> For the complete documentation index, see [llms.txt](https://docs.calk-ai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.calk-ai.com/agents/what-is-rag-and-why-its-awesome.md).

# What is RAG? (And why it’s awesome)

Welcome to one of the brains behind Calk!\
Let’s break down **RAG** — in plain English.

***

### 🧩 RAG stands for "Retrieval-Augmented Generation"

It sounds fancy, but here’s the simple idea:

Imagine you’re asking ChatGPT a question. It tries to answer from what it already knows.

Now imagine if, before answering, it could **go look into your company’s Notion, Google Drive, or Slack**, find the exact info it needs — and **then answer** using that real information.

That’s RAG. 🧠🔍✍️

***

### 🧠 Why do you need RAG?

Here’s the thing:\
**AI models like GPT or Claude have a memory that doesn’t update.**\
They were trained months ago — so they don’t know:

* Your latest processes
* Your current clients
* What your team said in Slack last week

But your company moves fast.\
You write new docs, launch new features, and change how things work — sometimes every day.

**RAG lets your AI stay in sync.**

By connecting to your tools, it can:

* Retrieve your real, live knowledge
* Answer based on what’s true *right now*
* Keep learning without retraining the model

So your AI doesn’t guess — it **knows.**

***

### 🛠️ How does RAG work?

1. **You ask a question.**\
   → Like: “What’s our refund policy?”
2. **Calk searches your connected knowledge.**\
   → It looks through Notion pages, Google Docs, uploaded files, etc.
3. **It finds the most relevant info.**\
   → Like a sentence in your company handbook.
4. **Then it generates an answer using that info.**\
   → So it feels like it really understands your business.

That’s Retrieval-Augmented Generation:\
**It retrieves before it generates.**

***

### 🔗 How Calk uses RAG

Every time your agent answers with internal knowledge, RAG is doing the work in the background.

You don’t have to configure anything fancy:\
Just connect your tools → your agents become **faster, smarter, and always up to date.**

> Want to see it in action?\
> Check out the [Use Cases](/use-case.md) tab for real examples — from onboarding and customer support to async Q\&A and internal helpdesks.