Introducing the next generation of Amazon OpenSearch Serverless for building your agentic AI applications

This article announces the next generation of Amazon OpenSearch Serverless, a fully managed search and vector engine optimized for building AI agents.

• Scales from zero to thousands of requests per second with up to 60% cost savings
• Creates resources in seconds and scales 20x faster than previous generation
• Native integrations with Vercel and Kiro for rapid AI agent deployment
• Supports full-text search and vector search collection types
• Express create option requires no configuration with automatic security policies
• Charges based on OpenSearch Compute Units (OCUs) for indexing and search
• OpenSearch Agent Skills provide pre-built domain knowledge for agent workflows
• Generally available in all AWS regions where OpenSearch Serverless operates

The next generation OpenSearch Serverless enables developers to build production-ready AI agent applications with minimal infrastructure management and significant cost optimization.