Counterparty checks: a profile with sources in a few minutes
The system collects a counterparty's data from company registers, gives the source of every fact and lists the gaps. An employee decides whether to work with them.
Automation, paid once
from €3,000 net
Test on your process: €0
You pay 50% after acceptance
How much do automatic counterparty checks cost, and when do they pay back?
Short answer
Automatic counterparty checks cost from €3,000 net. In our scenario they pay back in 3.4 months. Today, checking 60 counterparties by hand costs €1,047 a month. With the system, the same work costs €158. The criteria and the decision to work with a company stay with you. The system gathers the facts with their sources and shows what is missing. The test on your process is free.
Statistics
Counterparty checks and late payment statistics 2026
1 in 4
According to the European Commission (2023), late payments cause one in four bankruptcies in the EU.
According to the European Commission (2026), 90% of EU companies that use AI say people take the decisions. In those companies, 2% of decisions are fully automated.
The team gets back about 26 hours of work a month, or 3 working days, and the company €10,668 a year. We count after the time a person spends checking and after the model cost. In this scenario the check also avoids about €518 a month of losses on unpaid invoices (assumptions under “How we calculate it”).
60 × 30 min = 30 h × €34.90 = €1,047 a month. With the system, a person checks the output in 15% of the old time (€157) and the model costs €0.46. That leaves €158. The saving is €889 a month, so €3,000 pays back in 3.4 months. On top of that, avoided losses on unpaid invoices come to about €518 a month in this scenario. We leave them out of the payback.
Assumptions: 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.
An employee checks the company register and the VAT register
Team
Copies the data into a spreadsheet
Team
Does not record where each fact came from
Team
A year later nobody knows what was checked
Team
With the system
The counterparty's details go into the system
Team
Collects facts from company registers
AI
Marks gaps and name differences
AI
An employee decides whether to work with them
Person
The profile with its sources stays in the history
System
What stays with people: The criteria and the decision to work with a company stay with you. The system gathers the facts with their sources and shows what is missing.
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%
the system sends the answers itself, without human typing
time from the arrival of the e-mail to the ready response (median)
30 s
time from the arrival of the e-mail to the ready response (median)
e-mails that require a response receive a ready-made draft
100%
e-mails that require a response receive a ready-made draft
less work for every 1000 answers (estimate)
47 h
less work for every 1000 answers (estimate)
Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.
The counterparty profile system we have already built
It collects records from the Polish company register (KRS), Polish public tenders (BZP) and EU tenders (TED), gives the source of each fact and marks gaps and name differences for the analyst to decide. It holds back personal data before publishing. A simpler profile costs €0.009 of model work. Demonstrator on public data.
“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.”
You choose the test cases. We anonymise them on request.
They stay in the EU and we delete them after the test.
We sign the NDA and the data processing agreement before we receive anything.
After acceptance you keep the code, the test set and the documentation. You pay for licences and model usage directly to the provider.
Questions
How much does automating counterparty checks cost?
From €3,000 net, paid once. After the 5-day test the build takes 2 to 6 weeks. You get a fixed price before the contract: 50% on signing and 50% after acceptance on your own profiles.
Does the system rate a counterparty's reliability?
The system gathers the facts and marks the signals to check against your criteria. An employee makes the assessment and the decision to work with them.
Would a manual check in the company register be enough?
With a few counterparties a month, it is enough. The system makes sense when checks are regular and an audit needs a record of what was checked and when.
When does it not pay off?
Below 17 profiles a month the payback takes more than a year. Then it is better to start with ChatGPT or Claude for the team, from €1,150 net.
What do we need to prepare?
A list of the sources you check today, your criteria for accepting a counterparty and 20 to 100 profiles from recent months, including rejected ones.
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.
Claude 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.
customer service
