Elastic Agent Builder
Elastic Agent Builder enables you to create AI agents grounded in your Elasticsearch data. It combines the power of large language models with Elastic-native features for prompt engineering, context engineering, and automation in one place, reducing the need to write and maintain custom application code.
Get started quickly with built-in agents, tools, and the chat UI, then extend with custom agents, custom tools, and programmatic interfaces for more advanced use cases.
- Elastic Stack users: an Enterprise subscription.
- Elastic Security Serverless users: the Security Analytics Complete or Elastic AI Soc Engine (EASE) feature tier.
- Elastic Observability Serverless and Elasticsearch Serverless users: the Complete feature tier.
- Elasticsearch relevance and security: Leverage Elasticsearch's search capabilities for precise context retrieval, with secure data access controls.
- Built-in agents and tools: Get started immediately with pre-configured agents and tools available out of the box.
- Chat UI: Chat with agents in real time using natural language.
- Custom and external tools: Build targeted tools to deliver precise context, or connect external tools through the Model Context Protocol.
- Custom agents: Create agents with tailored instructions and toolsets for specific use cases.
- MCP and A2A servers: Expose agents to external clients and enable agent-to-agent communication through standard protocols.
- Kibana REST APIs: Work with Agent Builder functionalities programmatically, including agents, tools, and conversations.
- Elastic Workflows integration: Automate complex processes within your deployment using the Elastic-native automation engine. Your agents can trigger workflows and workflows can invoke agents in their steps.
The Elastic Agent Builder framework consists of three key components: Agent Chat, Agents, and Tools.
Agent Chat is the synchronous chat interface for interacting with agents through natural language. The chat UI enables real-time communication where you can ask questions, request data analysis, and receive immediate responses from your configured agents. You can also chat with agents programmatically.
Agents are powered by custom LLM instructions and the ability to use tools to answer questions, take action, or support workflows. Each agent translates natural language requests into specific actions using the tools assigned to it. Choose from a set of built-in agents, or create your own.
Tools are modular, reusable functions that agents use to search, retrieve, and manipulate Elasticsearch data. Tools are the primary mechanism for connecting agent capabilities to your data. Choose from a set of built-in tools, or create your own and assign them to your custom agents.
To get started you need an Elastic deployment and you might need to enable the feature.
Get started with Elastic Agent Builder
By default, on Elastic Cloud Hosted and Elastic Cloud Serverless agents use the Elastic Managed LLM, but you can configure other model providers using connectors, including local LLMs deployed on your infrastructure.
Learn more about model selection
Elastic Agent Builder provides APIs and LLM integration options for programmatic access and automation. These interfaces enable you to build integrations with other applications and extend Elastic Agent Builder's capabilities to fit your specific requirements.
Learn more about programmatic access
Configure security roles and API keys to control who can use agents, which tools they can access, and what data they can query.
Learn more about permissions and access control
Understand how tokens are calculated and accumulated during agent execution to predict the impact on your usage and costs.
Find solutions to common problems when working with Elastic Agent Builder.
Learn more about troubleshooting
Understand current limitations and known issues with Elastic Agent Builder.