---
title: "Comment by Julian Neagu on \"RAG Is the Easy Part: Designing AI Systems Around Messy Enterprise Data\" | Hashnode"
description: "The part about RAG being a search problem, not just a vector DB problem, hits home. Exact IDs and dates can matter more than semantic similarity. Learned this t"
url: "https://hashnode.com/posts/rag-is-the-easy-part-designing-ai-systems-around-messy-enterprise-data/6aab1e04da7e08af2521b9c6/comment/6aad00e5a37ba2a7715442d7"
---

[Discussion](https://hashnode.com/posts/rag-is-the-easy-part-designing-ai-systems-around-messy-enterprise-data/6aab1e04da7e08af2521b9c6)

Comment [RAG Is the Easy Part: Designing AI Systems Around Messy Enterprise Data](https://hashnode.com/posts/rag-is-the-easy-part-designing-ai-systems-around-messy-enterprise-data/6aab1e04da7e08af2521b9c6)

[Julian Neagu](https://hashnode.com/@julianneagulab)

[Sep 18](https://hashnode.com/posts/rag-is-the-easy-part-designing-ai-systems-around-messy-enterprise-data/6aab1e04da7e08af2521b9c6/comment/6aad00e5a37ba2a7715442d7)

The part about RAG being a search problem, not just a vector DB problem, hits home. Exact IDs and dates can matter more than semantic similarity. Learned this the hard way.
