United Transportation was drowning in email-based dispatch requests. Dispatchers spent their entire day reading emails, extracting shipment data by hand, updating boards, coordinating drivers, and manually generating status reports. Volume was growing. Errors were creeping in. The team had no bandwidth for anything that actually required human judgment.
"Dispatchers were spending their entire day reading emails and copy-pasting data. Now the system handles the routine work and our team focuses on what actually needs a human."
The dispatch team at United Transportation processed a high volume of inbound shipment requests via Microsoft Outlook every day. Each email contained unstructured AWB (Air Waybill) data, pickup details, and special handling instructions. Dispatchers had to read each email, manually extract all relevant fields, update a shared Notion dispatch board, assign a driver, send a confirmation, and follow up with status reports throughout the day.
As volume grew, this process became the primary constraint on the business. Critical details got missed. Assignments were delayed. The team was reactive instead of operational — spending their days on data entry rather than the judgment calls that actually required them.
Standard workflow tools like Power Automate handle structured data well — but inbound emails from freight clients don't arrive in a consistent format. Every shipper writes differently. Some embed AWB numbers in the subject line. Others bury them in a block of unstructured text. Some include special handling instructions in a P.S. A rules-based system would require constant maintenance and would still miss edge cases.
What the team needed wasn't pattern-matching — it was something that could read, understand, and make decisions. That's the gap AI agents fill.
We built five specialized agents that together handle the complete dispatch workflow — from email inbox to client status report — without dispatcher involvement for routine requests.
Monitors the shared Outlook inbox, classifies incoming emails by type (new dispatch request, driver update, client inquiry, other), and routes each to the appropriate agent or human queue.
Reads Excel attachments that accompany multi-shipment requests, extracts all shipment rows, normalizes the data structure, and passes clean records downstream for processing.
The core agent. Reads each classified email, extracts all AWB data, pickup details, special instructions, and deadlines. Validates completeness, flags missing information, and creates a structured record in the Notion dispatch board.
A purpose-built mobile interface for drivers to check in and check out at airport pickup locations. Timestamps each event, updates driver status in Notion in real time, and alerts dispatchers of any delays automatically.
Pulls live data from the Notion dispatch board and generates professional HTML status reports for clients and internal stakeholders. Reports are formatted, timestamped, and distributed automatically — no manual assembly required.
We didn't ask United Transportation to change a single tool. We built automation that connected the environment they already had — Microsoft, Google, and Notion — into one seamless system.
Outlook email as the inbound request channel · Excel spreadsheet attachments processed automatically
Google Sheets for customer data and reporting · Running seamlessly alongside the Microsoft environment
Central dispatch board and operational database · Real-time source of truth for the entire workflow
We work in your world, not ours. Most SMBs have a mix of Microsoft, Google, and other tools that have built up over years. We don't ask you to change that. We build automation that connects what you already have — so your team keeps working the way they know, and the repetitive work disappears.
You started a business to build something — not to be a data entry clerk. Let's find what's eating your time and show you what to do about it.
Get Your Free Drudgery Report →Or email us directly: contact@workanewway.com