Tag
Elasticsearch blog post describes building a persistent agent memory layer with three memory types (episodic, semantic, procedural), achieving 0.89 recall on a QA eval with zero tenant leaks using hybrid recall and DLS isolation.
A workshop/tutorial on agentic search techniques for context engineering, teaching how AI agents decide what context to retrieve from files, databases, memory, and the web using langchain and Elasticsearch.
The article argues against overusing vector search, highlighting BM25's effectiveness for exact keyword matching and its role in hybrid search systems.