AI Engineering
Building AI That Knows Your Data
RAG From Scratch · Volume I · Foundations
Your company’s answers are already written down. This book builds the machine that finds them.
On a Tuesday morning in March, the chief executive of Northwind Industries asked a simple question: have we ever agreed to a liability cap below one million dollars? The answer existed. It was written down, signed, and filed. Finding it took three days, and not finding it in time cost forty thousand dollars.
Every organization has a version of that Tuesday. The knowledge is real, it survived, and it is spread across a million files in a hundred formats, organized by whoever was closest to the filing cabinet that day. An organization knows more than anyone in it. That is the problem this series exists to solve.
Building AI That Knows Your Data teaches you to build Retrieval-Augmented Generation the way it should be learned: from scratch, from the documents up, with no magic imports doing the thinking for you. You will build a working system for Northwind, a fictional 240-person manufacturer with thirty years of documents and no way to search them, one chapter at a time, alongside a cast you will come to know by instinct: the CEO with the only acceptance test that matters, the operations manager who has been the company’s search engine for twenty years, the IT lead who builds the machine, and the in-house lawyer who trusts nothing until it shows its sources, and is right to.
Volume I builds the offline half: everything that happens to documents before anyone asks a question. You will crack open PDFs, Word files, spreadsheets, emails, and one scanned contract from 1994 that behaves like a sealed envelope. You will clean what you extracted, cut it into pieces a search engine can love, turn text into searchable meaning, and store a million vectors somewhere sensible. By the final chapter, a question in plain English finds the right passage across formats, vocabularies, and decades, with a score, a label, and a page number.
What you need: a computer that can run Python. No GPU, no cloud account, no budget. Every model in this volume is small, free, and runs locally, which is not a compromise but a lesson: the first serious question in enterprise AI is where your data is allowed to go, and this book’s answer, for the pilot, is nowhere.
Volume I is the foundation. The story continues in Volume II, where the front desk opens and the system finally answers.
About the Author
JC Marin
JC Marin is an AI infrastructure engineer who builds AI systems in the one kind of environment where “move fast and break things” is not on the menu: high-security enterprise networks where every deployment must answer for where the data goes.
As an AI subject matter expert at a major aerospace and defense company, he architected a multi-agent AI platform for an air-gapped classified network, including large-model serving, request routing, and per-user vector memory, along with the tiered, read-only-first safety strategy required to introduce agentic AI into that environment responsibly. The questions this book treats as drama, citations, provenance, superseded documents, and data that never leaves the building, are the questions he answers professionally.
He also runs an independent AI solutions practice, delivering AI systems, workflow automation, and web infrastructure to small businesses, and operates a self-hosted multi-GPU inference environment serving open-weight models with long-context workloads, the same build-it-yourself-first philosophy this series teaches. His foundation is a decade of hardened Windows, virtualization, and network administration in high-security settings, with certifications spanning security and infrastructure operations.
He is based in Melbourne, Florida. Building AI That Knows Your Data is his first technical book series.