Manufacturing
Sand's engineers stopped guessing why a line stopped.
A system that watches the production line and explains a stoppage before an engineer has to ask.
-70%less time to find why a line stopped
100%stoppages logged automatically
Construction · Mosaic
Mosaic estimates a job in a third of the time.
A model that reads the drawings and quantities, an estimating agent and a draft estimate the estimator corrects.
What changed
- less time producing an estimate
- -38%less time producing an estimatehours per estimate from drawings received to draft sent, 12-week average
- deviation from final cost
- ±6%deviation from final costmedian deviation of the draft estimate from the invoiced cost, closed projects
At a glance
- Starting point
- A process run by hand
- Capabilities
- Predict
- What we built
- A model that reads the drawings and quantities, an estimating agent and a draft estimate the estimator corrects.
- Where it runs
- The client's cloud. Drawings are processed and stored in their own account.
The problem
Estimators re-measured the drawings by hand for every job, then rebuilt the quantities and prices in a spreadsheet from a blank sheet. A spreadsheet template had been tried before; it drifted a little differently under every estimator until the numbers stopped meaning the same thing across jobs.
Mosaic needed an estimate that started from the drawings themselves, not from memory of the last similar job.
What changed
Estimators now produce an estimate 38% faster, measured over twelve weeks, and drafts land within ±6% of the invoiced cost on closed projects. They correct a draft instead of starting from zero.
Next
The next case.
Read the case
Talk to us about a similar problem.
Tell us how it is done today and what changes if it works. You get a straight answer on whether AI can solve it.
Talk to usor write to hello@maistik.studio