Case Study
15 MINUTES PER DRIVER. NOW ONE REVIEW CARD.
A family-run freight carrier's nightly dispatch email, morning fleet check, and new load intake, rebuilt as one desktop app that reads the paperwork and hands every result to a person to approve.
Freight & Trucking
7 trucks
Automation
July 2026
A seven-truck carrier was retyping the same load details out of rate confirmations every night, then walking the fleet truck by truck at 5 AM.
We built one desktop app that reads the documents, drafts the work, and puts a person in the approval seat.
2 WEEKS
Build Time
About two weeks to all three tools live on the client's own machine
15 MIN
Per Driver, Per Day
The hand-built dispatch email the app now drafts
686
Automated Checks Green
424 tests plus 262 application checks at handoff
The Situation
Kelley Transportation is a family-run interstate carrier running seven trucks. The owner handles daily dispatch, the operations manager books loads at night, and a part-time dispatcher runs the morning truck check remotely. Three people, one shared spreadsheet, and a paper trail that arrives from every direction.
Every evening the office built each driver's next-day dispatch email by hand. Read the operations spreadsheet, dig the load's rate confirmation out of a mailbox holding about 12,000 messages or a shared drive holding about 123,000 files across more than 1,400 broker folders, then retype pickup addresses, appointment windows, and reference numbers into an email template. About 15 minutes per driver, every day, on information that already existed in writing somewhere.
At 5 AM someone checked every truck's position against its delivery appointment, one truck at a time in the fleet portal, converting time zones in their head as they went. Meanwhile new load paperwork kept landing by email and by drive, and it had to be noticed by a person before it could be retyped onto the spreadsheet. Anything not noticed was not scheduled.
Before calling us, the operations manager had spent weeks trying to wire this together with general-purpose AI chat tools. It demoed well. It never survived real paperwork.
What We Built
One desktop app that runs on the client's own machine, with three tools inside it. Each one reads the paperwork the office already receives and stops at a review screen, because the office decides and the app does the reading.
Dispatch Emails
DRAFTED FROM THE PAPERWORK
The tool reads the live operations spreadsheet, pulls each load's rate confirmation and broker instruction sheet out of the mailbox and the shared drive, and uses Claude to read the documents, classify them, and extract the load details. The search that used to mean opening folders now runs across about 12,000 messages and about 123,000 files per load without anyone watching it.
Composition follows a strict driver and office split. Drivers get addresses, dates, appointment windows, reference numbers, and equipment requirements. Rates and payment terms never leave the office.
Every email lands as an editable review card with plain-language flags. A person reads it, edits it, and sends it. Sends go out through the client's own dispatch mailbox and mirror to Sent, so the audit trail stays where the office already looks for it.
Current Position Check
ONE BUTTON AT 5 AM
One button replaces the truck-by-truck walk through the fleet portal. A single fleet API call returns every truck. The app pairs each position with that driver's delivery from the spreadsheet, computes drive time, and shows the appointment and the ETA side by side in the receiver's time zone with Central alongside it, so nobody does time zone math from memory at 5 AM.
A truck that stops reporting gets an amber staleness flag rather than a stale position presented as current.
There is deliberately no verdict logic. The tool never declares a truck early or late. It puts the two times next to each other and the dispatcher reads them, because the dispatcher knows about the construction on the route and the receiver who takes trucks an hour before the window.
Incoming Loads
STAGED, NOT GUESSED
Every ten minutes the tool scans the mailbox and the drive for new freight paperwork and stages one row per load the spreadsheet does not already carry. Noticing new work is no longer a person's job.
Documents are judged by what their pages say, not by what their filenames claim. A file the tool cannot place is kept and flagged for someone to look at, never silently dropped, and a disagreement between what two documents say about the same load is surfaced rather than resolved by guesswork.
One click copies a paste-ready row for the spreadsheet. The driver cell stays blank on purpose, because the office assigns drivers and the paperwork does not.
NO WRITES
The app holds comment-only access to the operations spreadsheet and the shared drive, and performs zero writes to either. It reads, a person decides. A tool that cannot damage the record is a tool the office can leave running.
THEIR STACK
It runs on the client's machine, through their mailbox, their fleet account, and their own Claude subscription. Nothing routes through our infrastructure, so the work does not depend on us staying in the picture.
FLAGS, NOT GUESSES
Missing fields, unreadable documents, conflicting paperwork, and trucks that stop reporting all surface as flags. Nothing gets quietly filled in, and nothing gets quietly discarded.
The Numbers
Build and first-run figures measured at handoff. The last three tiles cover the search surface the tools cross on every load and the writes they make to the client's records.
~2 WEEKS
Build Time, All Three Tools
686
Automated Checks Green
40
Documents in First Intake Run
3
New Loads Staged, Every Field Correct
0
Documents Wrongly Set Aside
15 MIN
Per Driver, Per Day, Before
~12,000
Mailbox Messages Searched Per Load
~123,000
Drive Files Searched Per Load
0
Writes to Client Systems of Record
Accuracy check.
Given the same rate confirmation as a dispatch email the office had already sent by hand, the pipeline reproduced every data field, including an exact match on the subject line.
First fleet review.
The client read every row of the position check against what the office already knew that morning. Every row matched.
The client's own estimate
Within the first week the client put the time saved at first an hour a day, then three to four hours a day. That is the client's estimate rather than a measurement we took. What we can say is that the dispatch tool is in daily use for generating and reviewing driver emails.
What Comes Next
The intake tool is rolling into daily use alongside the other two.
Next is teaching the position check to read delivery stages off the spreadsheet, so a finished delivery never shows as the active stop.
After that, continued hardening as daily runs surface edge cases. Real paperwork is the only test that counts.
Common Questions
FAQ
What manual work did this automation replace?
Three things. Building each driver's next-day dispatch email by hand, which took about 15 minutes per driver every day. Checking every truck's position against its delivery appointment one truck at a time at 5 AM, with time zone math done in someone's head. And noticing new load paperwork as it arrived by email and drive, then retyping it onto the operations spreadsheet.
Does the app write to the client's spreadsheet or shared drive?
No. The app holds comment-only access to the operations spreadsheet and the shared drive, and it performs zero writes to either. It reads the records, presents what it found, and a person decides what happens next. The intake tool copies a paste-ready row to the clipboard rather than inserting it.
What happens when paperwork is missing or wrong?
It gets flagged, never guessed at and never silently dropped. Dispatch emails arrive as editable review cards carrying plain-language flags, so a person reads, edits, and sends. A document the intake tool cannot place is kept and flagged for a human to look at. A truck that stops reporting its position gets an amber staleness flag on the fleet check.
What does the system run on?
The client's own machine, the client's own accounts. Their dispatch mailbox, their shared drive, their fleet provider account, and their own Claude subscription. Nothing routes through our infrastructure, and sends go out through their mailbox and mirror to Sent so the audit trail stays where the office already looks.
How long did the build take?
All three tools were built in about 2 weeks, from access handover to running on the client's own machine. Hardening continued after that as daily runs surfaced edge cases.
Do you build this for other fleets and businesses?
Yes. The pattern applies anywhere a person reads documents and retypes what they say into another system. We scope the work against the paperwork you actually receive, build on your machine and your accounts, and keep a person in the approval seat. Get in touch and we will look at your workflow.
Someone in Your Office Is Retyping This Already
This kind of work falls under our revenue operations service. We build document processing that runs on your machine and your accounts, reads the paperwork you already receive, and stops at a review screen so a person still approves the work.