Category: Artificial Intelligence

This post shows how to build a semantic cache using vector search on Amazon ElastiCache for Valkey. As detailed in the Impact section of this post, our experiments with semantic caching reduced LLM inference cost by up to 86 percent and improved average end-to-end latency for queries by up to 88 percent.

In this post, we walk through the steps of integrating Oracle Database@AWS (ODB@AWS) with Amazon Bedrock for by creating a RAG assistant application using an Amazon Titan embedding model in Amazon Bedrock and vectors stored in Oracle AI Database 26ai.

In this post, we explore an artificial intelligence and machine learning (AI/ML)-powered database monitoring tool for PostgreSQL, using a self-managed or managed database service such as Amazon RDS for PostgreSQL and Amazon Aurora PostgreSQL.

In this post, we look at the costs, benefits, and drawbacks of replacing services for agentic AI with direct database access. Including those that work well and are proven in production, and new services yet to be built. Let’s take a closer look at the anatomy of an agentic AI application and what would factor into such decisions.

In this post, I show you how to build a serverless workflow orchestration engine that uses Amazon DynamoDB and AWS Lambda. The complete implementation is available in a GitHub repository, which includes two fully functional examples that you can deploy and run immediately to see the orchestration engine in action.

In April 2025, we introduced the Amazon DynamoDB data modeling tool for the Model Context Protocol (MCP) server. The tool guides you through a conversation, collects your requirements, and produces a data model that includes tables, indexes, and cost considerations. In this post, we show you how we built this automated evaluation framework and how it helped us deliver reliable DynamoDB data modeling guidance at scale.

In this post, we explore several approaches for automating the generation of vector embedding in Amazon Aurora PostgreSQL-Compatible Edition when data is inserted or modified in the database. Each approach offers different trade-offs in terms of complexity, latency, reliability, and scalability, allowing you to choose the best fit for your specific application needs.

When your network fails, finding the root cause usually takes hours of investigations, going through correlated alarms that often lead to symptoms rather than the actual problem. Root-cause analysis (RCA) systems are often built on hardcoded rules, static thresholds, and pre-defined patterns that work great until they don’t. Whether you’re troubleshooting network-level outages or service-level degradations, those rigid rule sets can’t adapt to cascading failures and complex interdependencies. In this post, we show you our AWS solution architecture that features a network digital twin using graphs and Agentic AI. We also share four runbook design patterns for Agentic AI-powered graph-based RCA on AWS. Finally, we show how DOCOMO provides real-world validation from their commercial networks of our first runbook design pattern, showing drastic MTTD improvement with 15s for failure isolation in transport and Radio Access Networks.

To help you move faster with greater confidence, we’re introducing a new DynamoDB data modeling tool, available as part of our DynamoDB Model Context Protocol (MCP) server. The DynamoDB MCP data modeling tool integrates with AI assistants that support MCP, providing a structured, natural-language-driven workflow to translate application requirements into DynamoDB data models. In this post, we show you how to generate a data model in minutes using this new data modeling tool.

Organizations are increasingly seeking to modernize their database infrastructure by migrating from legacy database engines such as Microsoft SQL Server and Oracle to more cost-effective and scalable open source alternatives such as PostgreSQL. This transition not only reduces licensing costs but also unlocks the flexibility and innovation offered by PostgreSQL’s rich feature set. In this post, we demonstrate how to convert and test database code from Microsoft SQL Server and Oracle to PostgreSQL using the generative AI capabilities of Amazon Bedrock.