Case study
Internal toolTruckPulse
Automated load-profitability and dispatcher-performance monitoring for a trucking company, built from Gmail broker PDFs and Telegram driver-rate messages.
FIG. 001 / ARCHITECTURE
How the system connects
Live model
Problem
A trucking company's director had to manually cross-reference thousands of broker confirmation emails (10-15 different PDF formats) against messages from roughly 400 driver Telegram groups to catch loads booked below a minimum profitable rate — a volume of matching that was humanly impossible to do reliably across 80+ dispatchers.
System
Background workers parse incoming Gmail broker-confirmation PDFs and monitor the dispatcher Telegram groups through a dedicated bot account, match each load by its load number across both sources, and calculate rate-per-mile and margin per deal against a configured minimum. A Python backend (SQLAlchemy/Alembic, background workers) and a TypeScript dashboard, deployed behind nginx/systemd, surface flagged bad deals and per-dispatcher performance.
FIG. 002 / HOW IT WORKS
How it works
TruckPulse is a client automation project: a monitoring system built for a trucking company running around 400 trucks and 80 dispatchers, where bad deals were previously discovered too late because no one could manually watch every broker email and driver channel at once. It ingests unstructured data from two very different channels (PDF attachments and Telegram chat), reconciles them by load number, and turns a "thousands of emails and hundreds of chats per day" problem into an automatic profitability and performance feed for the person running the company.
Stack
What it runs on
Related systems
UBA-BRAIN
Internal toolA shared markdown knowledge base and rule system that lets any AI CLI on any machine run the same client work with the same rules, memory and skills.
AI Product Visuals Pipeline
Internal toolA skill-driven pipeline that turns a client's chat request into an on-brand AI product photo, picking the right account, model and reference automatically.
IshFlow
Internal toolInstagram DM automation and lightweight CRM that lets a small seller manage customers, catalog and orders entirely from a Telegram bot.
Want a system like this for your team?
We start by mapping one workflow on a 30-minute call.