Category: AI
Articles tagged AI
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.
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.
Automating log parsing in Streams with ML
Learn how a hybrid ML approach achieved 94% log parsing and 91% log partitioning accuracy through automation experiments with log format fingerprinting in Streams.
How to build an agent knowledge base with LangChain and Elasticsearch
Learn how to build an agent knowledge base and test its ability to query sources of information based on context, use WebSearch for out-of-scope queries, and refine recommendations based on user intention.
Creating reliable agents with structured outputs in Elasticsearch
Explore what structured outputs are and how to leverage them in Elasticsearch to ground agents in the most relevant context for data contracts.
Getting started with Elastic Agent Builder and Strands Agents SDK
Learn how to create an agent with Elastic Agent Builder and then explore how to use the agent via the A2A protocol orchestrated with the Strands Agents SDK.
Build a financial AI search workflow using LangGraph.js and Elasticsearch
Learn how to use LangGraph.js with Elasticsearch to build an AI-powered financial search workflow that turns natural language queries into dynamic, conditional filters for investment and market analysis.
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.
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.
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.
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.
