What Is RAG? – free checklist (episode 16)

Why it matters

RAG means the AI looks up the right pages in your documents first, then answers using them. Like a librarian who fetches the right page before the AI answers.

The 5 questions

0 of 5 done

Does it look up first?RAG adds relevant text the AI was never taught to your question before it answers.Try: Ask: "Do you answer from my documents, or from memory?"
Which page was it?A RAG answer can include citations (a note saying which page it used). Ask for them.Try: "Which page did that come from?"
Is the library current?The AI can only find what is in the library. Old documents give old answers.General good practice.
Open the page yourselfRAG can reduce wrong answers, but it may not remove them all. Check the cited page.General good practice.
Who may read what?Private documents need rules about who is allowed to open which file, so people only get answers from files they are allowed to see.

Tap a step when you have done it. Your ticks stay on this device.

Rule of thumb

look it up first, then answer. Then check the page.

Sources: AWS, "What is RAG?" (aws.amazon.com/what-is/retrieval-augmented-generation); Microsoft Learn, "RAG and Generative AI - Azure AI Search"; Lewis et al., 2020, "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" (arXiv 2005.11401). The librarian comparison and steps 3 and 4 are our own general good practice.

Episode 16: Is your AI looking it up first?

Why it matters

The 5 questions

The AI Words Map

More like this

A new free sheet every week