Using AI to read long documents, contracts, and PDFs — companion videos

Tiago Forte

NotebookLM is the AI tool the article most enthusiastically recommends for long documents, and Tiago Forte — the Building a Second Brain guy — gives the cleanest tour of why. He demonstrates summarising meeting notes, querying long PDFs, and the source-grounding feature that stops the model from inventing facts the documents don't contain. After watching, you'll understand why "upload the PDF to NotebookLM" is the article's default suggestion.

What you should get from this: You can set up a NotebookLM notebook and use it to summarise, question and cross-reference long documents from your own sources.

Watch or know first: None — watchable cold; have one long PDF of your own ready to try afterwards.

Grace Leung

A more practical two-tool workflow: Perplexity for finding the documents and citations, NotebookLM for actually reading and synthesising them. Useful if your "long document" problem is really a "long stack of documents" problem — market research, regulatory filings, multi-source reports.

What you should get from this: You can chain Perplexity and NotebookLM into one research pipeline that finds sources and then reads and synthesises them.

Watch or know first: Know your way around NotebookLM first — the primary pick covers that.