In production since May 2026 · Lisbon

I build AI operating systems for businesses.

One system for an operation that used to live across tools that never talked to each other.

Hire me on Upwork
20 minutes · Google Meet · bring the jump that costs the most
Before

The operation lives in six places.

Every jump between them is time, and error.

Until one question.

“How do we stop typing every reminder by hand?”

The first module. Everything after it grew from the same data.

Module by module

Four modules, four before-and-afters, four numbers.

Each one measured on its own, in minutes per task, on this operator’s production data. The screens are recorded in the demo tenant.

01Messages

The messages write themselves. Sending stays one tap.

Before3.5 min per message, by hand, in six languages
Now0.2 min to review and send
≈ 6 ha month, back
100+ messages a month
Source: message log · August 2026 · one tenant, no demo data
02The weekly schedule

The schedule stopped being a picture and became data.

Beforea spreadsheet, exported as a picture, posted in the group
Nowone click, to the group and to each driver’s app
≈ 3 ha month, back
120+ assignments a month, no re-checking
Source: assignment log · August 2026
03Dispatch and the driver’s app

A last-minute tour used to mean five phone calls.

Beforecall the drivers one by one, mid-tour, to find who is free
Nowone screen shows who can take it; one click, and it lands in his app
≈ 4 ha month, back
120+ briefings a month
Source: dispatch log · August 2026
04The money

The balance settles as each tour closes.

Beforespreadsheets updated by hand; the close took an afternoon
Nowsettled the moment the tour ends; commissions ready at month end
≈ 6 ha month, back
month-end close: 3 h 30 to 30 min
Source: accounts ledger · 99 movements in 31 days · August 2026
The whole point

The areas talk to each other.

Nothing is typed twice. Every booking is read once, and the same data runs the day.

Ana Paula
Ana Paula
Founder and manager, Live Portugal
In her words

Jeff’s work had a very significant impact on our operation. The tools he developed let us raise productivity, cut the time spent on operational tasks considerably, and have far more control over the company’s different processes. They also brought more organisation and alignment between the different areas, making day-to-day communication and management much more efficient.

Beyond the technical quality of the work, I would also highlight his professionalism, his ability to understand the needs of the business and, above all, his readiness and availability to find solutions and answer the challenges that came up along the project.

I recommend Jeff without hesitation to any company looking for someone competent, responsible and focused on creating solutions that truly generate value for the business.

Written in Portuguese · translated
Measured, not projected

The numbers, with their source.

≈ 20 h / month
of manual work removed, across messaging, dispatch, the weekly schedule and the books
August 2026 · this operator only
414 messages
sent to customers in six languages, 404 delivered
Message log · May to Sep 2026
6,499 bookings
read from the calendar once, never retyped
Calendar sync · history since 2022
Measured on production data, one tenant, no demo data. Not a projection.How each number was measured →
The other half of the job

Where AI does not touch.

Writing this list with the client is part of the delivery, not an appendix. A team that does not know where the machine stops distrusts it entirely. The default:

  1. 01
    Decisions about peopleHiring, letting go, evaluating, changing someone’s shift.
  2. 02
    Money going outPayments, the final price, discounts, credit.
  3. 03
    Messages that leave with the company’s name, unreviewedWhen the subject is a complaint, a cancellation, money, or something that already went wrong.
  4. 04
    Clinical, legal or tax judgmentA model can draft. It does not sign.
  5. 05
    Any output whose data source cannot be tracedIf a number has no source, it does not go out. Missing data pauses the flow and tells a person.
  6. 06
    What the team already does well and fastAutomating that does not pay for its own upkeep.

In this system that line is the whole design. The schedule is built by the managers because it is a judgment about people. The balances are plain code because they must be right. The customer send is a human decision because the cost of being wrong is the channel the business runs on.

How it starts

The map and the first module.

Fixed price, one to two weeks, quoted after the call. You keep the map of your operation and one module running, whether or not we continue.

Week 1

Map the operation. Time the costliest jump.

Every tool the operation lives in, and every copy between them. Minutes per task, ten real runs, before anything changes.

Weeks 1 to 2

Draw the line. Build the first module.

What the AI will do and what it will never do, approved before the build. The first module is built so the second one fits.

Day 30

Measure again, same unit.

Same task, same method. If the hours did not come back, that gets written down too.

Tell me which jump between your tools costs the most.

Hire me on Upwork
20 minutes · Google Meet · bring the jump that costs the most
Jefferson Alves
Jefferson Alves
Built the system, works at the company, runs it every day · Lisbon

Full disclosure: I work at that company. I built the system that runs the operation where I work, so I live with my own decisions.