AI automation for a transfer company in Italy
The owner tracked the day on a paper sheet, while orders arrived from 2 own websites, 7 booking platforms, direct calls and WhatsApp. We built one order hub with a Telegram bot and a phone planner. AI reads the messages. The owner keeps every decision.
The client is anonymous. The demo and all screenshots use fictional data.
Orders in many places, and the day on paper
- A small transfer company in Italy, with seven drivers on the current driver list.
- Orders arrive through 2 own websites, 7 booking platforms (by email and in their apps), and direct calls and WhatsApp messages.
- The owner decides which platform bookings to accept. Platforms email every booking, and the owner takes only some of them.
- The owner tracked the day on a paper sheet: time, route, platform, driver.
One sheet, and three ways to work with it
One day sheet
All accepted trips are in one list: time, route, source, driver, price.
Telegram bot
A team member sends a booking screenshot, a booking number or plain text. The bot records the order and replies in one line.
Phone planner
A private link opens the day. The owner assigns a driver with one tap, adds notes, creates, moves and removes trips. No app to install.
Google Sheet
The same data for the owner and bookkeeping.
Morning digest
At 06:30 Italian time the chat receives the day’s trips and highlights trips without a driver.
Dispatch draft
The planner proposes a driver for each unassigned trip and flags trips one driver cannot reach in time. The owner accepts with checkboxes. Nothing is assigned automatically.
See it on fictional data
These frames come from the demo, not from the live system. The demo is a simplified recreation in the browser, and you can click through it yourself.



AI reads. Code runs. The owner decides.
Claude Sonnet
Reads chat messages and booking screenshots and turns them into commands. It can run only a short allowlist of order commands.
Python
Website and mailbox import, email parsers, sync, journals, planner, digest and dispatch draft. These parts give the same result every time.
Slash commands
If the model hits a limit, slash commands work in the chat without AI.
The owner decides
Only the owner confirms an order or assigns a driver.
What the logs show
We counted these figures from the production logs on the server.
| Fact | Value | Period |
|---|---|---|
| Sync runs logged | 2,02718 Oct to 5 Nov 2026 | 18 Oct to 5 Nov 2026 |
| Failed sync runs | 1 (Google 503, next run succeeded)18 Oct to 5 Nov 2026 | 18 Oct to 5 Nov 2026 |
| Gaps over 30 minutes between runs | 018 Oct to 5 Nov 2026 | 18 Oct to 5 Nov 2026 |
| Morning digests sent | 15 of 15 days logged22 Oct to 5 Nov 2026 | 22 Oct to 5 Nov 2026 |
| Booking actions in the journal | 265 (244 added, 21 removed), including 7 test records19 Oct to 4 Nov 2026 | 19 Oct to 4 Nov 2026 |
| Actions that came from the chat | 238 of 26519 Oct to 4 Nov 2026 | 19 Oct to 4 Nov 2026 |
| Driver assignments | 182 (169 in the phone planner, 13 by link)19 Oct to 4 Nov 2026 | 19 Oct to 4 Nov 2026 |
| Platform emails read, read-only | 17,690stored window, up to 400 days | stored window, up to 400 days |
| Bot cost at API prices, general setup | $145.26 for 55 messages18 to 24 Oct 2026 | 18 to 24 Oct 2026 |
| Bot cost at API prices, focused setup | $2.52 for 47 messages26 Oct to 4 Nov 2026 | 26 Oct to 4 Nov 2026 |
| Automated tests | 168 passing5 Nov 2026 | 5 Nov 2026 |
| Python code | about 4,150 lines5 Nov 2026 | 5 Nov 2026 |
The sync log also has 3 skipped starts, because the previous run was still active, and 1 connection error line on 21 Oct. The next run succeeded each time.
Cost per message fell from about $2.64 to about $0.05. The earlier setup also ran on more expensive models and a much larger prompt, so we do not credit one cause alone.
Costs are API-price equivalents. The bot runs on a subscription, so they are not invoices. 25 Oct is left out of the cost rows, because the setup changed that day.
The bot-cost sample is small: 55 and 47 messages.
No before-and-after numbers
- We have no “before” measurement, so this page makes no claim about hours saved, more orders, more revenue or fewer mistakes.
- AI does not plan the day. The dispatch draft is a rule-based algorithm, its travel times are rough estimates, and the owner’s criteria are still open.
What we would tell the next client
Copying the paper sheet won
The owner rejected the calendar view and asked for the paper sheet layout.
Email is a reference, not a source of orders
Platforms send everything, and only the owner’s confirmation makes a trip.
An append-only journal keeps the history
A journal that only appends records shows who changed what and when.
Review before handover
The code review found three silent data loss risks, and we fixed all three before handover.
Less AI was enough
A smaller prompt and a cheaper model were enough for this job.
About this case
Does AI decide who drives?+
No. The dispatch draft is a rule-based algorithm without AI, and its travel times are rough estimates. Only the owner confirms an order or assigns a driver.
What can the AI do in this system?+
It reads chat messages and booking screenshots and turns them into commands. It can run only a short allowlist of order commands.
What happens if the AI model hits a limit?+
Slash commands work in the chat without AI, and the sync, journals, planner and digest are plain code.
How much time or money did this save?+
We do not know. We have no measurement from before the project, so we make no claim about hours saved, orders, revenue or mistakes.
Is the demo the live system?+
No. The demo is a simplified recreation on fictional data. The chat is a recorded script and no AI runs on that page. The live system and its data are private.
Why is the client not named?+
We publish this case anonymously as a transfer company in Italy. The screenshots come only from the demo, so they show no real people, hotels, addresses or prices.
Do your orders live in chats, emails and paper?
Tell us how your day works now, and we will tell you which parts need AI and which need plain code.
Talk to us