Skip to content

Blog · Published · Updated

An extra freight charge: what was agreed?

Short answer

Automated freight cost reconciliation sets every charge on a carrier's invoice against the right transport order and its terms. The logistics employee sees the difference next to the passage of the order and has a basis for a question to the carrier. The judgement and the decision stay with a person. At Syntalith the system costs from €3,000 net and at 1,000 lines a month pays back in 2.0 months.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
net for the automation of one process, build paid once
from €3,000
from signing the contract to acceptance
2–6 weeks
free prototype on your cases
€0

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Transport and AI: statistics 2026

2.0 mo.

payback of a €3,000 check at 1,000 carrier invoice lines a month: €1,745 of work today, €269 with the system. Scenario.

Figures checked: 22 October 2026

Unloading with a tail lift was already in the order

The transport order clearly includes unloading with a tail lift as part of the service. On the invoice for that transport, the carrier lists it as an extra charge. The person checking the documents has to find the right order before asking about the charge.

A good comparison shows, next to the line, the transport number and the passage of the order that includes unloading in the price. The logistics employee opens both documents, checks that they concern the same service and asks the carrier where the separate charge comes from. They record the answer with the case, so the billing team sees what was agreed.

From an invoice line to a question for the carrier
  1. 01LineA charge from an invoice that covers many transports.
  2. 02TransportA reference that leads to a specific order, besides the carrier and the month.
  3. 03Order versionThe version accepted for delivery, if the client changed the order.
  4. 04ComparisonThe service described on the invoice next to the terms of the order.
  5. 05ClarificationA question to the carrier and the answer recorded with the case.

If the agreed order is missing, it has to be found before the system compares anything. The workflow for checking changes to orders is described on the AI in transport and logistics page.

What freight invoice checks cost and when they pay back

Scenario: 1,000 carrier invoice lines a month
Today
1,000 lines × 3 min = 50 h (€1,745)
With the system, a person checks the output in 15% of the time
€262
Model, 1 call per case, Claude Sonnet 5.5
€7.11
Cost of one case
€1.75 today, €0.27 with the system
Saving
€1,476 a month

Payback of €3,000

2.0 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 2,500 input tokens and 300 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

The count includes only the checking time. Every undue surcharge cleared up before payment is an extra benefit we leave out, because its size depends on the carriers.

First check the transport management system

Transport management systems can reconcile expected freight costs with carrier invoices, as for example Microsoft's documentation on freight reconciliation describes.

What to choose
  • Charges and services are in order in the transport system

    configuration or integration

    €0

  • A few transports a month

    a spreadsheet and a manual comparison

    €0

  • Different invoice layouts and service descriptions from many carriers

    reading with AI and comparison with the order

    from €3,000

  • The difference needs a search through emails about the delivery

    an agent that investigates discrepancies

    from €3,000

A language model is not needed to match clearly described lines. If the system already confuses the fields of a document while reading it, the reading has to be fixed first. The wider search is described in the article on investigating invoice discrepancies.

How to measure the effect

Measure the number of surcharges challenged before payment, the time from receiving the invoice to the clarification and the number of cases in which the carrier corrected the invoice. Also record false alarms: lines the system flagged that matched the order. Too many false alarms will make the logistics team stop reading the flags.

After a few months the data shows which carriers most often add services outside the order. That is material for the next rate negotiations, with no automatic penalties.

A carrier who does not answer a question about a surcharge is a matter for the person who manages the relationship with them. The system records the question and the reply deadline, and the decision on payment stays with a person.

The first scope

Prepare for the call
  • One surcharge for which an employee had to look up earlier agreements
  • Where they found the order and whom they passed the question to
  • A chosen group of carriers or one invoice workflow
  • The format of invoices and orders, with no confidential data

To start, choose the carriers with the most invoices. That is where looking up orders by hand takes the most time and where you will see fastest whether the comparison works. Once the surcharges are cleared up, the data can feed a report of vehicle and order costs, which needs its own cost split rules.

Worked example · Scenario

How we count the payback: transport and logistics

We run the same count for your carriers in the free analysis.

€1,745

a month for retyping 1,000 CMR and POD documents

Payback: 2 mo.

3 minutes per document and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. We use it here in place of a transport sector wage. Model cost: 0.007617 USD per reading, measured in our system, which is about €0.0069 per document, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

This process can go on its own. You will check this on your cases before you pay.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 25, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI automations

This process can go on its own. You will check this on your cases before you pay.

The system takes over repetitive work from emails, documents and spreadsheets, and hands over uncertain matters to a human. A prototype for 20-100 cases that your team has already handled costs €0. You pay the other half of the price when the system reaches your goal.

See AI automations →
net for the automation of one process, build paid once
from €3,000
from signing the contract to acceptance
2–6 weeks
free prototype on your cases
€0

Questions

  • How do I check surcharges on a carrier's invoices?

    Link each invoice line to the right transport and compare the service described with the terms of the accepted version of the order. The carrier and the month are not enough when one invoice covers many transports.

  • How much does automating freight reconciliation cost?

    At Syntalith from €3,000 net. At 1,000 invoice lines a month and 3 minutes of checking each, it pays back in 2.0 months, counting an employee's checking and the model cost, at the EU average hourly labour cost according to Eurostat.

  • When is the transport management system enough?

    When charges and services are already in order in the system, its feature for reconciling costs with invoices, or an integration with the billing software, is enough. AI makes sense when carriers send documents laid out in different ways.

  • Does the system reject an invoice on its own?

    No. It shows the difference and the linked documents. The logistics employee judges the carrier's explanation and records the decision with the case.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
When we roll out ChatGPT, Claude or Copilot, you buy the licences directly from OpenAI, Anthropic or Microsoft and they invoice you. We add nothing to the licence.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.