Skip to content

Blog · Published · Updated

Optima: KSeF, OCR or a custom automation?

Short answer

Before you buy automation around an accounting program, separate three tasks: receiving the invoice from KSeF, reading the image of a document and preparing the information the accountant needs. They use different features and licences, and an invoice available in KSeF needs no second reading from an image. At Syntalith an automation costs from €3,000 net, and with 1,000 invoices a month at 3 minutes each it 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, 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

KSeF in Poland: statistics 2026

2.0 mo.

payback of a €3,000 automation at 1,000 invoices a month: €1,745 of work today, €269 with checking and the model. Scenario.

Figures checked: 22 October 2026

KSeF and OCR meet different needs

KSeF is Poland's national e-invoicing system. The program vendor's OCR reads data from scans and photos and loads invoices into the VAT register or the sales module with the status of a document to verify (vendor help: OCR). If the invoice is already available in the KSeF flow, first check how its data is used in the program: reading the image again should not be the default step just because a supplier offers OCR. For KSeF licensing the vendor requires the right program version and updates (vendor help: KSeF licensing), so you base the budget on a specific installation.

An example: an accounting firm receives one message with attachments for two of the companies it serves. Amounts and supplier names were read correctly, and before passing them on the documents have to be assigned to the right company. The automation prepares the split for approval, showing the buyer's identifier and a passage of the comment.

Part of the budgetWhat to settle
The program and the vendor's packagesthe modules you hold, the period and the billing method
Preparing the installationthe version, updates and the administrator's support
The new flowthe sources of documents, questions and employees' answers
The connection to the programreading, where results are written and confirmation of the result
Acceptance and maintenancetest cases, fixes and changes
Three tasks, kept apart
  1. 01Receiptan invoice from KSeF in the program, with no second reading
  2. 02ReadingOCR only for documents outside KSeF
  3. 03Assignmentthe document to the right company and flow
  4. 04Explanationthe cost description for the accountant's decision
  5. 05Accepting the scopeone company's documents never reach another

What KSeF and OCR automation costs and when it pays back

Scenario: 1,000 invoices a month
Today
1,000 invoices × 3 min = 50 h × €34.90 = €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
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 covers the work around a case: searching, reading, writing and passing it on. What stays is the time to check the output, 15% of today's work in the scenario. Before we quote, we measure both times on 20 to 100 cases your team has already handled, in a €0 test that takes 5 working days.

Before you order a build, you can also compare classifying documents by type and company with ready services, for example a custom classifier in Document Intelligence.

A custom automation or the program's features

Do not add up packages based on similar names. Ask your account manager for a list of the features covered by the contract and a separate quote for the missing elements, because the vendor's terms depend on the configuration. A custom automation makes sense for work the program does not cover: assigning documents for an accounting firm's many clients, gathering the cost description from correspondence or questions to employees. With unambiguous data a rule is enough, and a model is assessed on free-text correspondence. The cost of the module, configuration and an extra flow is compared in what KSeF automation costs.

The program's feature or your own flow
  • Invoices from KSeF, few scans

    the program's KSeF features

    the vendor's licence

  • Scans from outside KSeF

    the vendor's OCR or your own reading

    a licence or from €3,000

  • Many companies, cost descriptions from correspondence

    a custom automation before the import

    from €3,000

Where to start

Agree the scope of access with the person responsible for accounting. The acceptance trial shows that one company's material never appears in another client's set. The scope is described in AI around an accounting program. We build this kind of rollout as part of AI automations. For the free process review, a description of one case from recent weeks and the tools it went through is enough. You do not need to send confidential documents, and you get a written plan within 2 working days.

Worked example · Scenario

How we count the payback: invoices from KSeF

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

€1,396

a month for checking 600 invoices from KSeF by hand

Payback: 2.5 mo.

4 minutes per invoice (a check against the order and the cost description) 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 €0.004 per invoice in our invoice coding system, converted 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 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

  • Do you still need OCR after KSeF?

    Usually not for invoices available in KSeF, because their data is already structured. OCR stays for documents outside KSeF, for example scanned receipts or foreign invoices.

  • What should you automate around an accounting program?

    Work the program does not cover: assigning documents to the right company in an accounting firm, gathering the cost description from correspondence and questions to employees. Check the program's features before the quote.

  • How much does such an automation cost?

    At Syntalith from €3,000 net. With 1,000 invoices a month at 3 minutes each, the payback is 2.0 months. We agree integrations and maintenance before the quote, and the model costs €7 a month.

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.