Free test

Grade us first, free, on a job you already know

Send one closed-out job you already know the answers to: plans, specs, or both. We run it, and inside five business days you get back what it found, every claim cited to a sheet, to grade against what you already know. No fee, and no obligation afterward except telling us the truth about it.

A set you already know is the only fair test, because you can check what it found against what actually happened in the field. Do not tell us what went wrong on it. Keep that back and grade us on it.

How it gets to us. Either we bring the machine to your office and the set never leaves it (travel at your cost), or you send a download link from wherever the set already lives and our own model reads it on our own machine. Tell us when to delete it: it comes off the machine when you say, and we keep no backup copy of it.

Send a set you already know

In the email: what the job was, roughly how many sheets, and where the set lives now. We reply with how to get it to us.

How the free test works, step by step

Then, if the test earns it: a free pilot

Three weeks on your own sets, with your own login. Before it starts we agree on a one-page scope, name the owner on your side, and book the debrief. It is free for the first five firms, through December 31. Your sets are read on our machine, on the same terms as the free test.

What it does today.

Everything below runs on the box now, as of September 2026.

Three buttons under an answer in Redgorge Reader, labelled Right, Wrong and Rightly declined, under the heading Was this right? — In the pilot, every answer has Right, Wrong and Rightly declined buttons; the free test is graded on a sheet. Public bid set: Pittsburg USD Bid 24-026.

Cited answers with a snip of the sheet Ask about a sheet in plain language and get the answer plus the sheet, the spec section, and a picture of the exact spot, so you can open the document and check it in about ten seconds. Every citation is checked against the labels actually found on that sheet before you see it.

Questions across a whole set, and the honest negative When it cannot answer, it says what it read and what it could not read. On the Pittsburg specs it opened with “Searched all 333 pages.” A bare “not found” hides whether it looked at all.

RFI drafting When the documents genuinely do not answer something, it names the gap, says where it already looked, and drafts the RFI for you to send. There is no model anywhere in that path: the draft is assembled from what the reader already cited, so it cannot invent a reference.

Spec-against-spec conflict checking Built into the app. It reads a spec against itself and reports two paragraphs that call for different things on the same assembly, with both citations. Tested on a spec with conflicts planted in it, it never called a near miss a conflict; the runs are in build log entry 003.