Context Engine

Context Engine helps you turn enterprise data into reusable context for agents and applications. By investing in useful context up front, you reduce the time and tokens agents spend repeatedly finding and interpreting the same information and help them answer recurring questions more consistently. Because that context is stored as Knowledge Indicators (KIs), you can review and improve it over time.

You organize context around a specific subject or set of questions, generate KIs from relevant data, and make that knowledge available to an agent.

To build and use context with Context Engine:

  1. Create an AI index

    Create an AI index for a defined area of context.

  2. Add source data

    Add one or more sources that contain the relevant data.

  3. Generate Knowledge Indicators

    Configure automations, implemented as Elastic Workflows, to generate and refresh KIs from those sources.

  4. Make the context available

    Make the AI index available to an agent or application.

  5. Configure context retrieval

    Configure the agent or application with the appropriate tools and instructions to retrieve KIs as context and query source data when current detail is required.

Follow Get started with Context Engine to create an AI index from existing Elasticsearch data, generate your first KI, and test how an Elastic Agent Builder agent uses it.

Learn how AI indices, sources, automations, KIs, and agent access fit together in Context Engine concepts.

Learn how to choose source data, select a KI generation strategy, review automations, and maintain useful context in Build and maintain an AI index.

Learn how to use Context Engine with agents, including Elastic Agent Builder agents and agents built with LangChain.