Elastic, the Search AI Company, has introduced Agent Builder, a new set of capabilities powered by Elasticsearch that enables developers to rapidly build custom AI agents using their own data. The tool allows developers to create AI agents through a natural, conversational interface, streamlining the process of context engineering—the critical task of delivering relevant, accurate data to AI models at the right time. In enterprise environments, valuable context is often buried in unstructured data across documents, emails, business applications, and customer feedback. Traditionally, extracting and organizing this information for AI agents has been complex and time-consuming. Agent Builder simplifies this by embedding context engineering directly into Elasticsearch, offering a unified platform for retrieval, governance, orchestration, and observability. Ken Exner, Elastic’s chief product officer, emphasized the importance of precision and control in AI agent development. “AI agents don’t just need lots of data, they need the right data and tools, with relevance, guardrails, and observability built in,” Exner said. “Agent Builder makes Elasticsearch one of the fastest and most reliable platforms to build accurate, data-driven AI agents—where everything happens in one place, natively.” With Agent Builder, developers can immediately start interacting with their data through a built-in conversational agent. They can ask natural language questions and receive intelligent, context-aware responses without writing code. The system automatically identifies the right data sources, translates queries into optimized semantic, hybrid, or structured searches, and returns only the most relevant information to the large language model. The platform also offers advanced customization. Developers can create custom tools using Elasticsearch’s powerful query language (ES|QL) to fine-tune data access and ensure accuracy and security. They can define custom agents from scratch, setting their own persona, tool access, and security policies. This level of control helps ensure agents behave reliably and align with organizational standards. Agent Builder supports integration with external systems through the Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication, allowing safe and governed connections between AI agents and applications—all managed through Elasticsearch’s execution layer. Agent Builder is currently available in Technical Preview on Elastic Cloud in both serverless and self-managed configurations, with broader availability expected in Elasticsearch version 9.2. Elastic’s platform is already used by thousands of organizations, including over half of the Fortune 500, to power search, observability, and security solutions. With Agent Builder, the company is expanding its role in the AI landscape by giving developers a fast, secure, and intelligent way to build AI agents that work with their data, not against it.