Skip to content

Blog · Published · Updated

An AI knowledge base for shared service centers

Short answer

An AI knowledge base in a shared service centre joins the shared procedure with the annex of the unit being served into one answer that tells the employee what to prepare. It first establishes the unit, because the language of the question does not reveal it. Requests stop coming back incomplete. At Syntalith the app costs from €3,000 net. At 1,500 requests a month with 5 minutes of checking each, it pays back in 0.8 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 per application, fixed price before contract
from €3,000
from signing the contract to acceptance
4–10 weeks
free prototype on your documents
€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

Service centres and AI: statistics 2026

0.8 mo.

payback of a €3,000 app at 1,500 SSC requests a month: €4,362 of checking procedures today, €673 with the app. Scenario.

Figures checked: 22 October 2026

One answer from two documents

A shared service centre handles supplier data requests for two units in different countries. Both use the shared request form from the procedure. The current annex for one of them also requires a project code and a handover of the request to the project coordinator.

The employee asks in Polish, so the assistant first establishes which unit they serve. The requirements of both units are the company's internal arrangements, so the source of truth is the approved annex that the process owner maintains. Two links without the content joined would leave the employee comparing documents at every request.

Why finding the general procedure is not enough

When an SSC takes on more units, the shared procedure does not cover every arrangement. An experienced colleague remembers the annex, while a new employee follows the main instruction and the gap shows up at the recipient's end.

Who maintains the answer
  1. 01Process ownerNames the approved material and how the annex relates to the unit.
  2. 02ChangeWhen the coordinator stops checking requests, the owner updates the annex.
  3. 03ConflictTwo documents describe a task differently, so the assistant shows both passages.
  4. 04QuestionThe employee sends the case to the process owner.

What an SSC knowledge base costs and when it pays back

Scenario: 1,500 SSC requests a month
Today
1,500 requests × 5 min = 125 h (€4,362)
With the system, a person checks the output in 15% of the time
€654
Model, 1 call per case, Claude Sonnet 5.5
€19
Cost of one case
€2.91 today, €0.45 with the system
Saving
€3,689 a month

Payback of €3,000

0.8 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: 5,000 input tokens and 400 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

Every request that comes back to be completed means opening the case a second time on both sides. That is why the trial counts the preparation time and the number of requests sent back by the recipient, before the rollout and after it. Employees judge whether the answer let them prepare the request without asking their team lead.

What your current tools can provide

First check whether the form already shows the unit's requirements and whether the procedure page leads to the right annex. Microsoft describes SharePoint knowledge sources in Copilot Studio, which respect existing permissions. The assistant does not automatically search documents reached through links, so an annex kept as a separate file has to be added to the sources.

Form, library or app
  • The form shows the unit's requirements

    better access to the explanations

    no new app

  • The procedure leads to the annex

    a tidied procedure page

    configuration

  • The answer is built from documents in different places

    an AI app that joins the sources

    from €3,000

Retrieval decides the quality of the answer: according to Anthropic (2024), contextual embeddings with BM25 cut failed retrievals by 49% (Contextual Retrieval). When employees find the answer but struggle to pass it to colleagues in another language, training for multilingual shared services teams will help. The first scope is answers from documents for a few units in one process. For the call, bring a case that came back because a unit's requirement was missed, and the name of the library that holds the procedures.

Worked example · Scenario

How we count the payback: answers from company documents

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

€3,723

a month for finding answers to 800 questions in documents

Payback: 1 mo.

Our assumptions are 8 minutes to find an answer in documents or ask a colleague, and checking in 15% of the old time. €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: Claude Sonnet 5.5, about 6,000 + 500 tokens per answer from documents, 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 ↗

When an off-the-shelf tool does not fit, we build your own.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 →

Custom AI apps

When an off-the-shelf tool does not fit, we build your own.

We build an application with a language model for the work of your team: searching the company's knowledge, case panel or portal. We check the validity of your documents before launch, and the code stays with you.

See AI applications →
net per application, fixed price before contract
from €3,000
from signing the contract to acceptance
4–10 weeks
free prototype on your documents
€0

Questions

  • How does an AI knowledge base help a shared service centre?

    It joins the shared procedure with the annex of the unit being served and answers what exactly to prepare. A new employee no longer learns about the annex only when the request comes back from the recipient.

  • Is Copilot Studio enough for this kind of knowledge base?

    Copilot Studio lets you choose SharePoint knowledge sources with existing permissions respected. It does not automatically search documents that the material links to, so an annex kept as a separate file has to be among the sources.

  • How much does a knowledge base for an SSC cost?

    At Syntalith an AI app on documents costs from €3,000 net. At 1,500 requests a month of 5 minutes each, the payback is 0.8 months.

  • What if two documents describe a task differently?

    The employee sends the question to the process owner, and the assistant shows the conflicting passages. The owner updates the material when a unit's requirement changes.

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.