Skip to content

Blog · Published · Updated

Private AI for answering payroll questions

Short answer

A private AI assistant for payroll gathers the right payslip and the internal decision record for an employee's question, and drafts a reply. The reply describes what follows from the documents, and a payroll specialist checks and sends it. At Syntalith an application on a local model costs from €3,000 net plus GPU hardware. At 400 payroll questions a month of 15 minutes each, it pays back in 1.2 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
model on your server or in the cloud in the EU
quoted after the review
same work in application with EU cloud model
from €3,000
task, data and equipment analysis
€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

HR, payroll and AI: statistics 2026

1.2 mo.

payback of a €3,000 local application at 400 payroll questions a month: €3,490 of work today, €1,087 with checking and the GPU server. Scenario.

Figures checked: 22 October 2026

A question about a bonus that still waits for a decision

An employee asks why their bonus is missing. The specialist checks the payslip for the period: there really is no bonus on it. In the internal register she sees that the decision has not been made yet. The assistant shows a summary with links to both sources and a draft: „There is no bonus on your payslip for this period. I checked the status: the decision on it has not been made yet.” The reply does not decide what is owed or when it will be paid, and the specialist sees which decision is missing.

Employees describe their questions in their own words: one asks about a missing item, another about a difference from last month. A document from another period does not explain the current question, and a record about another person can never be the basis of a reply, even when it holds the same words. The view links the question to the period and to that person's documents.

A payroll question to a reply
  1. 01Questionthe employee's words and the period it concerns
  2. 02Payslipthat person's document for that period
  3. 03Registerthe internal record of the decision, or of its absence
  4. 04Drafta reply built from what the documents show
  5. 05Sendingthe specialist checks and sends

What it costs and when it pays back

Scenario: 400 payroll questions a month
Today
400 payroll questions × 15 min = 100 h (€3,490)
With the application, a person checks the output in 25% of the time
€873
Hardware in the company, counted in the scenario as a rented GEX45 server
€214
Saving
€2,403 a month

Payback of €3,000

1.2 months

The volume, the time and the checking share are the scenario's assumptions, which we measure in the test. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. The price of the GEX45 with 24 GB of GPU memory is from Hetzner's website on 22 October 2026, without the one-off setup fee of €209. We price hardware in your own server room after the analysis.

The count covers the time spent searching, reading and putting material together. What remains is the time to check the result against its source, 25% of today's work in the scenario. We measure both times in a test on 20 to 100 cases the team has already handled.

What runs locally and what you have to agree

In the local version, the model runs on a named computer or server. Ollama describes a local mode with the cloud models switched off, but that covers the program that runs the model. A passage from a payslip can stay in the material prepared for search, and case details in a saved draft or a log, so the administrator and the process owner agree access and retention. You also need a person who handles updates and the problem when the application does not show the right document.

What to agree with IT beyond the model
  • Where the application takes documents from and where it saves results
  • What stays in logs, backups and the question history
  • Who has access to questions, answers and summaries
  • Who updates the model, the application and the document set

What the employee portal can already handle

If the questions are mostly about where to download a payslip or what the fixed descriptions mean, a portal and approved answers are enough. A model is worth considering when the messages vary and a reply needs several records gathered and explained in plain words. The assessment covers the work after the text is generated: checking sources, corrections and preparing the message. The administrative work of HR is described in AI in payroll, and the rules for answers with sources in an assistant on company documents.

Portal, templates or an assistant
  • Questions about where the payslip is and fixed descriptions

    a portal and approved answers

    no build

  • Varied questions, sensitive data

    a private assistant for payroll

    from €3,000 plus hardware

  • Questions from HR and documents too

    an assistant for HR and payroll with permissions

    priced after the analysis

Where to start

The first scope covers one type of question, for example bonuses and allowances, and one person from payroll who judges the drafts. The administrator and the process owner agree access and retention. We deploy local models as part of private LLMs, and we build the view for working with sources as an AI application. For the free analysis, a description of one case and of the places where the material sits is enough. Confidential files stay in the company, and you get a written plan within 2 working days.

Worked example · Scenario

How we count the payback: a payroll team

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

€2,908

a month for handling 1,000 employee documents by hand

Payback: 1.2 mo.

5 minutes to receive and check an employee 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. Model cost: reading a document in our case file system (about €0.0002) plus a description of what is missing (Claude Sonnet 5.5, about 2,000 + 300 tokens), 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 ↗

A model on your server or in the cloud in the EU, proven on your tasks.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 →

Private AI models

A model on your server or in the cloud in the EU, proven on your tasks.

We select the model and equipment for the task, run it and measure the quality using your examples before you buy anything. The data stays in the company or in the cloud in the EU. We price implementation, hardware or hosting and support separately after analysis.

View private AI models →
model on your server or in the cloud in the EU
quoted after the review
same work in application with EU cloud model
from €3,000
task, data and equipment analysis
€0

Questions

  • Can AI answer employees' payroll questions?

    It can prepare a draft from the payslip and the internal records of that person for the right period. A payroll specialist checks the sources and sends the reply. The assistant does not decide what is owed or when it is paid.

  • Where should payroll data be processed for AI?

    In an environment the company sets, for example its own server. Beyond the model, the agreement has to cover the material prepared for search, saved drafts and the application's logs.

  • How much does such an application on a local model cost?

    At Syntalith from €3,000 net plus GPU hardware, for example a Hetzner GEX45 server with 24 GB at €214 a month. At 400 payroll questions a month, the payback is 1.2 months.

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.