Documents &amp; PDFs

Drop in a 40-page document and get the parts that matter — the decisions, the risks, the things you would otherwise miss. A practical workflow for using AI to read what you do not have time to read.

Using AI to read long documents, contracts, and PDFs

Understand the idea well enough to try it safely in a low-risk setting.

New to AI

8 min read

Google's NotebookLM is the easiest way to chat with your own documents — books, papers, meeting notes, research files. A practical tour of what it does, where it shines, and the four use cases worth setting up this week.

NotebookLM: turn any source into a personal knowledge base

Turn the workflow into a small practical experiment with a clear quality check.

Beginner

10 min read

Build your own document-grounded chat in under an hour, with no code. The three no-code options worth using in 2026, the tradeoffs, and the patterns that distinguish a useful RAG from a frustrating one.

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

Build a document-grounded assistant and know when stale, low-quality, or out-of-scope sources make answers unsafe.

IBM Technology. Explains the ingestion side of RAG and agents: preparing PDFs and other files so document structure, tables and layout survive into downstream retrieval. That supports the article's warning that RAG quality and safety begin before embedding, especially when parsing complex business documents.

Unlock Better RAG & AI Agents with Docling

20 minutes

Paragon. Walks through the production RAG permission problem and compares tool-calling, namespaces, ACL tables and relationship-based permissions. That directly supports the article's core rule: retrieval must only return sources the current user is allowed to see, and source-system permissions cannot be treated as an afterthought.

Permissions & Access Control for RAG - a Deep Dive Tutorial

11 min read

RAG quality starts before retrieval. A secure ingestion guide for PDFs, OCR, metadata, permissions, source freshness, deletion, malware risk, and operational ownership.

Secure document ingestion for RAG: PDFs, OCR, metadata, and retention

Design a secure document-ingestion pipeline for RAG with permission metadata, OCR quality checks, source freshness, retention rules, deletion behavior, and ingestion tests.

10 min read

A company knowledge assistant is only safe if retrieval respects permissions. How to design RAG source boundaries, ACL filtering, document ownership, logging, stale-source handling, and refusal behavior.

Company knowledge RAG: permissions, leakage, and source boundaries

Design a company knowledge RAG with permission-aware retrieval, source ownership, leakage controls, and refusal behavior.

12 min read

A production RAG pipeline is six stages, each with specific patterns that determine quality. The architecture, the choices at each stage, and the iterative evaluation discipline that distinguishes RAG that works from RAG that disappoints.

Building a production RAG: ingestion, embedding, retrieval, reranking, eval

Evaluate the implementation pattern, failure modes, and guardrails before building.

11 min read

Most RAG implementations work poorly because they get three things wrong. A practical guide to chunking documents, reranking results, and combining keyword with semantic search — without becoming a search engineer.

Chunking, reranking, and hybrid search: make RAG actually work

Evaluate the implementation pattern, failure modes, and guardrails before building.

17 minutes

AI Engineer. Douwe Kiela led the original RAG paper at FAIR and now ships RAG into regulated enterprises. The talk is mostly about what stops working at scale — chunking strategies that don't survive 100k documents, "accuracy is table stakes, inaccuracy is the real problem," and why attribution and observability matter more than the embedding model. Good calibration before re-reading the article's eval and monitoring sections.

RAG Agents in Prod: 10 Lessons We Learned — Douwe Kiela, creator of RAG

19 minutes

AI Engineer. LlamaIndex's CEO walking the gap between "naive RAG demo" and a real pipeline — small-to-big retrieval, sub-question routing, hybrid search, evaluation. The shape of his slides maps almost directly onto the article's pipeline sections; watch first, then re-read the article with his diagrams in your head.

Building Production-Ready RAG Applications: Jerry Liu

69 minutes

Greg Kamradt. The article spends a lot of words on chunking; this is the longest, most patient explanation of what each chunking strategy is actually doing — from character-recursive through document-aware to semantic and agentic splitting. Pair it with Greg's free ChunkViz tool to build intuition before you start tuning.

The 5 Levels Of Text Splitting For Retrieval

24 minutes

AI Jason. Covers the exact stack the article argues for — query translation, hybrid retrieval, reranking, and a corrective-RAG loop — in one runnable build. Useful as a working mental model for what the chunk → rerank → answer pipeline looks like when it's actually doing its job.

"I want Llama3 to perform 10x with my private knowledge" - Local Agentic RAG w/ llama3

11 minutes

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.

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

26 minutes

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.

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

28 minutes

Matt Wolfe. Once you understand the basics, this is the right second video. Matt runs through a long list of less obvious uses — turning a book into a study guide, briefing yourself on a competitor from their content, generating mind maps from a folder of PDFs — that help you see how flexible the "grounded notebook" frame actually is.

35+ INSANE Ways To Use NotebookLM (For FREE)

Beginner

35 minutes

Paul J Lipsky. A clean three-step framing — curate sources, ask the right questions, produce final outputs — that maps almost one-to-one onto how the article tells you to think about NotebookLM. Recent enough (early 2026) to match the current UI, including Studio, audio overviews, and mind maps.

How To Master NotebookLM in 2026 (Free Course)

Beginner

18 minutes

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.

This NotebookLM + Perplexity Workflow Will Cut Your Research Time by 50% (or More)

New to AI

26 minutes