Use an AI index
Elastic Cloud Serverless projects are autoscaled environments, fully managed by Elastic and available on Elastic Cloud. Availability This functionality is experimental and is not ready for production usage. Experimental features may change or be removed at any time. Elastic will work to fix any issues, but experimental features are not subject to the support SLA of official GA features. Specific Support terms apply. Serverless interfaces and procedures might differ from classic Elastic Stack deployments. The Elastic Stack includes Elastic's core products such as Elasticsearch, Kibana, Logstash, and Beats. Availability We plan to add this functionality in a future Elastic Stack update. Subject to changes. 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.
Serverless
Experimental
Experimental
Stack
Planned
Planned
This page is currently hidden from the documentation navigation.
The following Context Engine pages are live:
Use an AI index to retrieve reusable context generated from source data or saved by agents as memory. Applications can call the Context Engine APIs directly. Agents call the same operations through tools that their integration provides, such as the built-in Elastic Agent Builder tools or LangChain tools that wrap the APIs. These paths reduce repeated source data discovery and interpretation.
Use the following guides to retrieve context through an agent or application:
| Goal | Start here |
|---|---|
| Retrieve context directly or compare the available query modes | Retrieve context from an AI index |
| Save task context in an AI index and retrieve it in later conversations | Save and retrieve memories with Context Engine |
| Configure and test an agent that uses an AI index | Configure agents to use an AI index |
| Use an AI index with an Elastic Agent Builder agent | Use Context Engine with Elastic Agent Builder |
| Query an AI index from LangChain or LangGraph | Query AI indices from LangChain |
Use an AI index from Claude Code with the Context Engine skill and the elastic CLI |
Use Context Engine with Claude Code |
Each supported access path lists the AI indices available to the caller, describes the relevant AI index, and queries it for Knowledge Indicators (KIs) or memories. This discovery-first flow provides the correct backing index, field names, and available context instead of requiring the agent or application to guess them. For the complete workflow, refer to Retrieve context from an AI index.
The following pages provide reference and maintenance guidance:
- Context Engine APIs lists the available operations and links to their complete Kibana API reference.
- Evaluate and improve Knowledge Indicators explains how to test retrieved context and improve its automations.