Skip to content

Blog · Published · Updated

Counterparty verification: the cost of automation

Short answer

Checking a bank account in Poland's VAT payer register often needs neither AI nor an app of your own. Automation makes sense when an employee regularly retypes identifiers, saves confirmations and links them to a case in another system. At Syntalith it costs from €3,000 net. At 600 checks a month at 6 minutes each, it pays back in 1.7 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, 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

Automation in companies: statistics 2026

1.7 mo.

payback of a €3,000 automation at 600 counterparty checks a month: €2,094 by hand, €317 with checking and the model. Scenario.

Figures checked: 22 October 2026

Start with the question the source answers

Poland's Ministry of Finance describes a search in the VAT payer register (the „white list”) for a chosen day and a check of the link between a NIP or REGON number and a bank account. The result comes with an electronic confirmation of the query (the Polish tax administration's guide).

The register answers the question about the data in the register. It does not say whether a company will pay, deliver a service, or whether a message about a changed account comes from an authorised person. Do not add those conclusions in an AI summary. The company settles the legal scope of the checks with its own specialists.

Rules or AI
  • A few checks a week

    the search in the register

    €0

  • A fixed identifier, the confirmation saved with the case

    automation on rules

    from €3,000

  • Correspondence in many shapes and a description of discrepancies

    automation with AI

    from €3,000

No answer is a separate state

A purchase list contains two entities with similar names. One has a correct NIP, the other only a shortened name. The first goes to the check, and the second needs its identity established before it gets a result.

StateWhat to keep with the case
Result receivedParameters, the day of the data, the time of the query and the confirmation
Incomplete identifierThe missing field and a question for the person who raised the request
Source unavailableA note of the failed attempt and the next step
Data changedThe previous result and the reason for a new check

An empty answer must not turn into „not found” or „checked”. If the project supports an AML procedure, first separate collecting data from the duties of an obliged entity.

What it costs and when it pays back

Scenario: 600 counterparty checks a month
Today
600 checks × 6 min = 60 h (€2,094)
With the system a person checks the output in 15% of the time
€314
Model, 1 call per case, Claude Sonnet 5.5
€3
Cost of one case
€3.49 today, €0.53 with the system
Saving
€1,777 a month

Payback of €3,000

1.7 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: 1,500 input tokens and 300 output tokens per call at Anthropic's rates, at the ECB rate of 1.1205 USD per euro on 22 October 2026.

The model is a small item here, because rules handle the query by identifier. AI works on the correspondence and the discrepancies. Add access to paid sources and upkeep after an interface change to the budget.

What raises the cost of the project

What the quote depends on
  • Number of sources

    one or several

    Each register has a different interface, limits and access terms.

  • Frequency

    once or on a cycle

    Checking again before a payment is different work from checking when a relationship starts.

  • Where it is saved

    the case in your system

    The confirmation has to reach the right case with the date and the parameters.

An account number from an email needs the request itself confirmed, as we describe in workflows for bank detail changes.

How to order the first scope

The first scope
  1. 01SourceChoose one source and one decision an employee makes.
  2. 02CasesFictitious cases with complete data, an ambiguous entity and a reading error.
  3. 03BasisAgree how to reproduce the basis of a result.
  4. 04StopDecide when work stops because information is missing.

Syntalith builds a counterparty verification workflow with separately agreed access to the sources. For the conversation, a description of your current check is enough, without a supplier list or account data. When the quote concerns one company and the order comes from another, see comparing buyer data in B2B sales.

Worked example · Scenario

How we count the payback: counterparty verification

We run the same count for your process in the free process review.

€1,047

a month for checking 60 counterparties by hand

Payback: 3.4 mo.

30 minutes to check a counterparty 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 measured the model cost of the simpler profile, €0.009, in our counterparty profile system, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026. Avoided losses are a scenario: we assume that 1 in 800 counterparties checked is a company that would not have paid, and that the check protects €6,900 on average. In the review we calculate it on your receivables.

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 21, 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, paid once
from €3,000
from signing the contract to acceptance
2–6 weeks
free prototype on your cases
€0

Questions

  • How much does automating counterparty verification cost?

    At Syntalith from €3,000 net per process. We price access to paid sources and upkeep after an interface change separately. At 600 checks a month at 6 minutes each, the payback is 1.7 months.

  • Do you need AI to check an account in the VAT payer register?

    Usually not. Plain rules handle a query by a fixed identifier and saving the answer. AI makes sense with correspondence that comes in many shapes and with describing discrepancies.

  • What does Poland's VAT payer register show?

    Poland's Ministry of Finance describes a search for a chosen day and a check of the link between a NIP or REGON number and a bank account, with an electronic confirmation of the query. The register does not say whether a company will pay or whether a request to change an account is genuine.

  • What if the register does not respond?

    Show it as a separate state. An empty answer must not turn into „not found” or „checked”. The employee sees the failed attempt, and the system repeats the query by the agreed rules.

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
You buy accounts directly from OpenAI or Anthropic and receive an invoice from them. We do not add anything to the license.
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.