Skip to content

Blog · Published · Updated

AI invoice coding: from a proposed entry to the ledger

Short answer

A model that names an account and an amount has prepared a proposed entry. An entry in the books needs a check of the source document, the agreed rules and control of the whole workflow, which Articles 20, 21 and 24 of Poland's Accounting Act describe. The accountant approves the proposal. At Syntalith the automation costs from €3,000 net, and with 1,000 cost invoices a month at 3 minutes each it pays back in 2.3 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
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

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

Accounting and AI: statistics 2026

2.3 mo.

payback of a €3,000 automation at 1,000 cost invoices a month: €1,745 of work today, €444 with checking and the model. Scenario.

Figures checked: 22 October 2026

AI invoice coding: a similar invoice, a different treatment

The same supplier issues invoices for two different services: machine servicing and staff training. The model proposes the account used for the previous invoice, because the supplier's name matches. A similar name does not settle the accounting treatment, and an accountant who approves the proposal without opening the description will book the training as servicing.

The proposed view shows the fields read, the document and the basis for the suggestion: which earlier invoice the model judged similar and why. When the description does not settle the treatment, the gap becomes a question for the accounts team. In Poland, Article 20(5) of the Accounting Act sets the conditions for computer records to count as equivalent to source documents, Article 21 describes checking a document and qualifying it for entry in the books, and Article 24 requires the books to be reliable, verifiable and kept up to date. The responsibility of the head of the entity under Article 4(5) stays when the books are entrusted to another person.

From the document to the entry
  1. 01Documentan invoice from KSeF or a PDF with a source identifier
  2. 02Proposalaccount, amount and the basis for the suggestion
  3. 03Checkthe accountant approves or corrects, with a reason
  4. 04Entrythe accepted entry in the system with the rules version
  5. 05Correctiona new document linked to the original entry

The test covers the path from the document to the entry in the system: a repeated document, a correction and an interruption after the data is passed on. A retry does not create a second entry without a check.

What automated invoice coding costs and when it pays back

Scenario: 1,000 cost invoices a month
Today
1,000 cost invoices × 3 min = 50 h (€1,745)
With the system, a person checks the output in 25% of the time
€436
Model, 1 call per case, Claude Sonnet 5.5
€8
Cost of one case
€1.75 today, €0.44 with the system
Saving
€1,301 a month

Payback of €3,000

2.3 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: 3,000 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 each case: searching, reading, writing and handing over. What remains is the time to check the result, 25% of today's work in the scenario. Before the quote we measure both times on 20 to 100 cases the team has already handled, in a free test that takes 5 working days.

In this process the most expensive mistake is one approved without reading. So in the test we count the proposals the accountant corrected and those where the model flagged uncertainty. If there are more corrections than with manual coding, the scope goes back to the rules.

Where the project ends

Before you order, settle whether the project ends at a proposal, prepares an import or makes the entry. These options need different controls and access. The safest start is a proposal with its basis and the accountant's approval. Our invoice coding demo shows the mechanism of a proposal with a cited precedent.

What to choose for which workflow
  • Regular suppliers, one treatment

    coding rules in the system

    configuration

  • Proposals for the accountant to approve

    an automation of proposals with their basis

    from €3,000

  • Import or entry with no retyping

    an integration with workflow control

    priced after the review

Where to start

We run the first test on invoices from a closed month and compare the proposals with the entries the accounts team accepted. We build this kind of system as part of our AI automations. For the free process review, a description of one case from the last few weeks and the tools it went through is enough. You do not need to send confidential documents, and you receive a written plan within 2 working days.

Worked example · Scenario

How we count the payback: cost invoices

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

€1,745

a month for coding 1,000 cost invoices by hand

Payback: 2 mo.

3 minutes per invoice 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 ↗

Start with the process that takes the most time each week.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 implementation

Start with the process that takes the most time each week.

The engineer chooses one process with you and calculates how much it costs today. Then we build a free prototype on 20-100 cases that your team has already handled. We write down the goal and the fixed price in the contract.

See AI implementation →
analysis with an engineer and a free prototype
€0
team in ChatGPT or Claude, up to 10 people
from €1,150
automation, agent or application for one process
from €3,000

Questions

  • Can AI code invoices?

    It can propose an account and an amount with the basis for the suggestion. In Poland, an entry in the books needs the document to be checked and approved by the accountant under the Accounting Act.

  • Who is responsible for the books when you automate?

    The head of the entity, under Article 4(5) of Poland's Accounting Act, also when bookkeeping is entrusted to another person. The choice of software does not change that.

  • How much does such an automation cost?

    At Syntalith from €3,000 net. With 1,000 cost invoices a month at 3 minutes each, the payback is 2.3 months. We agree integrations and maintenance before the quote, and the model costs €8 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.