Use cases by industry10 use cases
AI automation for logistics and freight forwarding
A European road forwarder gets quote requests by email in German, Polish, Italian and English, all day. Whoever answers first usually wins the load, so reps retype postcodes, loading meters and ADR classes into the TMS and Timocom instead of selling. Behind them, dispatch runs on a spreadsheet, CMRs and delivery notes arrive as phone photos, and the warehouse side bills storage from month-end exports.
Most AI built for freight is American. Augment, which raised an $85M Series A and integrates with McLeod PowerBroker, HappyRobot and Vooma serve US truckload brokers who price against DAT. Forwarders on CargoWise, Soloplan CarLo, Winsped or Transporeon, writing to carriers in five languages, are served far less well. That gap is where a freight quote desk that prices by your own margin rules, customs declaration drafting signed off by a licensed broker, and 3PL billing built from warehouse events earn their keep.
Eurostat's latest survey adds context: of EU enterprises that use AI, only about 6% apply it to logistics, the lowest share of any business function it measured. The software is old, the documents are messy and much of it has no API, which is exactly the integration work a custom build is for.
What I would build for logistics and freight
An agent for the shared inbox: every email sorted, answered or filed into the right system
Reads every email in your shared mailboxes, sends orders and invoices into the right system, drafts replies for approval, and flags fake bank-detail changes.
Microsoft 365 shared mailboxes / Gmail and Google Workspace / The ERP (Business Central in this example) / Teams or Slack / The AP flow and accounting system
Automating portals and legacy systems that have no API, with a person approving the final click
Keys data into insurer portals and API-less desktop systems with a computer-use model, logs every screen, and waits for a person to approve each submission.
Broker management system / Insurer and carrier portals / A legacy desktop ERP / Computer-use model (Copilot Studio, Claude or OpenAI) / Outlook
Freight quote requests in four languages, answered in minutes and priced by your own rules
Reads freight quote requests in your customers' languages, asks for what is missing, prices the lane with your margin rules, and sends or drafts the quote.
Outlook and Microsoft 365 / TMS (Soloplan CarLo, Transporeon, CargoWise or similar) / Freight exchange data (Timocom, Trans.eu; DAT in the US) / HubSpot or the TMS customer record / Truck routing API (PTV or HERE)
PDFs into rows: document data entry that sends only the doubtful fields to a person
Reads delivery notes, proofs of delivery and forms from an inbox or folder, checks each field against your TMS or ERP, and asks a person only about doubtful values.
Gmail and Google Drive / Excel and Google Sheets / TMS or ERP / OCR or vision model / Review screen
Turning a 40-tab dispatch spreadsheet into an internal tool with rules, roles and history
Moves daily planning off a 40-tab spreadsheet into a web tool with validated forms, roles and a full edit history, while people keep Excel for analysis.
Excel and Google Sheets / Postgres / Microsoft 365 single sign-on / The ERP or TMS / Slack
3PL invoices built from warehouse events instead of month-end spreadsheets
Computes storage, pick and pack and value-added service charges from WMS events and each client's rate card, drafts invoices, and explains any line a client questions.
The WMS (Extensiv, ShipHero, Logiwa or similar) / Excel or Google Sheets / Xero / QuickBooks Online / Client-facing breakdown
A customer portal where B2B clients track orders, download documents and ask questions
Each customer company gets its own logins, live orders and shipments from the ERP and carriers, every document in one place, and an assistant that sees only their data.
NetSuite / SAP Business One / Carrier APIs or the TMS / Document storage (SharePoint or a DMS) / Outlook and Microsoft 365
Customs declarations drafted from commercial invoices and packing lists, for the declarant to sign
Cross-checks shipment documents, reuses tariff codes from your accepted history, argues new ones with EU rulings, and drafts declarations for a declarant to sign.
Customs software (CargoWise, AEB, DAKOSY or similar) / ATLAS (Germany) or CDS (UK) / Outlook / Excel / EU TARIC and EBTI
Modernizing a 20-year-old Delphi or VB6 application with AI and tests, one module at a time
Documents what an old application really does, pins that behavior with tests built from real data, then replaces it module by module while it keeps running.
The legacy application (Delphi, VB6, Access, old PHP or .NET Framework) / SQL Server or Access database / Claude Code / The target stack / CI pipeline
Plain-English questions over your own database, with the SQL shown and checked
Answers plain-English questions from a read-only copy of your database, shows the SQL and definitions behind each answer, and asks when a question is ambiguous.
Postgres or BigQuery / dbt or plain SQL views / Metabase / Slack / Excel export
The retyping, chasing and billing behind every load
The spot quote race
Every request needs origin, destination, dates, loading meters or pallets, weight, ADR and temperature pulled out of free text. The model extracts; margin floors, fuel surcharges and key-account rules stay in code, and outlier lanes go to a rep.
Documents that arrive as photos
CMRs, delivery notes and proofs of delivery come in rotated, stamped and handwritten. PDF data extraction with per-field confidence sends only the unsure fields to a person, shown next to the image region they came from.
Billable events nobody billed
Storage per pallet per week, pick and pack, relabeling and returns handling go unbilled when rate cards live in contracts and invoices are rebuilt from WMS exports. Computing them from warehouse events, with an explanation per line, closes the leak and shortens disputes.
Portals and green screens
Shipping-line portals, customs systems and old dispatch software rarely offer an API. Automating a system without an API means computer use for the last mile, credentials in a vault and a person approving before anything is submitted.
What stays with a person, and what to buy
Customs signatures
A licensed broker signs every declaration. The system cross-checks invoice, packing list and bill of lading and suggests tariff codes with its reasoning; sanctions and restricted-goods hits always go to a person.
New carriers and changed bank details
A new subcontractor, or an email announcing a changed IBAN, is checked against the freight exchange profile, insurance documents and a known phone number, and a person approves. Fake-carrier and payment fraud cost too much to leave to a score.
US voice and check calls
For US brokers, HappyRobot, Augment and Vooma already answer carrier calls and run check calls. Buy them; a custom build there rarely beats a well-funded product.
Key accounts and rate floors
Quotes for key accounts, and anything below the lane's floor, are drafted for a rep rather than sent. Speed matters, but a wrong rate on a contract customer costs more than a slow one.
Software these builds usually connect to
The systems do not get replaced. The build sits across them, reads from them through their APIs, and writes results back.
CargoWise / Soloplan CarLo / Winsped / Transporeon / Timocom / Trans.eu / McLeod PowerBroker / Extensiv / ShipHero / Descartes / AEB / ATLAS
Frequently asked questions
Can AI answer freight quote requests automatically?
It can draft or send most of them within your rules. The model reads the email in whatever language it arrives, extracts the lane, dates, loading meters, weight, ADR and temperature needs, and asks for anything missing. Prices come from your lane history, market rates and margin rules in code, never from the model. Key accounts, dangerous goods and rates below your floor go to a rep.
Is there AI for European freight forwarders, not just US freight brokers?
Very little off the shelf. The funded tools, HappyRobot, Augment and Vooma among them, are built around US truckload brokers, McLeod and DAT. European forwarders on CargoWise, Soloplan CarLo or Winsped, using Timocom and Trans.eu, with carriers writing in Polish, German and Romanian, mostly need a custom integration on top of the TMS they already run.
Can AI read CMRs, delivery notes and proofs of delivery?
Yes, including phone photos, stamps and handwriting, provided every field carries a confidence score and the unsure ones go to a person. Extracted values are checked against the load in the TMS, such as consignee, date and pallet count, before anything is written back, so a misread date cannot trigger an invoice on its own.
Our dispatch runs on a spreadsheet. Should we replace it?
Not always. If the spreadsheet has one editor and simple rules, leave it, or move it to Airtable. Replace it when a dozen people edit it, formulas break silently and only one person understands it; then a small internal tool with roles, validation, history and Excel export is worth building, and people can keep Excel for analysis.