Companion videos

Build a personal RAG: chat with your own documents (no code) — companion videos

The fastest way into RAG without writing code is to upload a stack of your own documents into NotebookLM, Claude Projects, or ChatGPT Projects and start asking real questions. These videos give you the cleanest walkthroughs — the first from the author of *Building a Second Brain*, the second a tighter feature-by-feature tour for when you want the audio overview, study guide and briefing-doc patterns shown one after the other.

Primary pick

25:49

How to Use NotebookLM (Google's AI "Tool for Understanding")

Tiago Forte

Tiago is the *Building a Second Brain* author and treats NotebookLM as exactly what the article describes — a personal RAG over your own notes, PDFs and clippings. He shows the citation-grounded chat, the limits of the tool, and how it fits next to a Readwise/Obsidian workflow, which is the natural endpoint for most readers of the article.

What you should get from this: Understand the personal source-grounded workflow: collect documents, ask bounded questions, and verify citations before trusting the answer.

Watch or know first: Have a small set of notes, PDFs or transcripts you are allowed to upload to a third-party tool.

AI Expert note: The durable lesson is source grounding, not the exact NotebookLM interface. Re-check current sharing, retention and source limits before using this with workplace or client documents.

Open video page

Also worth watching

11:10

How To Use NotebookLM For Beginners In 2024 (NotebookLM Tutorial)

TheAIGRID

A faster, feature-first tour: uploading mixed sources (PDFs, YouTube transcripts, blog posts), generating a briefing doc, focusing the chat on a single source, and the audio-overview podcast. Good if you want a quick map of the surface area before committing time to a longer walkthrough.

What you should get from this: See the basic NotebookLM source-grounded workflow before building a personal document assistant.

Watch or know first: Understand that NotebookLM answers from uploaded sources rather than from a general company knowledge base.

AI Expert note: This is a 2024 beginner tour, so the UI and feature set are dated. Keep it only for the grounding pattern: collect sources, ask source-bound questions, then verify citations.

Open video page