aws-solutions-library-samples

Guidance For Cost Analysis And Optimization With Amazon Bedrock Agentcore — DevOps skill for Claude Code

DevOps community

This Guidance shows how to simplify AWS cost management across multiple accounts by building a conversational AI agent that consolidates billing data from multiple sources into a single natural langua.

How to install Guidance For Cost Analysis And Optimization With Amazon Bedrock Agentcore

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aws-solutions-library-samples/guidance-for-cost-analysis-and-optimization-with-amazon-bedrock-agentcore and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Guidance For Cost Analysis And Optimization With Amazon Bedrock Agentcore does

This Guidance shows how to simplify AWS cost management across multiple accounts by building a conversational AI agent that consolidates billing data from multiple sources into a single natural language interface.

Alternatives in DevOps

  • Datachain — The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure 2.8k ★
  • Proxy — route Claude Code requests through multiple upstream providers (OpenCode Go, OpenCode Zen, and AWS Bedrock) wi 957 ★
  • WP CLI And Ops — WordPress CLI and operations management 902 ★

README

Guidance for Building a FinOps Agent Using Amazon Bedrock AgentCore on AWS

Table of Contents

  1. Overview
  2. Prerequisites
  3. Automated Deployment
  4. Manual Deployment
  5. Deployment Validation
  6. Running the Guidance
  7. Next Steps
  8. Cleanup
  9. FAQ, Known Issues, Additional Considerations, and Limitations
  10. Notices
  11. Authors

Overview

Managing costs across multiple AWS accounts often requires finance teams to query data from several sources to get a complete view of spending and optimization opportunities. This Guidance demonstrates how to build a FinOps agent using **Amazon Bedrock AgentCore** that helps finance teams manage AWS costs across multiple accounts. The conversational agent consolidates data from **AWS Cost Explorer**, **AWS Budgets**, and **AWS Compute Optimizer** into a single interface, so teams can ask questions like "What are my top cost drivers this month?" and receive immediate answers.

The Guidance uses **Amazon Bedrock AgentCore Runtime** to host a custom agent built with the **Strands Agents SDK** and **Anthropic Claude Sonnet 4.5** on **Amazon Bedrock**. **Amazon Bedrock AgentCore Gateway** provides unified tool discovery and invocation, routing requests to two **Model Context Protocol (MCP)** server runtimes — one for AWS Billing and Cost Management and one for AWS Pricing. **Amazon Cognito** manages user authentication, and **AWS Amplify** hosts the web application frontend. **AgentCore Memory** retains 30 days of conversation cont