Agentic AI

June 5, 2026

Your Elastic agent, Google's ADK, and zero custom APIs: building “Lucky Planet” over A2A

Elastic Agent Builder's native A2A endpoint lets Google's ADK orchestrate a remote agent, with no custom REST API. Watch it work in 'Lucky Planet,' a random-exoplanet game built end-to-end.

Your Elastic agent, Google's ADK, and zero custom APIs: building “Lucky Planet” over A2A
137,000 people, zero human decisions: agentic disaster response with Elasticsearch

June 4, 2026

137,000 people, zero human decisions: agentic disaster response with Elasticsearch

Find out how a Kibana detection rule, a workflow and an AI agent automatically relocated 137,000 military personnel across seven installations when a hurricane hit, no dispatcher required.

Build a RAG agent with Elasticsearch and GitHub Copilot SDK

June 1, 2026

Build a RAG agent with Elasticsearch and GitHub Copilot SDK

Wire Elasticsearch into the GitHub Copilot SDK as a RAG tool in five lines of C#, grounding your agent in your own logs, docs and data instead of model training data.

Cutting agent costs with pre-computed context

Cutting agent costs with pre-computed context

Pre-computing context as Knowledge Indicators reduces LLM agent token costs by up to 75% and improves answer accuracy from 60% to 92%. This post covers the extraction, retrieval and feedback loop that make it work, tested against the BrowseComp-Plus benchmark.

Elastic Agent Builder: How we taught AI agents to manage their own context

May 5, 2026

Elastic Agent Builder: How we taught AI agents to manage their own context

Agent Builder in Elasticsearch 9.4 ships dynamically loaded skills, a conversation context store, selective compaction, and external connectors to cut token costs by 40% and let agents handle their own context management.

Elastic-caveman: Cutting AI response tokens by 64% without losing the best of Elastic

April 29, 2026

Elastic-caveman: Cutting AI response tokens by 64% without losing the best of Elastic

Learn how to use elastic-caveman to cut AI response tokens while keeping the Elastic agentic brilliance.

How to build agentic AI applications with Mastra and Elasticsearch

April 8, 2026

How to build agentic AI applications with Mastra and Elasticsearch

Learn how to build agentic AI applications using Mastra and Elasticsearch through a practical example.

Creating an Elasticsearch MCP server with TypeScript

Creating an Elasticsearch MCP server with TypeScript

Learn how to create an Elasticsearch MCP server with TypeScript and Claude Desktop.

The shell tool is not a silver bullet for context engineering

March 25, 2026

The shell tool is not a silver bullet for context engineering

Learn what context-retrieval tools exist for context engineering, how they work, and their trade-offs.

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.

Try it yourself