Let's talk
How it works

Rules you can read.

Every check is plain code that applies written rules to a file you export. There is no AI model inside a check: the same file gives the same result every time. An AI assistant is optional, and it only reads the results.

Three parts.

1

The check

A small program with one job, such as matching freight bills to contract rates. It reads a folder of exports on your computer and writes a worklist and a report.

2

Your settings

Most dates, rates, thresholds and rules that change with the law or a contract are settings in a file you can read and edit. The few that are fixed in code are named on the product page. Every result lists the settings it used.

3

The assistant, if you want one

Your AI assistant can call a check as a tool (MCP). It sees the result, with people's names and identifiers masked in most products, and helps you work through it. Through a check it cannot pay, send, file or change anything.

What reaches the model.

When an assistant calls a check, the check reads your file locally and returns findings. In most products, people's names, account numbers, birth dates, addresses and similar fields are replaced with stable pseudonyms or removed before anything is returned, and some have a stricter mode that masks more. Fairbooks and Fairlease mask less today: tax IDs are masked, but people's names reach the model. Amounts, dates and codes stay in clear, because that is what the finding is about.

The results then go to whatever model your assistant uses. For sensitive files, use a local model or one covered by your own agreements. Masking is a design choice, not a legal determination, and we make no compliance claim. Each product page says field by field what is masked and what stays in clear.

It does not pay.It does not send.It does not file.It does not delete.It does not change access.No login to your systems.No upload to us.

How it was tested.

Every product carries its own unit tests and scored eval cases, and a demo that runs on made-up files. On 21 Nov 2026 all 18 code repositories were downloaded fresh and their unit tests were run again on Node.js 22: 15,355 of 15,355 passed.

14 of the 17 products have also been through a final pass, on 19 Nov 2026. It adds a hostile pass that feeds the checks poisoned files and arguments, a 10,000-row speed test, the same cases in eight languages, and a release check run from a fresh copy with no network. Accuracy was then measured three ways on made-up files: the problems planted in each check's test files, the same files with every problem removed (anything reported there is a false alarm), and one-change copies that should each produce one finding. Last, the checks were run on public, real-world data, which found real bugs in most families; they were fixed before these numbers were taken.

For Fairbooks the final pass covers 7 of its 30 checks, and for Fairhaul 26 of its 30. Fairclaim, Fairlease and Fairstay have not had it yet, so they have no accuracy numbers, and their rows below say so.

ProductPlanted foundFalse alarms on clean rowsOne-change testsPublic data runs
Fairhaul (26 of its 30 checks)174 / 1740 on 19746 / 462
Fairpractice wave 1207 / 2070 on 2,29778 / 783
Fairpractice wave 2177 / 1770 on 40786 / 864
Fairwire270 / 2700 on 42466 / 664
Fairbuild170 / 1700 on 6746 / 462
Fairbrief187 / 1870 on 20420 / 202
Fairtable217 / 2170 on 49064 / 642
Fairshop158 / 1580 on 38082 / 825
Fairmake230 / 2300 on 44084 / 842
Fairpolicy122 / 1220 on 44279 / 794
Fairdrive185 / 1850 on 20563 / 632
Fairroom175 / 1750 on 373107 / 1072
Fairclinic180 / 1800 on 46896 / 964
Fairgive185 / 1850 on 57590 / 903
Fairbooks (7 of its 30 checks)44 / 440 on 8218 / 184
FairclaimNot yet measured this way. 865 of 865 unit tests and 498 of 498 eval cases pass.
FairleaseNot yet measured this way. 932 of 932 unit tests and 594 of 594 eval cases pass.
FairstayNot yet measured this way. 858 of 858 unit tests and 512 of 512 eval cases pass.
All measured2,681 / 2,6810 on 7,0511,025 / 1,02545

The test files and the checks were written by the same team, so these numbers show that the rules do what they are written to do. They do not yet say how often a check is right on a real business's files: that is measured at each setup.

Export formats, honestly.

The 14 measured products know 314 named export layouts from the systems they read, counted per product. 31 have been run on a real published file or a vendor's public sample. The rest were written from knowledge of each vendor's export and have not yet been tested on a customer's own file. That is why every setup starts by confirming the layout on your files, and why any column can be mapped by hand. Each product page lists its formats one by one.

Who keeps the rules current.

Most rules that change with the law, a standard or a contract (rates, limits, deadlines, code lists) are dated settings, listed in each check's README with their source. You can edit them yourself in a plain settings file. The few fixed in code are named on the product page and change only in a new version. On a support plan we update them, and the export layouts, when they change, and tell you what changed.

Where Fair Agents is today.

Fair Agents is new. We are looking for our first design partners: a fixed-price setup on your own files, with your feedback shaping the formats and the rules.

The first three clients of each product get 40% off the setup. How the offer works.

Become a design partnerTry the software