
How our agent skills research, build, and test a complete Elastic integration
We pointed our agent skills at the NIST NVD API and got two data streams and a validated CEL program, with pipeline and system tests passing. The research showed 78% of a day’s CVE records are republications of older ones, which changed the design.

We cut 40% of our MCP tools to get into Claude’s connector directory
Anthropic’s reviewers read every tool in our MCP connector and sent back fixes, wording changes and a case for publishing fewer of them, which is part of why mcp.elastic.co is now on the roadmap.

Using Jev as a search reranker: benchmarks and how to implement
We had Jev score Elasticsearch hybrid search results and let a short Python policy do the reranking, taking nDCG@10 from 0.9351 to 0.9565 on 250 Amazon Shopping Queries, and the code is all here.

Let the big model think, let the small model work: Splitting LLM costs in Elastic Workflows
Build an Elastic workflow that sends a data sample to a large model to propose classification labels. A human signs off, then a smaller model applies them across the full corpus.

Skip the stateful OTel Collector: Elasticsearch 9.5 natively stores both metric temporalities
Ingest cumulative and delta OpenTelemetry metrics under the same metric name while ES|QL and PromQL queries auto-detect temporality per series, with no new syntax or conversion pipelines required.

Kibana Dashboards API: A stable contract for every panel type, tested by 50+ teams before GA
Manage Kibana dashboards as code: Commit to Git, promote across environments, and automate deployments with the Kibana API and Terraform.

One prompt, a complete workflow: Elastic's AI agent writes your automation for you
Elastic Workflows takes a plain-text prompt and generates YAML you can inspect, version and run against your Elasticsearch data. Now GA, with human-in-the-loop workflows in Slack, parallel execution, and 10 new connectors.

On-prem in under 5 minutes: Jina embedding models now available for on-prem deployment
All 28 Jina AI models, including rerankers, as ready-to-deploy Docker containers, with zero telemetry and no license server. Drop-in compatible with OpenAI, Cohere, Voyage AI and Elastic Inference Service APIs.

4 NVIDIA AI tasks, 1 Elasticsearch API: Embeddings, chat, completion, and rerank
Set up NVIDIA hosted models in Elasticsearch with one API key and a model ID. No custom integration code needed.

One command. Natural language. Your Elasticsearch data, straight to the terminal.
Query your Elasticsearch data from the terminal in plain English. The official Elastic GitHub Copilot CLI plugin generates and runs ES|QL queries against your cluster. No Kibana, no manual syntax.

Building a multilingual voice agent with Elastic Agent Builder & Sarvam AI
A working demo combining Sarvam AI speech with Elastic Agent Builder: identity verification, per-customer ES|QL queries, and mid-call language switching across 22 Indian languages without multilingual indices.

Talk to your Elasticsearch data: building a real-time voice agent with Google ADK and MCP in 3 components
Wire Google ADK's real-time voice streaming to your Elasticsearch data via Agent Builder's built-in MCP server; no custom integration code required.
Ready to build state of the art search experiences?
Sufficiently advanced search isn’t achieved with the efforts of one. Elasticsearch is powered by data scientists, ML ops, engineers, and many more who are just as passionate about search as you are. Let’s connect and work together to build the magical search experience that will get you the results you want.