Data Sheet Comparer (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.

Set two to five data sheets side by side: every value with its sentence and page, units converted in code, and "not like for like" where the conditions differ.

WHAT IT DOES

Add two to five data sheets as PDF files with a text layer (ones whose text you can select and copy), Word files or text files, and, if you like, type your own requirements, one on each line. The sheets and your requirement lines are sent to OpenAI. The model reads the sheets and lists what each one states for each parameter: the figure, its unit, whether the sheet calls it a minimum, a typical value or a maximum, the condition it is stated for, and the exact sentence. Everything after that is done by the app itself, in code, on your computer. It looks up every sentence in the file it is said to come from and shows the page, or the heading in a Word or text file; a value whose sentence or figure it cannot find is shown as "not found in the file" and is left out of every comparison. It brings the figures of a row to one unit and shows the conversion (500 psi = 34.47 bar). It marks a row "not like for like" when one sheet gives a typical value and another a maximum, or when the figures are stated for different conditions, such as 25 degrees in one sheet and the whole temperature range in another. And it works out each of your requirements for each sheet: "inside your requirement as read", "outside your requirement as read" or "sheet is silent". After the run you can change a requirement, add one, or choose the row it is compared with, and the app works the results out again without asking the model and without any cost. You get a count of what was checked and what was not, the comparison, every value with its sentence, an Excel file and a Word summary. 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 34 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 what the sheets state, not how the parts perform, and it never ranks the parts or recommends one. The model can misread a value or miss one: check each value against the sentence and the page shown. Values that a sheet gives only in a graph, a drawing or a scan cannot be read or checked, and a sheet with no text layer is marked "not checked (scan or image)". "Sheet is silent" means only that the sheet does not state the figure: ask the maker. The app cannot know everything that makes two figures comparable (the test method, the definition of accuracy), so a row that is not marked can still be unlike. A figure in a unit the app does not know, such as "% of span", is compared only with a figure written in the same unit. Your requirement lines are sent to the model together with the sheets, so that it can match their names to rows; the results in the requirement column are the app's own arithmetic. Published standards are not an input: use data sheets, or documents of your own. A comparison with nothing marked does not mean the sheets are right. The output is not a design check, a selection or an approval.

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".