Joe McElroy
Software Engineer at Elastic
Connect Agents to Elasticsearch with Model Context Protocol
Let’s use Model Context Protocol server to chat with your data in Elasticsearch.
Elastic MCP server: Expose Agent Builder tools to any AI agent
Discover how to use the built-in Elastic MCP server in Agent Builder to securely extend any AI agent with access to your private data and custom tools.
Connecting Elastic Agents to Gemini Enterprise via A2A protocol
Learn how to use Agent Builder to expose your custom Elastic Agent to external services like Gemini Enterprise with the A2A protocol.
LangChain and Elasticsearch: Building LangGraph retrieval agent template
Elasticsearch and LangChain collaborate on a new retrieval agent template for LangGraph for agentic apps
Playground: Experiment with RAG applications with Elasticsearch in minutes
Learn about Elastic's Playground and how to use it to experiment with RAG applications using Elasticsearch.
Retrieval Augmented Generation (RAG)
Learn about Retrieval Augmented Generation (RAG) and how it can help improve the quality of an LLM's generated responses by providing relevant source knowledge as context.
Playground: Experiment with RAG using Bedrock Anthropic Models and Elasticsearch in minutes
Explore Elastic's Playground and learn how to use it to experiment with RAG applications using Bedrock Anthropic Models & Elasticsearch.
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.