Elastic Introduces Agent Builder to Accelerate AI Agent Development

Agent Builder also provides an out-of-the-box conversational experience for exploring, analyzing, and optimizing any data in Elasticsearch.

As AI agents evolve to take on more complex and data-driven enterprise tasks, reliability and accuracy depend on delivering accurate context. In most enterprises, this context is scattered across various unstructured data sources, including documents, emails, business apps, and customer feedback. The process for getting the relevant context into agents at the right time is known as context engineering. While Elasticsearch has always been a leading platform for the core of context engineering, Agent Builder dramatically expands on this strength. It simplifies the entire operational lifecycle of agents, their development, configuration, execution, customization, and observability directly into Elasticsearch.

”AI agents don’t just need lots of data, they need the right data and tools, with relevance, guardrails, and observability built in,” said Ken Exner, chief product officer at Elastic. “Developers already rely on Elasticsearch to find the right answer from their messy business data. Agent Builder goes further by making Elasticsearch one of the fastest platforms to build precise AI agents that use your data, where retrieval, governance, and orchestration all operate in one place, natively.”

With Agent Builder, developers have built-in tools that go beyond basic run queries of open-standard Model Context Protocol (MCP) endpoints. Users of Agent Builder on Elasticsearch can ask natural language questions, identify which indexes to query, configure searches, define agent parameters and more.

With Agent Builder, developers can:

• Immediately Chat with Company Data: Agent Builder includes a built-in, native conversational agent. Right out of the box, you can ask questions and interact with any data you have in Elasticsearch, turning your data into an active, conversational partner.
• Leverage Intelligent Built-In Tools for Relevance: Agent Builder comes with a set of built-in tools, including a powerful search capability that selects the right index, understands the structure of that data, translates natural language into optimized semantic, hybrid or structured queries, and returns only the most relevant context to the Large Language Model (LLM).
• Build Powerful Custom Tools: Define tools that give the agent new skills, harnessing the full power of Elasticsearch’s query language (ES|QL) to precisely control what data is used for context. This gives granular control over the relevance, accuracy, and security of your agent's responses.
• Define Custom Agents: Create your own custom agent from the ground up, going beyond the built-in options. You control the agent’s entire persona with a custom system prompt, decide exactly which tools it can access, and configure its specific security profile to meet your needs.
• Integrate with MCP and A2A Safely: Connect external agents and applications via MCP and A2A, while maintaining governance through the Elasticsearch execution layer.

To see Agent Builder in action or start building with it today, read the Elastic blog.

Availability

Agent Builder in Elasticsearch is available today in Technical Preview on Elastic Cloud in serverless and coming soon in version 9.2.

About Elastic

Elastic (NYSE: ESTC), the Search AI Company, integrates its deep expertise in search technology with artificial intelligence to help everyone transform all of their data into answers, actions, and outcomes. Elastic's Search AI Platform — the foundation for its search, observability, and security solutions — is used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of Elasticsearch BV and its subsidiaries. All other company and product names may be trademarks of their respective owners.

View source version on businesswire.com: https://www.businesswire.com/news/home/20251021080622/en/