Blogs
Insights de desenvolvedores e artigos práticos dos nossos experts para inspirar e fortalecer suas buscas
Building human-in-the-loop (HITL) AI agents with LangGraph and Elasticsearch
Learn what human-in-the-loop (HITL) is and how to build an HITL system with LangGraph and Elasticsearch for a flight system.
Apache Lucene 2025 wrap-up
2025 was a stellar year for Apache Lucene; here are our highlights.
Using Discord and Elastic Agent Builder A2A to build a gaming community support bot
Learn how to connect Discord to Elastic Agent Builder's Agent-to-Agent (A2A) server to create a gaming community support bot.
All about those chunks, ’bout those chunks, and snippets!
Exploring chunking and snippet extraction for LLMs, highlighting enhancements for identifying the most relevant chunks and snippets to send to models such as rerankers and LLMs.
Improve search performance with `best_compression`
While `best_compression` is typically seen as a storage-saving feature for Elastic Observability and Elastic Security use cases, this blog demonstrates its effectiveness as a performance-tuning lever for search.
Agent Builder, beyond the chatbox: Introducing Augmented Infrastructure
Learn about Elastic Agent Builder with Augmented Infrastructure, an AI agent that enables augmented operations, augmented development, and augmented synthetics.
Agent Builder now GA: Ship context-driven agents in minutes
Agent Builder is now GA. Learn how it allows you to quickly develop context-driven AI agents.
Building voice agents with Elastic Agent Builder
Exploring how voice agents work and how to build one using Elastic Agent Builder and LiveKit.
Monitoring LLM inference and Agent Builder with OpenRouter
Learn how to monitor LLM usage, costs, and performance across Agent Builder and inference pipelines using OpenRouter's OpenTelemetry broadcast and Elastic APM.
Context engineering vs. prompt engineering
Learn how context engineering and prompt engineering differ and why mastering both is essential for building production AI agents and RAG systems.
Faster ES|QL stats with Swiss-style hash tables
How Swiss-inspired hashing and SIMD-friendly design deliver consistent, measurable speedups in Elasticsearch Query Language (ES|QL).
Managing agentic memory with Elasticsearch
Creating more context-aware and efficient agents by managing memories using Elasticsearch.