Build a FinOps agent using Amazon Bedrock AgentCore

2026-03-31 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Data Science & Analytics · Depth: Intermediate, long

Summary

This post details how to construct a FinOps agent using Amazon Bedrock AgentCore to streamline AWS cost management across multiple accounts. The conversational agent integrates data from AWS Cost Explorer, AWS Budgets, and AWS Compute Optimizer, enabling finance teams to query cost drivers and optimization opportunities through natural language. The solution leverages AgentCore, Anthropic Claude Sonnet 4.5, the Strands Agent SDK, and the Model Context Protocol (MCP). It features a web application frontend hosted on AWS Amplify with Amazon Cognito for authentication, and maintains 30 days of conversation memory. The architecture involves five CDK stacks for authentication, image building, MCP server runtimes, AgentCore Gateway, and the main AgentCore Runtime, which orchestrates tool calls and model invocations.

Key takeaway

For Directors of AI/ML overseeing cloud financial operations, implementing this AgentCore-based FinOps agent can significantly enhance cost visibility and optimization. Your finance teams can gain immediate, natural language access to consolidated AWS cost data, reducing manual effort and accelerating decision-making. Consider deploying this solution to centralize cost analysis and identify savings opportunities more efficiently across your AWS accounts.

Key insights

An AgentCore-powered FinOps agent unifies AWS cost data for natural language querying and optimization.

Principles

• Consolidate data for holistic views.
• Enable natural language interaction for accessibility.

Method

Deploy a FinOps agent using AWS CDK, integrating AgentCore, Claude Sonnet 4.5, Strands Agent, and MCP servers to process natural language queries against AWS cost management services.

In practice

• Use AWS CDK for infrastructure deployment.
• Integrate AWS Amplify for web application hosting.
• Leverage AgentCore Memory for conversational context.

Topics

• FinOps Agent
• Amazon Bedrock AgentCore
• AWS Cost Management
• Anthropic Claude Sonnet
• AWS Cloud Development Kit

Code references

• aws-samples/sample-finops-agent-amazon-bedrock-agentcore
• aws-samples/sample-finops-agent-amazon-agentcore

Best for: AI Engineer, MLOps Engineer, Director of AI/ML

Related on AIssential

• Building AI agents for business support using Amazon Bedrock AgentCore — Amazon Bedrock AgentCore and Strands Agents enable significant cost reduction and operational efficiency for AI agent development in business support.
• Sage and AWS: Helping SMBs Embed Agentic AI — Sage and AWS partner to simplify agentic AI adoption for SMBs in financial workflows via cloud migration and a developer marketplace.
• Amazon Bedrock AgentCore harness is now generally available: Go from idea to production-grade agent in minutes — Amazon Bedrock AgentCore harness abstracts complex infrastructure, enabling rapid deployment and management of production-grade LLM agents.
• AWS Bedrock Agents: The Beginner’s Guide — AWS Bedrock Agents provide a managed platform for building and deploying AI agents with integrated orchestration and security.
• Semantic search across MCP tools with Amazon Bedrock AgentCore Gateway — Amazon Bedrock AgentCore Gateway enables scalable LLM agents through built-in semantic search for tool selection.
• AWS launches FinOps agent to bring AI cost governance to cloud spend — AI cost governance requires real-time, unit-economic analysis due to non-deterministic consumption patterns.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.