ℹDemonstration scenario. An example of a possible implementation, not a completed client project of Neural2B.

Automation of Logistics Request Processing

Demonstration scenario: extracting transportation parameters from emails and forms, verifying addresses, cargo, and timelines, preparing a draft order for the dispatcher.

Business situation overview

A logistics company receives hundreds of emails daily in various formats: 'calculate the route', 'pick up the cargo'. Dispatchers manually copy cities, warehouse addresses, dimensions, and sender's phone numbers. Responses are delayed. Clients turn to competitors.

Data flow and architecture diagram

1Input stream: logistics department email (IMAP / MS Graph API)

2Email and attached Excel/PDF file parser

3Address normalization module (cross-references with the database of populated areas in Ukraine)

4Tariff module: preliminarily calculates mileage and estimated cost

5TMS / CRM of the company: here the draft flight appears

The human role in the loop (Human-in-the-loop)

Before naming a rate to the client or confirming the loading of the vehicle, the dispatcher reviews the filled draft.

Synthetic test data

Example input and system response

User input request:

"Hello. We need to transport 14 pallets, total weight 8 tons, household chemicals (non-hazardous cargo). Loading: Kyiv, Pyrohivskyi Shliakh St., 34, on Friday by 14:00. Unloading: Dnipro, Budivelnykiv St., 28, on Monday morning. Calculate the cost of the tent."

Generated response / system action:

"Draft flight No. KIEV-DNIP-8T has been created: Route: Kyiv → Dnipro (~480 km); Cargo: 14 pallets, 8,000 kg; Body type: tent; Loading window: Fri by 14:00; Rate according to the tariff grid: calculated. Status: awaiting dispatcher review."

Limits of the demo scenario

✕The final rate is determined by the responsible logistician
✕Hazardous cargo (ADR) is automatically flagged for separate document verification
✕If details are missing, the system prompts for clarification

What to measure during pilot testing

✓Time from email to filled order card
✓Error rate in recognizing addresses and dates (target: < 2%)
✓How many times the dispatcher had to make manual corrections

Relevant company service

Document Processing Automation

Service overview →

Interested in a similar architecture?

We’ll adapt the logic of this scenario to your internal software, database structure, and operating rules.

Discuss adaptation

Other scenarios

Scenario adaptation: Automation of Logistics Request Processing

Describe the process that’s eating up your team’s time. We’ll suggest what can be automated, what data is needed, and where to start.