Loading

Get started with Elastic Agent Builder

To start using Elastic Agent Builder you need to deploy Elasticsearch and Kibana. If you don't already have an Elastic deployment, you can start a free trial or refer to Deploy > Choosing your deployment type.

Admonition

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

  1. Enable Elastic Agent Builder

    On non-serverless deployments, Elastic Agent Builder availability depends on the navigation mode of your Kibana space:

    You can also search for Agents in the global search field.

    Elastic Agent Builder is the default chat experience in all serverless project types.

    You can also search for Agents in the global search field.

    Note

    To learn about required privileges for Elastic Agent Builder, refer to Permissions and access control.

  2. Ingest data into Elasticsearch

    If you already have data in Elasticsearch, skip ahead to start a conversation.

    If you need to add data first, choose the path that fits:

  3. Start a conversation

    The Agent Chat UI provides a conversational interface where you can interact with agents and explore your data using natural language. The default Elastic AI Agent is ready to use immediately.

    Learn more in Agent Chat.

  4. Configure model (optional)

    On Elastic Cloud Hosted and Elastic Cloud Serverless, Elastic Agent Builder comes with preconfigured models ready to use. To switch models or add your own, refer to model selection and configuration.

  5. Build custom skills and tools

    The default Elastic AI Agent comes with built-in skills and built-in tools ready to use. To add your own domain expertise, create custom skills that package knowledge and tools into reusable instruction sets. For tips on writing effective skill instructions, refer to the skill creation guidelines. To learn how skills are invoked during a conversation, refer to how skills are invoked.

    You can also create custom tools to give your skills and agents access to additional data sources. If you need a fully separate agent with its own system prompt, you can create a custom agent.

    To work programmatically, try the Elastic Agent Builder API tutorial or explore the Kibana APIs.