Your best coordinator spends Thursday reading.
That is the process I fix.
Twenty years of MEP coordination, five of them as a contractor's CTO. I take one document workflow, measure what it actually costs you, rebuild it, and measure it again. Then I hand you the number. I also built the software that does the reading, so you can see how I work before you hire me.
$4,000 to $5,000, fixed. One day on site or on a call, one workflow mapped end to end with real cycle times, and a written finding inside five business days. Credited in full against a build if you start one within 60 days.
Direct to Shane. No form, no sales sequence.
ASKED
Does anything in the mechanical package conflict on duct insulation?
CONFLICT — SPEC vs. SCHEDULE
The specification and the drawing schedule call for different values on the same assembly. One of them is going to be installed.
Sources on this answer: 3 · unsourced claims: 0
Mock-up on an invented set — the shape of an answer, not a run. The real run is in 03.
Every company has a job that is one person, reading, at 11pm.
Not "inefficiency". A specific hour, with a name attached to it. Four questions I ask in the first meeting, because the answers are usually a name, a duration and a failure, and that is a scoped piece of work.
What happens when an addendum lands?
Who opens it, what do they do with it, and how long until the field knows. The base documents still say the old thing, and they will keep saying it until somebody reads both.
What was the last thing installed wrong because two documents disagreed?
And what did it cost. Not a productivity number. A change order, a demo-and-rehang, a delay you carried.
Where has somebody already tried to fix this?
Every company has a graveyard. What was bought, who championed it, and why it did not take. That history is worth more to me than a wish list, and it usually names a budget line that already existed once.
If that job took a quarter of the time, who notices?
And what do they do with the time. If nobody notices, there is nothing to fix and I will tell you so on the day rather than three weeks into a build.
One workflow. One number. A fixed price and a date it ends.
Every engagement carries an acceptance criterion written as a number, not an adjective, and a measurement taken before I change anything. If we cannot measure it, neither of us can tell afterward whether I did anything, and I would rather say that up front.
One-day workflow teardown $4,000 to $5,000 · one day, written finding in 5 business days
One document workflow mapped end to end, instrumented with real cycle times off real packages, a ranked list of what to fix, and what each fix is worth per year. You own the finding whether or not you ever hire me again.
Credited in full against a build started within 60 days. It exists so neither of us has to guess at the scope of the bigger thing.
Fixed-scope workflow build $18,000 to $35,000 · 4 to 6 weeks
One named workflow, one named metric, measured before and measured after. Submittal log triage. An addendum reconciled against the base documents. Spec sections pulled into a takeoff-ready schedule. An equipment schedule checked against the one-line and the panel capacity.
Half up front, half on acceptance, and acceptance is the number in the scope document rather than my opinion or yours.
Larger programs
Multiple workflows, sequenced, each one carrying its own acceptance number. Priced on scope after a teardown, and never as an open retainer.
What I will not do
No staff augmentation. I am not a body you rent by the sprint. If what you need is a pair of hands inside your team, I am the wrong call and I will say so in the first ten minutes.
No hourly. Hourly has no defined end, and it means every tool I build that makes the work faster cuts my own invoice. That is a bad incentive to hand somebody you are hiring to make something faster.
No workflow that cannot be measured. If we cannot count the thing before and count it again after, there is no way for you to know whether the money did anything, and I will not take work I cannot be graded on.
I built the tool. Then I built the test that grades it, and it keeps refusing my work.
Redgorge Reader reads a construction document set and answers questions about it with the sheet and the paragraph attached. It is not what I am selling. It is how you can check, before you spend anything, whether I am careful with somebody else's documents.
The set
Pittsburg Unified School District — District Admin. Offices HVAC Units Replacement, Bid 24-026. Project manual dated March 2024, 333 pages. It read the full mechanical division: all eight Division 23 technical sections, 49 pages of specification.
A public bid document, and a public record. Ask and I will send you the exact PDF I ran, so you can check every quote against it yourself — which is the whole point. No vendor with customers will hand you their test set. I do not have that problem yet.
The run
Seventy-five seconds, wall clock, start to finish — on the appliance, in the room. Nothing was uploaded, and nothing about that document left the machine.
No OCR and no vision pass required — this manual had a clean text layer.
The result
Twelve of twelve quotes verbatim. Every passage it attributed to the manual appears in the manual, word for word, and every paragraph number it cited was real. It also examined six apparent contradictions and called all six correctly as not conflicts — including duct liner against external duct wrap, which are different assemblies in different sections and are the exact false positive a keyword search reports.
That is the only thing this run tested, and it is the one that has to hold first: whether a citation is worth enough that you stop checking them by hand.
The number I would rather not publish.
Reading a specification is one job. Pulling a door, window or equipment schedule off a drawing sheet into a table is a different one, and it is the part that is not good yet. So I built a test for it: drawing sets I read and labelled by hand first, so there is a right answer to check against. Here is where that build stands today.
The terms, for anyone who wants them. Precision is the share of the rows it reports that are really there. Recall is the share of the rows that are really there that it reports. F1 combines the two into one number, and it is low whenever either one is low, so it cannot win by guessing more or by guessing less. Macro means each drawing set is scored on its own and the scores are averaged, so one large set does not drown out ten small ones. Row counts are not a measurement: a row count can only go up. The run-by-run chart is in the build log.
And the part that is not settled. Read 0.441 with its composition, because the headline flatters: two of the eight sets are negative controls with no rows to find, and finding nothing there scores a perfect 1.00. Across the six sets that carry real labels the average is nearer 0.25, and three of those score zero while the run still reports itself as fine. I labelled those sets myself, so this is my homework marked by me. Nobody in the construction trade has graded any of this output yet, which is the single most useful thing anyone reading this could change. I have not found anyone in this field publishing an independently graded number, and mine is not independently graded either, which is exactly what the paragraph above is admitting. I am telling you mine because you should not have to take an accuracy claim on faith, least of all from someone you are about to pay.
Exactly what exists, as of today.
This site used to advertise three things that were not built. Two of them now are, and both are running on the machine that answers day to day. Here is the whole list, including the one that still is not built.
Twenty years of reading these sets by hand.
I have done this reading pass by hand for twenty years in construction — every sheet, every spec section, on sets that ran to hundreds of pages.
As director of BIM technology I took our scope into coordination on a California hospital tower, the Sphere, Allegiant Stadium and the Hard Rock — one trade among many in the model, working it out against everybody else's.
Then five years as CTO of an industrial refrigeration contractor, where I built the BIM department from nothing and authored the FabCAD database the shop fabricates from. Not a report somebody filed. A thing the fitters use every day.
Redgorge is the tool I kept wishing existed. I built it on hardware I can hand you, because I know exactly which of those documents you are not allowed to upload.
Revit · Navisworks · Revizto · FabCAD MEP · reality capture & point clouds
prefabrication programs · Procore · NetSuite · process design
— Shane Brooks
The platforms in your contract went through procurement. An AI service did not.
Your document platforms were named, reviewed and signed off, and everybody knows where the files sit. A service with its own retention and training terms went through none of that — so pasting a set into one is a conversation you would have to go and have. This is one quiet box on your network, so there is nothing to disclose, nothing to review, and nothing to explain to the owner.
The other consultant you could hire for this work would paste your set into a hosted model. That is the difference, and it is the entire reason the box exists.
About the box, plainly. The model occupies 41.1 GB of graphics memory while it is answering. A workstation with an RTX 4090 has 24 and is not enough, and almost nobody has forty spare gigabytes of GPU memory idle in a closet. So the hardware is a requirement, not an upsell: one machine, bought at cost after the contract is signed, currently around $1,500 to $2,000. It is a line item against the engagement. I am not in the hardware business and I do not want to be.
What actually happens if you say yes.
The whole thing, spelled out — including where your documents go, what it costs, and what happens if it turns out to be worth nothing.
You name one workflow
The addendum one. The submittal one. The one where somebody re-types a schedule into a spreadsheet. You do not need to know what the fix is; naming the job and the person who owns it is enough to start.
If your contract needs an NDA signed first, send me yours.
I spend a day inside it, with a stopwatch
Real packages, real cycle times, the actual sequence rather than the one on the org chart. Where documents are involved, I would rather work on real ones, and where they cannot leave your network, I bring the machine to them or I work on your side of the wall.
Tell me what should happen to any files afterward — deleted, returned, or never copied off your network in the first place — and that is what happens. Nothing is used to train anything. Nothing about your company appears on this site; the tests published here are public bid documents, and they stay the only ones.
You get it in writing inside five business days
The workflow mapped end to end, what each step actually costs you per year, a ranked list of what to fix, and what a fix would take. Yours to keep, and yours to hand to somebody else if you would rather they built it.
Including the parts I could not measure and the parts I got wrong. That list is the most useful part for me and usually the most reassuring part for you.
Then you decide, with a number in front of you
If a build makes sense, the teardown fee comes off it in full. If it does not, we stop, and you still have the map. If the honest answer is that this workflow is not costing you enough to be worth fixing, that is in the document too, in writing, and it is the cheapest way to find out.
If it earns nothing, you have lost a day and the fee, and you know something about your own operation that you did not know on Monday.
Or, if you would rather grade me first
Send one closed-out job you already know the answers to. Plans and specifications together if you have them; an addendum against its base documents is better still. I run it, and you get back what it found and what it got wrong, every claim cited to a sheet. No fee, and no obligation to do anything afterward except tell me 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 me what went wrong on it. Keep that back and grade me on it.
Pick the job nobody wants to do on a Thursday.
One day, one workflow, one written finding you own. If a build follows, the day comes off the price. If it does not, you keep the map.
Teardown: $4,000 to $5,000, fixed. Credited in full against a build started within 60 days. Grading a closed-out set costs nothing.