December 1, 2025
Building a ChatGPT connector with Elasticsearch to query GitHub issues
Learn how to build a custom ChatGPT connector and deploy an Elasticsearch MCP server that uses hybrid search to query internal GitHub issues.


November 28, 2025
Developing an agentic RAG assistant using LangChain and Elasticsearch
Learn how to build an agentic rag news assistant using LangChain and Elasticsearch that answers queries about articles with adaptive routing.

November 26, 2025
Building an AI agent for HR with Elastic Agent Builder and GPT-OSS
Discover how to build an AI agent that can answer natural language queries about your employee HR data using Elastic Agent Builder and GPT-OSS.

November 25, 2025
Top Elastic Agent Builder projects and learnings from Cal Hacks 12.0
Explore the top Elastic Agent Builder projects from Cal Hacks 12.0 and dive into our technical takeaways on Serverless, ES|QL, and agent architectures.

November 24, 2025
Creating an LLM agent newsroom with A2A protocol and MCP in Elasticsearch: Part II
Discover how to build a specialized hybrid LLM agent newsroom using A2A Protocol for agent collaboration and MCP for tool access in Elasticsearch.

November 21, 2025
Getting started with Elastic Agent Builder and Microsoft Agent Framework
Walk through the complete process of creating an agent with Elastic Agent Builder and then explore how to use the agent via the A2A protocol orchestrated with the Microsoft Agent Framework.

November 20, 2025
You Know, for Context - Part III: The power of hybrid search in context engineering
Discover how to use context engineering and hybrid search to improve AI output accuracy with aggregations, RBAC, and non-content signals.

November 19, 2025
Implementing agentic search with observability to autotune relevance in Elasticsearch
Learn how to implement agentic search in Elasticsearch to automatically train a relevance model from logged user data.

November 18, 2025
You Know, for Context - Part II: Agentic AI and the need for context engineering
Learn how the evolution of LLMs towards agentic AI increases the need for context engineering to solve RAG context limits and memory management.