---
title: "Comment by Ahmet Özel on \"Productionizing RAG: Building a Scalable AI Teaching Assistant\" | Hashnode"
description: "The 200-concurrent-query claim is the next place I would put measurement detail beside the 40% average latency reduction. Concurrent users, requests in flight a"
url: "https://hashnode.com/posts/productionizing-rag-building-a-scalable-ai-teaching-assistant/6ac0d039532ad5f6d2983f93/comment/6ac2923a5e424f7fa8a6461f"
---

[Discussion](https://hashnode.com/posts/productionizing-rag-building-a-scalable-ai-teaching-assistant/6ac0d039532ad5f6d2983f93)

Comment [Productionizing RAG: Building a Scalable AI Teaching Assistant](https://hashnode.com/posts/productionizing-rag-building-a-scalable-ai-teaching-assistant/6ac0d039532ad5f6d2983f93)

[Ahmet Özel](https://hashnode.com/@ahmetozel)

[Oct 4](https://hashnode.com/posts/productionizing-rag-building-a-scalable-ai-teaching-assistant/6ac0d039532ad5f6d2983f93/comment/6ac2923a5e424f7fa8a6461f)

The 200-concurrent-query claim is the next place I would put measurement detail beside the 40% average latency reduction. Concurrent users, requests in flight and sustained completed requests per second describe different loads, especially with a hosted model behind the application.

A useful test would ramp query arrivals while ingestion is running, then report throughput, queue wait, tail latency and timed-out requests. Include both short definition questions and longer walkthroughs. That would show whether asynchronous ingestion protects query service under contention, rather than merely making the upload interface nonblocking.