Questions about procedures and documentation
Staff can ask questions about procedures and documentation without sending files to a public chatbot.
Behind the scenes: a knowledge base built from company documents (known as RAG).
A brand of iTech Group
An AI assistant on your servers, with no data sent to the cloud.
I work with a team that has 30 years of IT experience. We analyse your needs, select the hardware and models, install the environment, connect your company documents and train the team that will use it.
Check if your infrastructure is ready for local AI See deployment packages
A team with 30 years of experience
Deployments on your servers
Your data stays in-house
Team training after go-live
Public cloud models are convenient, but they mean sending questions, procedures and documents outside the company. You also pay per user and depend on an internet connection. That is why we deploy the assistant on your servers.
Questions, documents and the model run on your servers. That matters for GDPR and for protecting trade secrets.
You set the environment up once. You do not pay a subscription for every user, and you are not waiting for the next price rise from a cloud provider.
Once installed, the environment runs locally — including when there is no connection to the outside world.
I work with a team that has 30 years of IT experience. We deploy what we teach: the environment has to run on your servers, not just in a slide deck.
A local assistant runs on your servers. These are typical uses, described in everyday language first.
Staff can ask questions about procedures and documentation without sending files to a public chatbot.
Behind the scenes: a knowledge base built from company documents (known as RAG).
The assistant can summarise a contract or compare a quote with your template. The documents stay on a server in your company.
Routine tickets can be pre-sorted, and draft replies suggested from your instructions and earlier solutions.
Instead of digging through folders and mailboxes, people ask in plain language and get an answer with a pointer to the source.
A long report, minutes or a briefing can be turned into a short summary that is quick to read — still on your servers.
We run language models on your servers. Questions, documents and answers stay in the company. The scope is always tailored to your situation — no one-size-fits-all package.
Indicative scope and pricing, so it is clear what scale of work we are talking about. Amounts are net, in Polish zloty (PLN).
We review your infrastructure and needs, recommend hardware and a model, and deliver a report with recommendations. You can then decide whether and how to deploy a local assistant.
from PLN 2,500 net
We install a local model runtime (Ollama) and a company chat interface (Open WebUI) on your servers, so the team can use an assistant without sending data to the cloud.
PLN 3,500–5,000 net
A first, limited deployment: an assistant that answers questions based on a selected set of company documents. We test the quality of the answers and secure access.
This uses RAG: the assistant first retrieves passages from your documents, then prepares an answer from them.
PLN 8,000–12,000 net
We set up a company assistant that answers from your documentation: a knowledge base, access rights, security, and preparing the team for day-to-day use.
PLN 15,000–25,000 net
A broader deployment tailored to your processes: integrations with existing tools, monitoring, backups and extending how the assistant is used in the company.
from PLN 30,000 net
Ongoing care for the environment after go-live: updates, health checks and help with changes, so the assistant keeps running reliably.
from PLN 1,000 net/month
The two-day “AI under control” workshop: from installing a model, through working with company documents, to securing and operating the environment.
“AI under control” course agenda
PLN 4,000–6,000 net
Prices are net, for business clients, and are indicative. The final quote follows an audit or a review of your requirements.
We work step by step, on your servers. You are left with a working environment, documentation and a team that knows how to use it.
We discuss your tasks, data and servers. We determine whether a local assistant makes sense and where to start.
We recommend a server, a graphics card — if one is needed — and models suited to your use cases. There is no single setup that fits everyone.
We install Ollama and Open WebUI on your servers, set up accounts, HTTPS and backups, add a knowledge base from your company documents and, if needed, connect the environment to your existing tools.
We train the team that will use the assistant. We leave documentation and can look after the environment after go-live.
iTech AI is a brand of iTech Group. Implementations and training are led by Jakub Wojtanowski. He works with a team that has 30 years of IT experience.
We work with networks, Linux systems, containers, security and local language models. We deploy what we teach: an AI assistant should run on your servers, not just in a presentation.
Jakub is the lead trainer and is responsible for how deployments are carried out.









Alongside deployments we run practical courses, on-site or remotely, on virtual machines. Dates are agreed individually. The fee for the “AI under control” workshop is listed with the deployment packages.
Course · 2 days
Local language models in the company, with no data sent to the cloud. Two days of practical workshops for administrators.
Course · 2 days
From installing Docker, through Compose and a private Harbor registry, to image scanning and host management.
Course · 2 days
From the k3s mini-distribution to a kubeadm cluster built from scratch. 16 labs for administrators.
Course · 2 days
From a threat model and an audit, through SSH with MFA and a firewall, to SELinux, AIDE and monitoring with Wazuh.
Jakub Wojtanowski leads deployments together with a team that has 30 years of IT experience. Hardware, models and scope are agreed individually.
Not always. Smaller models can run on a capable server without a dedicated GPU. Larger models and a more comfortable working pace usually need a graphics card with enough memory. We discuss hardware individually — there is no single setup that fits everyone.
The model itself only knows what it learned during training, and it does not reach out to the internet or your files on its own. To answer from your company documents, we add a knowledge base (known as RAG): it first searches your materials, then prepares an answer based on them.
The point of a local installation is that questions, documents and the model stay on your servers. During the deployment we set up the network, HTTPS and backups so that this is the case. This does not relieve the company of its own obligations under GDPR.
It depends on the scope: from simply starting the assistant to adding a knowledge base, user accounts and usage rules. The timetable and stages are agreed individually.
A local installation helps keep data in the company, which matters for GDPR and the protection of trade secrets. The AI Act adds further duties that depend on how the model is used. We do not provide legal advice — we can help on the technical side and point out where you should consult a lawyer.
For work with company data and procedures, a local assistant lets you keep questions in-house. It is not a copy of a particular cloud service, but your own environment, under your control. Some uses can still be left in the cloud — that is the company’s decision.
Tell us what you need. We can check whether your infrastructure is ready for a local AI assistant, or discuss a deployment or training. We will get back to you and agree the next steps.
You can also write directly to kontakt@itechai.pl.