Long Report Consistency Checker (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.

Look for the places where your own long report does not agree with itself: a value given two ways, a table that does not add up, a reference to a table that is not there.

WHAT IT DOES

Add your own report as a Word file, a PDF with a text layer (one whose text you can select and copy), or text. Before the model is asked anything, the app reads the report on your computer. It finds, in code: One wording given two values in different places (the summary, the text, the conclusions), with units converted, so that 2.5 kN and 2500 N count as the same and so do 2.5 and 2.50. Two units side by side that do not agree, such as 25 mm (1.2 in). A figure in a sentence that points to a table or a figure caption and is not there. Totals and percentages in a table that do not add up. A reference to a table, figure, equation, section or appendix that is not in the file, and ones that are numbered and never referred to. Gaps and repeats in the numbering. An abbreviation that is never spelled out, used before it is spelled out, spelled out twice, or spelled out and never used. One unit written in more than one way, such as mm and millimetres, which is listed as style and not as a disagreement. The model then reads the report for what code cannot judge: two differently worded passages that describe the same thing and seem not to agree, a name or a date written two ways, a conclusion that states a figure or a scope its results passage does not state. The app looks both passages of every such remark up in your file, says where they are, and compares the figures in them itself. Each remark by the model is marked 'worth a look' and nothing stronger. You get a count of what was checked and what was not, the two passages of every finding side by side with the page or section of each, a Word report and an Excel 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 8 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 finds disagreements and cannot tell which place is right. It compares a value with another only when both are given in the same words, so the same quantity described in different words is left to the model, whose remarks are a reading and not a check. Tables are read from Word files; in a PDF the app cannot tell which figures stand in one row, so table totals are checked only in Word files and in text with tabs or bars. Text in pictures, charts and text boxes, and equations set with the equation editor, are not in the text of the file and are not read. An abbreviation that is also an ordinary name or a part number may be listed although it needs no spelling out. Numbers written as words, and numbers with a decimal comma, are not compared. A long report costs more: the spending limit for one run is set to $5.00, the price for a run doubles above about 210 PDF pages, and the app is best used on up to about 190 pages at a time. A blank findings list does not mean the document is correct. Use it on your own report only, never on one you are reviewing or marking for someone else, and follow the rules of your employer, journal or funder on the use of AI.

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".