The safest way to organize notes with AI is to let it change how a note is written and never what it says. MindMax quick notes work that way: every typo, misheard word and broken sentence is corrected, the thought is filed under the right heading, and nothing you did not say is added — no facts, no conclusions, no firmer wording than yours.

That sounds like a small distinction. It is the whole difference between a note you can trust next month and a note you have to re-check.

To have AI edit a Word document with tracked changes, the AI has to change the .docx itself instead of handing back rewritten text. In MindMax you @ the file, describe the change once, review the edits in groups, and the ones you accept are written into the same file as Word tracked changes — styles, numbering and headers untouched.

That sounds like a small detail. It is the whole difference between an edit you can send to a client and an afternoon spent rebuilding a document that used to be fine.

To review a Word document with AI and send back real comments, the AI has to anchor each comment to the words it is about, and you have to be the one who decides what is sent. In MindMax you say what the review is for, adopt the drafted comments you agree with in your own words, and export them into a copy of the .docx as ordinary Word comments.

The point of a review is not the opinion. It is an opinion the author can act on, on the sentence it is about, in the file they already work in.

To ask AI a real question about a whole book — where the argument turns, what the author walks back, whether chapter nine contradicts chapter two — the AI has to read the book the way you would: look at the table of contents, decide which chapters the question needs, read those in full, and go back for another if the first did not settle it. Pasting the whole book in and searching chopped-up fragments both fail at exactly these questions.

Every AI reading tool has to decide what happens when the material is longer than the model can handle well. That decision is invisible in the answer, and it determines whether the answer can be trusted.

MindMax itself is free to use: reading, writing, searching and keeping your files in your own folder cost nothing, and the only thing you pay for is AI work, either through a subscription or with your own API key. Opening a PDF, highlighting, searching your folder, editing a note and exporting to Word never spend credits. Asking, explaining, annotating, translating, recognising a scan or transcribing your voice is AI work, and does.

That line is deliberate, and this post explains where it sits and why — because "free tier" in most software means "a demo that runs out on day two", and that is not what we mean.

A decision matrix is a table with your options down the side and your criteria across the top; you score every option on every criterion, optionally weight the criteria, and compare. Its value is less the final total than the discipline: every option is judged on the same ruler, and the criterion you were quietly ignoring becomes a column you have to fill in.

The last post in Thinking models in practice, a short series on classic methods and how to run them on your own material.

Checking that an AI's quote really appears in a PDF sounds like pressing Ctrl+F. In practice the text inside a PDF is not the text you see: words are hyphenated across lines, paragraphs are split by page breaks and running headers, and letter pairs like "fi" are stored as single symbols. A quote check that ignores this either rejects real quotes or accepts paraphrases. Getting it right is most of the work.

We said every quote in MindMax is checked against the source. This post is about why that sentence hides more than it shows — and what you should expect from any tool that claims the same.

Six thinking hats is a method for looking at one question from six angles, one at a time: white for facts, red for feelings and instinct, black for risks, yellow for value, green for new ideas and blue for managing the process and deciding the next move. Its point is separation — not arguing optimism against caution in the same breath.

Part of Thinking models in practice, a short series on classic methods and how to run them on your own material.

To write a thesis chapter with AI without losing the argument, settle the thesis and outline yourself before any prose is drafted, write from your own sources rather than the model's memory, keep a running record of what the draft has already argued, defined and promised, and review every AI change as a marked edit. Also: check your institution's rules on AI use before you start, not after.

The usual approach — ask a chat assistant for one section at a time — produces sections that are each fine and a chapter that does not hold together.

To answer an RFP, tender or security questionnaire with AI, give it the questionnaire as the structure and your current policies as the only source, require a quote from a named document under every answer, and check every answer that states a number, date, certification or promise. Treat any answer without a quote as a question for a colleague, not a draft to send.

Drafting is the easy part now. The expensive mistakes are elsewhere.