📖 Building your own RAG system is like deciding to build your own email server in 2024. Sure, you c

written by Stefan Christoph

- 2 minutes read

📖 “Building your own RAG system is like deciding to build your own email server in 2024. Sure, you could do it. But why would you want to?” - Alden Do Rosario in his article “Dear IT Departments, Please Stop Trying To Build Your Own RAG” (https://pub.towardsai.net/dear-it-departments-please-stop-trying-to-build-your-own-rag-4546b4638273) on medium. Love it. Highly recommended read.

🎡 Don’t reinvent the wheel! The trap of building something, which on the first glance looks so simple, but then we you get into it you discover layers of hidden complexity.

📝 RAG is powerful — it grounds model answers in your own documents — and it’s the architecture style I see behind many of today’s GenAI applications. If you are on the hunt for a good foundation to build your RAG-based application on, I can suggest to have a look at Amazon Bedrock Knowledge Bases or Amazon Q Business — an AWS starting point (I work there), and which one fits really depends on your requirements: how much control you need over retrieval, security, operations, and cost. How many dials do you need?

🤿 If you want to dive deeper - have a look into this year’s re:invent sessions:

👷‍♀️ Just to give you a starting point. What are you going to build?

#aws #reinvent #genai #rag

📝 Last updated: August 13, 2026 — Technical corrections from a quality audit