs, updated IaC changes, or AWS Command Line Interface (CLI) commands.
• To start, users create an agent profile in the AWS Well-Architected console to define scope, select optimization pillars, & set goals for cost optimization, performance, resilience, & security.
• Access requires provisioning customer-managed IAM roles that allow the agent to read resource configurations, utilization metrics, & application topology.
• Resource & application recommendations are generated within 24 hours after profile creation.
• Users can conduct architecture reviews on pre-deployment workloads by uploading IaC projects in Terraform, AWS CloudFormation, or AWS Cloud Development Kit (CDK).
• Applications can be defined with AWS accounts, regions, services, & tags to enhance the relevancy of recommendations.
• Prioritized recommendations include details, insights, impacts, trade-offs, & automation-ready remediation steps.
• Updated IaC templates provide code changes that users can copy directly into their codebase.
• API access allows integration into existing development & operations workflows via the AWS MCP Server & plugins.
• Automation features deliver recommendations with exact IaC code changes, identified risks by pillar, & periodic updates through the console & API.
• Generative AI capabilities may produce errors or incomplete information, requiring user evaluation & oversight per AWS Responsible AI practices.
• Existing AWS Well-Architected Tool remains available for manual evaluation with user-defined lenses.
• The preview is available in US East (N. Virginia), US East (Ohio), & US West (Oregon) regions.
• Workloads from any AWS commercial Region can be onboarded.
• The service is delivered by AWS Support & available to customers with an AWS Support plan.