Loading

Get started with Elastic Agent Builder

Serverless Elasticsearch Preview Serverless Observability Unavailable Serverless Security Unavailable Stack Preview 9.2.0

Learn how to get started by enabling the Elastic Agent Builder features and begin chatting with your data.

  1. Set up an Elastic deployment

    If you don't already have an Elastic deployment, refer to Select your deployment type.

    Note

    For Elastic Cloud Hosted deployments, make sure you are using the solution navigation instead of classic navigation. You can set up a new space to use the solution nav.

  2. Enable Elastic Agent Builder

    Elastic Agent Builder is enabled by default in serverless Elasticsearch projects.

    Find Agents in the navigation menu to begin using the feature, or search for Agents in the global search field.

    You have to enable Elastic Agent Builder to get started on non-serverless deployments.

    You can enable the features using the UI:

    1. Search for AI / Agent Builder in the global search field.
    2. Toggle Elastic Agent Builder to on.
    3. Select Save changes.

    Find Agents in the navigation menu to begin using the feature, or search for Agents in the global search field.

  3. Ingest some data

    Before you begin with agents, you need some data in Elasticsearch. Otherwise, you will be chatting to the underlying LLM without any retrieval-augmented context.

    To learn about adding data for search use cases, go to Ingest for search use cases. For a broader overview of ingestion options, go to Ingest: Bring your data to Elastic.

    Tip

    If you're not ready to add your own data, you can:

  4. Begin chatting

    The Agent Chat UI provides a conversational interface where you can interact with agents and explore your data using natural language. Elastic Agent Builder includes a default agent named Elastic AI Agent with access to all built-in tools, so you can begin chatting immediately.

    Learn more in Agent Chat.

  5. Configure model (optional)

    By default, Elastic Agent Builder uses the Elastic Managed LLM. To use a different model, refer to model selection and configuration.

  6. Begin building agents and tools

    Once you've tested the default Elastic AI Agent with the built-in Elastic tools, you can begin building your own agents with custom instructions and creating your own tools to assign them.