Category: Artificial Intelligence

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.

Healthcare providers manage an ever-growing volume of patient data and medication information to help ensure safe, effective treatment. Although traditional database systems excel at storing patient records, they require complex queries to access information. By adding generative AI capabilities, healthcare providers can now use natural language to search patient records and verify medication safety, rather than writing complex database queries. In this post, I show you a solution that uses Amazon Bedrock and Amazon DynamoDB to create an AI agent that helps healthcare providers quickly identify potential drug interactions by validating new prescriptions against a patient’s current medication records.

In this post, we describe a solution to integrate generative AI applications with relational databases like Amazon Aurora PostgreSQL-Compatible Edition using RDS Data API (Data API) for simplified database interactions, Amazon Bedrock for AI model access, Amazon Bedrock Agents for task automation and Amazon Bedrock Knowledge Bases for context information retrieval.

Text-to-SQL can automatically transform analytical questions into executable SQL code for enhanced data accessibility and streamlined data exploration, from analyzing sales data and monitoring performance metrics to assessing customer feedback. In this post, we explore how to use Amazon Relational Database Service (Amazon RDS) for PostgreSQL and Amazon Bedrock to build a generative AI text-to-SQL chatbot application using Retrieval Augmented Generation (RAG). We’ll also see how we can use Amazon MemoryDB with vector search to provide semantic caching to further accelerate this solution.