I’m currently building a RAG system for an e-commerce company, basically giving an AI assistant a...I’m currently building a RAG system for an e-commerce company, basically giving an AI assistant a...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
I’m currently building a RAG system for an e-commerce company, basically giving an AI assistant access to the company’s own knowledge and product information so it can give useful, context-aware responses instead of just generating random answers.
The interesting part isn’t just connecting an LLM.
It’s making sure the AI can:
→ Find the right information
→ Understand the user’s question
→ Retrieve relevant context
→ Give an accurate response
→ Actually be useful in a real business workflow
Still working on it, but I’m excited about where it’s going.
This is the kind of AI automation I enjoy building, systems that solve actual business problems, not just AI demos.
Building something similar? Let’s talk.
Post image
Ibrahim's avatar
I’ve built something similar for Purchaser, an e-commerce marketplace for automotive and industrial products.
I built a RAG-powered AI agent inside Slack that gives the team access to Purchaser’s product and spare-parts database. Instead of opening Excel and manually searching...
Paul 's avatar
Using Slack as the interface is a really cool way to make the RAG actually useful for the team.
Ibrahim's avatar
Thanks, Paul! 🙌 Exactly—that was the goal: make the RAG system something the team can actually use within their existing workflow instead of adding another tool. Slack made it much more practical.
Andreas's avatar
One thing that will save you a lot of time: build a small evaluation set early — 50–100 real questions with the document or product that should be retrieved for each. Before tuning prompts, measure retrieval quality (does the right doc surface in the top 3?) with it. Chunk size...
Paul 's avatar
Yeah, absolutely. I agree with this. I’ve been testing the RAG with a small set of real e-commerce questions first, so I can see where the retrieval is strong and where it needs improvement. I’ll definitely add an evaluation set and measure retrieval quality before tuning the...
Back to feed
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started