Category: Artificial Intelligence

In this post, we walk through building an agent that investigates blocking and deadlocks on Amazon RDS for SQL Server — two issues that directly impact application performance, cause transaction failures, and lead to user-facing timeouts. Using the Strands Agents framework, we convert the T-SQL queries DBAs already use for these investigations into agent tools, combine them into a single agent, and deploy it to AgentCore Runtime.

In this post, we walk through the steps to set up the custom migration assistant agent and migrate a PostgreSQL database to Aurora DSQL. We demonstrate how to use natural language prompts to analyze database schemas, generate compatibility reports, apply converted schemas, and manage data replication through AWS DMS. As of this writing, AWS DMS does not support Aurora DSQL as target endpoint. To address this, our solution uses Amazon Simple Storage Service (Amazon S3) and AWS Lambda functions as a bridge to load data into Aurora DSQL.

In this post, you learn how to implement conversational operations for Oracle E-Business Suite (Oracle EBS) on AWS by connecting Kiro CLI with your monitoring infrastructure through the MCP. We walk through the technical architecture that enables natural language queries to retrieve CloudWatch metrics, analyze logs, and execute operational commands.

In this post, we demonstrate how to efficiently migrate relational-style data from NoSQL to Aurora DSQL, using Kiro CLI as our generative AI tool to optimize schema design and streamline the migration process.

In this post, we show how you can use graph algorithms to analyze the results of AWS Entity Resolution and related transactions for the CNP use case. We use several AWS services, including Neptune Analytics, AWS Entity Resolution, Amazon SageMaker notebooks, and Amazon S3.

In this post, we talk about the benefits of caching in generative AI applications. We also elaborated on a few implementation strategies that can help you create and maintain an effective cache for your application.

In this post, we show you how to build a centralized dashboard for monitoring Amazon RDS configurations across your organization by using AWS Config and Amazon Quick Suite. This solution delivers detailed insights across different areas, such as summary metrics, backup configurations, security posture, engine and support information, extended configurations, and resource tagging.

In this post we show you how to build production-ready AI agents with durable state management using Amazon DynamoDB and LangGraph with the new DynamoDBSaver connector, a LangGraph checkpoint library maintained by AWS for Amazon DynamoDB.

In this post, we show how you can turn your ideas into full-stack applications with Kiro powers for Aurora. We explore how a new innovation, Kiro powers, can help you use Amazon Aurora best practices built into your development workflow, automatically implementing configurations and optimizations that make sure your database layer is production-ready from day one.

In this post, we walk through how we used Kiro, an agentic Integrated Development Environment (IDE), to build a complete fitness center management application that digitizes paper-based fitness tracking. We explore Kiro’s spec-driven development workflow and see how it transforms complex application development into a streamlined, iterative process. Our solution uses Amazon DocumentDB as the backend.