RedHub AI
How the roll-up gate works
How the Drawing-Set Takeoff Readiness gate works
This tool grades each sheet on whether a machine could measure it, then reads the set at the weakest one. It reads 14 sheets and rolls them into one verdict — the worst, never the average — then a gate that can only make it worse.
The 14 sheets
Any measured sheet with no declared scale forces NOT MEASURABLE, whatever both scores say — a quantity read off an undeclared scale is not a quantity. It fires a second way when the set has neither a controlled source nor a revision log, because then nothing establishes which version you are measuring. It releases the moment the trigger clears, and it can only ever make the verdict worse.
Why: The set-level controls score 92 and read TAKEOFF-READY AS DESCRIBED. Eleven of fourteen sheets are READABLE. And the whole set is not measurable, because A-201 has no declared scale — a sheet that scores 83 and reads clean on every other signal. An average would have buried it under thirteen better sheets; the weakest-sheet rule surfaces it, and the fix is one email.
A single sheet is the crisis, and that is the whole point. The roll-up takes the worst sheet, never the average, because a takeoff is only as good as the weakest drawing it reads — and the gate escalates past even that when a measured sheet has no declared scale. Thirteen clean sheets cannot outvote the one that cannot be measured. Grades a drawing set as you describe it, never a person. It opens no drawing and reads no file — every input is an answer you supply, using rules you can see. It produces no quantity, no cost and no bid recommendation, and it is not affiliated with any takeoff or estimating vendor.