Explained Simply
Thirteen short, illustrated guides that explain how AI works, what happens to personal information, how finance teams keep the numbers exact, what separates information from expertise, and how the Document Substrate puts it all to work.
The collection
Six guides cover how AI actually behaves, what that means for personal details and for money work, and the words we use for knowing things:
- How an AI chat really works — five ideas that explain almost everything: messages, tokens, the context window, tools, and agents. Learn these and the model stops being magic and starts being a tool with knowable limits.
- How an AI finds the right page — answering from your own documents: two kinds of search, a filing system for meaning, the merge that combines them, and the loop that turns it into a chat.
- How an AI is told what to do — prompts, skills and tools: the note that says how to behave, the recipes it opens when a job calls for them, the hands it borrows to act, and which to reach for.
- Personal information and the cloud AI — what counts as a personal detail, where it goes wrong, and the two protections people constantly mix up: a disguise and a promise. You want both, for different reasons.
- Finance and the dice-rolling AI — why a model that gives different answers to the same question can still be trusted with money work: where the errors come from, and the checks that keep the numbers exact.
- From information to expertise — five words people mix up: information, knowledge, intelligence, judgment and expertise. What each one is, how they differ, and how they build on each other.
Seven more cover the Document Substrate — those ideas put to work on real client documents:
- How Document Substrate works — the whole trip in eight pictures, upload to finished workpaper.
- How it's put together — the pieces, the three shelves of memory, and a question's journey through them.
- How privacy works — the promise, the three nets, the vault, and the three places where real details do travel.
- Teaching it a new job — what it takes to add a new checking job to the system.
- How answers stay good — the quality loop and the exam books that keep the output honest as the system changes.
- Teaching the system without a developer — building a check from a sentence, teaching it a new document type, the record of decisions, and what runs on its own.
- Six stages, from preparer to adviser — how staff in an accounting practice move from typing figures to reviewing and advising, and what the Document Substrate takes over at each stage.
Every section has an Under the hood box, collapsed by default, with the technical version: the table names, the model calls, the actual guarantees.
Each guide stands on its own, so you can start anywhere — though if AI is still largely magic to you, start with how an AI chat really works and the rest reads easily.