One of our CAISA participants recently asked a great question about Retrieval Augmented Generation (RAG). I promised to look into it, and I realized that we’ve already applied RAG in one of our ongoing projects!

What is RAG?

RAG, or Retrieval Augmented Generation, is a powerful hybrid model that merges the best of two worlds: retrieval-based systems and generative models. In RAG, the system first retrieves relevant information from a knowledge base, and then uses this data to generate more accurate and contextually relevant responses. This allows the system to provide fact-based, enriched answers that go beyond standard generative models, which rely only on their training data.

How Are We Using RAG?

We are developing a Knowledge Agent that taps into the wealth of information from the Business Excellence library on our forum (https://www.benchmarksixsigma.com/forum/business-excellence-dictionary-glossary/). This agent retrieves data from the best, most relevant answers available on the forum, and then augments that information to deliver responses. Essentially, this mirrors the essence of RAG in action by providing knowledge-driven outputs.

Work in Progress: Excellence Navigator

Although this agent is still a work in progress, you can try it out here: https://www.benchmarksixsigma.com/excellence-navigator/. Please note that some of your questions may return messages like, "Unable to browse the internet," especially when the agent identifies that the topic isn’t yet covered in our knowledge base. We are progressively improving the agent by adding more topics over time to expand its capability.

This project showcases our practical use of RAG, and we are excited to refine it as we move forward!

🚀 Update: The Excellence Navigator Agent is now ready!
What started as a work-in-progress has matured into a functional RAG-powered Knowledge Agent. It now retrieves insights directly from our Business Excellence Library and delivers enriched, contextually relevant answers.

✅ Try it out here: Excellence Navigator
We’ll continue expanding its coverage, but it’s already a practical demonstration of how CAISA participants learn to design working AI solutions.