May 26, 2026
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.
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.
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.
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.
March 27, 2026
Creating an Elasticsearch MCP server with TypeScript
Learn how to create an Elasticsearch MCP server with TypeScript and Claude Desktop.
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.
March 23, 2026
Using Elasticsearch Inference API along with Hugging Face models
Learn how to connect Elasticsearch to Hugging Face models using inference endpoints, and build a multilingual blog recommendation system with semantic search and chat completions.
March 18, 2026
AI agent memory: Creating smart agents with Elasticsearch managed memory
Learn how to create smarter and more efficient AI agents by managing memory using Elasticsearch.
March 17, 2026
The Gemini CLI extension for Elasticsearch with tools and skills
Introducing Elastic’s extension for Google's Gemini CLI to search, retrieve, and analyze Elasticsearch data in developer and agentic workflows.