Skip to content

Blog · Published · Updated

AI knowledge sources after their author leaves

Short answer

When the author of documents leaves, the company assistant can lose a source, because the manual it answers from sits on their personal drive. So handing over duties also covers AI sources: moving chosen documents to the team library, a new owner and a check of the connection. At Syntalith an AI app on company documents costs from €3,000 net. At 150 questions about moved material a month, with 15 minutes of searching each, it pays back in 2.7 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

AI knowledge bases: statistics 2026

2.7 mo.

payback of a €3,000 app at 150 questions about moved material a month: €1,309 of searching today, €198 with the app. Scenario.

Figures checked: 22 October 2026

The file is needed, and its author is leaving

An events coordinator keeps the guide to ordering company materials on their own drive. They shared it with the department, and it was connected to the internal assistant. Before leaving, they give their successor the warehouse contact and the list of open orders, and nobody remembers that the assistant reads the guide from their account. Once the account is switched off, the assistant stops finding the answer.

AI sources in a hand-over of duties
  • A list of the documents the assistant answers from
  • Which of them sit on a personal drive
  • App connections that depend on a specific person's account
  • A new owner for each item

The whole personal drive does not go into the shared base automatically, because it may hold working notes and private files. The department names the material its daily work relies on, and the new owner can correct it and report problems with answers. If important explanations exist only in the leaver's memory, a separate conversation about handing over knowledge is needed.

What keeping AI knowledge sources after an author leaves costs and when it pays back

Scenario: 150 questions about moved material a month
Today
150 questions about moved material × 15 min = 37.5 h × €34.90 = €1,309
With the system, a person checks the output in 15% of the time
€196
Model, 1 call per case, Claude Sonnet 5.5
€2
Cost of one case
€8.73 today, €1.32 with the system
Saving
€1,111 a month

Payback of €3,000

2.7 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: 6,000 input tokens and 500 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro.

The model is a small item here. What decides the result is the time searching and asking around takes today, and how much of it is left for checking the answer. In the scenario we count the questions that, after the author leaves, go to colleagues because the assistant cannot find the source, and the time spent searching for a copy of the file.

Before pricing the build we run a test on 20 to 100 questions the team has already asked: we compare the app's answer with what an employee found by hand and count the time from question to source. The test takes 5 working days and costs €0.

A retention period is not enough

Microsoft describes the OneDrive retention period after a Microsoft 365 user is deleted. It is a helpful admin setting, and it chooses no material and moves nothing to the team library. If the company has a working process for handing over files, and the assistant uses only shared libraries, a separate project is unnecessary and adding AI sources to the hand-over list is enough.

A list, a review or a project
  • The assistant reads only shared libraries

    AI sources on the hand-over list

    no project

  • Some sources sit on personal drives

    a review of sources before someone leaves

    as part of maintenance

  • Connections depend on many people's accounts

    rebuilding connections onto team libraries

    from €3,000

Where to start

The first step is a list of the assistant's sources with the owner of each, made before a planned departure. Knowledge nobody wrote down is covered in the piece on handing over an expert's knowledge.

For the first call, one question that regularly goes back to colleagues and a note on where the team looks for answers are 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: answers from company documents

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

€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

  • What happens to the AI assistant when the author of documents leaves?

    Chosen documents move from the personal drive to the team library, the assistant gets a new connection, and every item a new owner. Without this, the assistant loses the source once the account is switched off.

  • Is a file retention period after someone leaves enough?

    No. Retention keeps files for a while, and it chooses no material, moves nothing to the team and does not change the assistant's connection.

  • How much does such an AI knowledge base cost?

    At Syntalith an AI app on documents costs from €3,000 net, typically up to €7,000. At 150 questions about moved material a month of 15 minutes each, the payback is 2.7 months. We price maintenance individually.

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.