Type to search.

Elastic Agent Builder

Serverless

Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud.

Availability

  • Generally available

    This functionality is generally available and ready for production usage.

Serverless interfaces and procedures might differ from classic Elastic Stack deployments.

Stack GA 9.3+ …

The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats.

Availability

  • Generally available since 9.3

    This functionality is generally available and ready for production usage.

  • Preview in 9.2

    This functionality is in technical preview and is ready for evaluation. Use with caution in production; it is not recommended for mission-critical workloads. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features. Specific Support terms apply.

Unless stated otherwise on the page, this functionality is available when your Elastic Stack is deployed on Elastic Cloud Hosted, Elastic Cloud Enterprise, Elastic Cloud on Kubernetes, and self-managed environments.

This documentation corresponds to the latest patch available for each minor version. If you're not using the latest patch, check the release notes for changes.

Elastic Agent Builder is an AI conversational platform that lets you create AI agents that answer questions and take actions over your Elasticsearch data using natural language. Agents combine LLM reasoning and context engineering with built-in and custom tools that query your indices, so responses are grounded in your data. Key use cases include:

  • Chat with your Elasticsearch data immediately using the chat interface, preconfigured agents, and built-in tools available out of the box.
  • Build custom agents and tools tailored to your specific use cases using the UI or APIs.
  • Import tools from external MCP servers to give your agents additional capabilities.
  • Expose tools and agents to external systems like Claude Desktop, Cursor, and LangChain apps through the MCP server, A2A server, and REST APIs.

Learn more in key capabilities

To get started you need an Elastic deployment and you might need to enable the feature.

Get started with Elastic Agent Builder

Admonition

This feature requires the appropriate Elastic Stack subscription or Serverless project feature tier.

The Elastic Agent Builder framework consists of four key components: Agent Chat, Agents, Skills, 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.

Learn more about Agent Chat

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.

Learn more about agents

Skills are reusable instruction sets that give agents specialized expertise for particular task domains. A skill bundles knowledge content and tools so the agent knows how to approach a specific type of task. Skills load selectively based on the user's query, keeping agent configurations clean while enabling deep domain expertise. Choose from a set of built-in skills, or create your own.

Learn more about skills

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.

Learn more about tools

On Elastic Cloud Hosted and Elastic Cloud Serverless, Elastic Agent Builder comes with preconfigured models ready to use. You can also configure other model providers using inference endpoints, including local LLMs deployed on your infrastructure.

For solution-specific ratings of models tested on Elastic Security AI chat and AI-powered features, refer to the LLM performance matrix for Elastic Security.

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.

Learn more about token usage

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.

Learn more about limitations and known issues

Elastic Agent Builder release notes are part of the Kibana release notes. Look for the Elastic Agent Builder entries in each release.