Revision Change Register (App Maxxing, early release)

EARLY RELEASE: PLEASE READ BEFORE BUYING

• This app needs your own OpenAI API key. It will not run without one, and a ChatGPT subscription does not include one.
• It is an early release that still needs further testing. So far each app has passed our own offline tests, and has been run on its built-in sample against the live service on both models (October 2026). It has not yet been tried on a wide range of real files of different kinds and sizes. You may meet faults.
• Please tell us what you find after you buy: email kit376351@gmail.com with the subject "Maxxing feedback". Every report is read, and fixes are sent to buyers free.
• If we cannot get it running for you, email us within 14 days for a refund of the app price.

Compare two revisions of your own document. The app finds the differences in the text itself; the model only describes them.

WHAT IT DOES

Add the old and the new revision of a document of your own: a test procedure, a design note, a specification you wrote. The app compares the two on your computer, before anything is sent: every passage that was added, removed, reworded or moved, and inside each changed passage every changed number with its old value, its new value and the percentage, every changed unit (converted by the app, so you can see whether 6 bar to 0.6 MPa is the same quantity), and every changed requirement word such as 'shall' to 'should'. A step that only got a new clause number because an earlier step was deleted is listed as 'renumbered only'. Each difference gets an ID. Your two files stay on your computer: only the changed passages are sent, each with its ID and one line of what stands before it (if most of the document changed, most of it is sent), and the button 'See exactly what will be sent' shows every word. The model writes, for each ID, what changed in plain words, why it might matter and who should look. It cannot add a change the app did not find, and it cannot drop one: a note for an unknown ID is thrown away, and a difference with no note still appears, marked 'no description'. You get the count first ('the app found 23 differences; all 23 are in the register'), the changed numbers on top, the register with removed words struck out and added words underlined, an Excel file with empty columns for your own review, and a Word file. For educational purposes only.

HOW IT IS BUILT

• The app's own code does the finding, the arithmetic and the unit conversions. The AI is used only for what code cannot do, and what it says is checked against your file.
• Anything the app cannot find in your file is marked "not found in the file", not trusted.
• The cost is shown before each run and after it, with a limit you set for one run.
• No verdicts: the app never says pass, fail or compliant. It shows you what it found and where.

WHAT YOU NEED

• Windows, Mac or Linux, and free Node.js 18 or newer
• Your own OpenAI account with API access and a key (platform.openai.com). This is separate from a ChatGPT subscription.
• You pay OpenAI for what you use, on top of the price of the app. In our own tests on a short sample file, a run of this app cost about 11 cents. Longer files cost more.
• The app uses OpenAI's GPT-6 Astra model. In Settings you can switch to a cheaper model at about a fifth of the price.
• About ten minutes of setup. A step-by-step guide is included.

HONEST LIMITS

The app compares wording, not meaning: the descriptions and 'why it might matter' are the model's suggestions, written from the changed passages alone, and they can be wrong. A document that was heavily re-ordered or re-numbered confuses the comparison, and the register gets long. Scans and pictures of documents cannot be compared: a PDF needs a text layer (one whose text you can select and copy). Pictures, drawings, text inside images, page headers and footers, footnotes, comments and formatting are not compared. A Word file is read as if every tracked change had been accepted. Differences only in capital letters, spacing, the kind of quote mark or the kind of dash are not reported. A number written in words is not seen as a number, and a unit is read only when it is written straight after its number. PDF text is cut into sentences, and tables in a PDF may come out as one long passage. One run describes up to 600 differences; the register still lists every one. Published standards are not an input: use your own documents. The app gives no opinion on what a change means for a contract, and no opinion on whether a change is right or allowed.

For educational purposes only, and for your own research and your own documents. The app points things out for you to check: it does not certify, approve or sign off anything, what the AI writes can be wrong, and it is not a substitute for review by a qualified person. You are asked to accept this when you first open the app.

PRIVACY

The app runs on your computer. It says before each run exactly what will be sent to OpenAI, under OpenAI's terms, and what stays on your computer; nothing is sent to us. Use it only with documents you are allowed to send to an AI service: not an employer's or customer's confidential documents, not export-controlled material, and not someone else's unpublished work. Your key is stored only on your computer and is sent only to OpenAI.

WHAT IS INCLUDED

The app (a zip file), start files for Windows, Mac and Linux, a sample to try, a setup guide and a README. Kitson Workshop is not affiliated with or endorsed by OpenAI.

REFUNDS

Digital download. If we cannot get it running for you, email kit376351@gmail.com within 14 days for a refund of the app price. Credit you bought from OpenAI is theirs to refund or not.

FEEDBACK AND IDEAS

Email kit376351@gmail.com with the subject "Maxxing feedback" to report a fault or tell us what worked. For a new app idea, use the subject "Kitson idea".