← Back to the blog
AI 18 Apr 2026 · 7 min read

RAG on your intranet: when it’s worth it (and when it isn’t)

Not every AI problem in an SME is solved with RAG. A practical guide to deciding before you spend 6 months building it.

NS
Nico Sherpa
K2 Labs team
X LI

Over the last 18 months, almost every discovery meeting we start with an SME ends with the same sentence: "we want a ChatGPT, but with our documents". The market’s answer to this is always the same — RAG (Retrieval-Augmented Generation). And sometimes it’s the right answer. Other times, it will take you 6 months to find out it wasn’t.

This post captures the framework we use at K2 Labs to decide, in less than a week of work, whether a RAG project will work for a specific client. It isn’t definitive. But it has saved us from three commitments that would have been catastrophic.

What is RAG, in plain terms?

RAG is the pattern "find relevant documents, feed those documents to the model, and have it answer using that information". It’s the difference between asking a model something cold and giving it top-k fragments of context before the question.

Mechanically, it’s three pieces:

In 2026, wiring this up with LangChain or llama-index is a Friday afternoon. What’s hard is making it answer well.

When it DOES make sense

RAG’s sweet spot is fairly specific. It works very well when:

A real case: an industrial distributor with 4,000 technical datasheets in PDF. Call-centre technicians spent 40% of their time searching for specifications. RAG cut that figure to 8%, with a clear ROI in 3 months. Here, every box was ticked.

When it does NOT

And here comes the nuance that’s rarely discussed. RAG is a bad idea when:

If the problem is solved by full-text search + an LLM at the end, you don’t need RAG. You need Elasticsearch and a prompt.

The decision framework in 5 questions

In the first meeting, we run this battery. If three or more answers are "no", we recommend a different approach.

Closing

RAG is not a silver bullet, but it’s not a failure either. It’s a specific architecture for a specific problem. The hard part of a consultant’s job in 2026 is no longer building the pipeline — it’s having the honest conversation about whether your problem fits.

If you’re considering a project like this and want a second opinion before committing, write to us. One hour of discovery can save you a semester.

NS
About the author

Nico Sherpa

One of K2 Labs' digital sherpas. We write about how we build software with AI — no hype.

Will you let sherpasguide you?

One hour of discovery can save you a semester. Let’s talk.