Managing Amazon OpenSearch Service clusters demands deep domain expertise from index lifecycle management and shard rebalancing to fine-grained access control and vector search tuning for generative AI workloads. These tasks require repetitive REST API calls, hand-crafted JSON configurations, and constant context-switching across documentation. What if you could manage your OpenSearch cluster the same way you'd describe a task to a colleague in plain English?
This session demonstrates how agentic AI transforms OpenSearch operations. Using Kiro CLI with the open-source OpenSearch MCP (Model Context Protocol) Server, teams can perform cluster health triage, index lifecycle policy management, security configuration, and k-NN vector index optimization through natural language commands.

We walk through real-world scenarios including incident response, setting up RAG pipelines with vector search, and automating ISM policies all without writing a single REST call. Attendees will learn how the MCP standard bridges AI agents to OpenSearch APIs, democratizing cluster management for developers and administrators of all experience levels.