The record

Every claim,
with its working.

Ten measurements across four engagements. Measured means we timed it on a live engagement. Modelled means the arithmetic came from the client’s own task list. Nothing here is a benchmark, and where a figure is rounded, the working underneath shows the unrounded number.

Three of the four engagements below are property businesses, because that is where we started. The exception is our own operation, where 32 agents run this company. The jobs are the same in a clinic, a restaurant or a contractor’s office — what changes is the record.

Record compiled 10 Nov 2026 · 10 measurements · 4 engagements · 1 vertical held back

EngagementWhat was measuredResultTier
01Our own operationAgents in production32 agentsMeasured
02Our own operationRuns a day, from the run log3,781 / dayMeasured
03Commercial brokerageListing preparation, per property19.25 → 4.05 hModelled
04Commercial brokerageHours returned, one listing desk, a year122 h a yearModelled
05Public recordsBridgeport VGSI, per parcel22.8 sMeasured
06Public recordsWorcester, per parcel19.0 sMeasured
07Public recordsGreenville, per parcel16.4 sMeasured
08Property managementScreening turnaround3 days → 4 hMeasured
09Property managementMaintenance resolution60% fasterMeasured
10Property managementLate renewal offers0 lateMeasured

One vertical is published with no number, on purpose — home services, because we have not measured it yet.

01 / Our own operation

We run it ourselves before we sell it.

Engagement internal
Tier measured
Source run log

This business is operated by scheduled agents that never sleep and never forget a deadline. Every number below is taken from our own logs, not modelled.

The measurementResult
01
Production

32 agents in production

Scheduled work across both mailboxes, the deadline board, document intake and reporting. Nothing sends without a person approving it.

32
Scheduled agents
Measured
02
Volume

3,781 runs a day

Reads, recalculations, retrievals and drafts — measured from the run log, not estimated.

3,781 / day
Runs
Measured
03
What it caught

A report waiting 44 days

A management report had been sitting for 44 days; it closed the day the missing files landed. A payment tracked as “overdue” for 18 days turned out to be due on the day it was paid — the date on the envelope was the mailing date, not the due date.

44 days
Closed the day files landed
Measured
The working3,781 runs ÷ 24 h = 157.5 runs an hour, every hour, from the run log
44 days is how long one report sat before the missing files landed
02 / Commercial brokerage

The twenty-hour listing.

Engagement anonymised
Tier modelled
Basis his task list

A commercial broker in Hartford County keeps one number for getting a single listing to market: the preparation. His own estimate was twenty hours. We modelled his task list top to bottom and landed within 5% of it, independently.

The measurementResult
01
Preparation

19.25 hours to 4.05

Photographs, comps, dimensions, zoning, the write-up, and the same facts typed into three portals that each want them in a different order.

19.25 → 4.05 h
Per listing
Modelled
02
Returned

15.2 hours a listing, 122 a year

The hours that go are the ones with no decision in them: retyping, reformatting and filing. The four that stay are the ones only the broker can do.

15.2 h
Returned per listing
Modelled
03
Annual

122 hours a year

On the listing desk alone, at his volume. Client anonymised at his request; the method and the full task list are available on request.

122 h/yr
Listing desk only
Modelled
The working19.25 − 4.05 = 15.2 h returned, per listing
15.2 h × 8 listings a year = 121.6 h, rounded to 122
122 h is about 15 working days of one person’s year, on the listing desk alone
03 / Public records

No API, no problem.

Engagement internal
Tier measured
States CT · MA · SC

Most county property records are public and hostile to automation: a search box, one parcel at a time, no data feed and no plan for one. We built a routine that drives the site the way a person does — search, wait, read, record — and timed it on real parcels in three states.

The measurementResult
01
Connecticut

Bridgeport VGSI

Ownership, assessment, appraisal and last sale, re-checked against the source page.

22.8 s
Per parcel
Measured
02
Massachusetts

Worcester

Same fields, a different county form, the same run.

19.0 s
Per parcel
Measured
03
South Carolina

Greenville

One parcel is a demo. A hundred, the night before a meeting, is a different week.

16.4 s
Per parcel
Measured
The working22.8 → 16.4 s = 6.4 s spread across three county systems
Same routine, three different forms. No API was used or asked for.
04 / Property management

200 units, and the question that never stops.

Engagement client
Tier measured
Portfolio 200 units

A property management firm came with a problem that did not sound like a technology problem. The portfolio was growing; operations were drowning the team.

The measurementResult
01
Screening

Three days into four hours

Applications flow through background, credit and scoring. A human reviews the final call only.

3 days → 4 h
Turnaround
Measured
02
Maintenance

60% faster resolution

Tenants submit, the job is auto-assigned by trade, and status flows back without anyone retyping it.

60% faster
Resolution time
Measured
03
Renewals

Zero late offers

Triggers fire 90 days out off actual lease dates. No spreadsheet. No forgetting.

0 late
Renewal offers
Measured
The working72 h − 4 h = 68 h of waiting removed, per application
Three calendar days was the old clock; four hours is the new one
05 / The rule

We measured ourselves first.

Engagement internal
Tier measured
Date Sept 2026

Buyers increasingly ask an assistant for a recommendation instead of scrolling ten results. So we ran our own version of that test on ourselves — and we were missing, for reasons we could fix.

What it found

Our own site was telling AI crawlers to stay out. A page still published a contact address retired months earlier. Claimed results had no case study behind them.

What we changed

Crawler permissions opened for the assistants people actually use. Contact details corrected at the source. This page — so every claim has a number and a method under it.

Why it is here

A report that only ever finds problems in the client’s business is not a report, it is a pitch. We publish ours because nobody else does.

06 / Where this goes next

The jobs travel. The record is what changes.

Four verticals are measured and live. The rest are in build — each one gets its own agent, its own record and its own front door, and none of them ships with a number until we have one.

Start here

Your job goes in this ledger next.

Built to a written scope. Price agreed before anything is built.

Build your agent