A brand of iTech Group

We deploy local language models in your company

An AI assistant on your servers. Data can stay in the company — with the right configuration.

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 Begin with Local AI – Start

From audit to maintenance

Deployments on your servers

An assistant on your servers

Team training after go-live

AI can help with everyday work. Data can stay in the company – with the right configuration.

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.

  • Data stays in the company

    Questions, documents and the model can run on your servers. To make that the case, as part of the deployment we configure limits on outbound connections, disable telemetry and control external integrations. This matters for GDPR and the protection of trade secrets.

  • Predictable costs

    You do not pay a per-user subscription just for using the local model, as you would with many cloud providers. Updates, integrations, external services and licences may still need an internet connection or incur extra cost.

  • Local operation

    Day-to-day work with the assistant can run locally, including when there is no outside connection. Updates, some integrations, external services and licences may still require the internet or additional fees.

  • We deploy what we teach

    The environment has to run on your servers, not just in a slide deck. Details about the people who lead the deployments are in the Who we are section.

How this helps in a company

A local assistant runs on your servers. Below are typical uses, without jargon in the foreground.

IT department assistant

It supports day-to-day IT work: routine tickets, procedures and suggestions based on the team's knowledge, without sending those materials to a public chatbot.

Searching technical documentation

Instead of digging through manuals, diagrams and notes, you can ask a question in plain language and get an answer with a reference to the source.

Behind the scenes: a knowledge base built from company documents (known as RAG).

Internal procedures knowledge base

Staff can ask about company procedures and policies. The materials stay on your servers when, as part of the deployment, we limit outbound connections, disable telemetry and control external integrations.

Reviewing contracts and quotes

The assistant can summarise a contract or compare a quote with your template. Documents can remain on a server in the company – with the configuration we set during the deployment.

Document summaries

A long report, protocol or memo becomes a short brief you can read quickly, still on your servers.

Deploying a local AI assistant

We run language models on your servers. With the right configuration — limiting outbound connections, disabling telemetry and controlling external integrations — questions, documents and answers can stay in the company. The scope is always tailored to your situation — no one-size-fits-all package.

  • Analysis of needs and your current environment
  • Hardware and model selection
  • Installation of Ollama and Open WebUI on your servers
  • A knowledge base from your company documents
  • Security: accounts, HTTPS, backups
  • Integration with your existing environment
  • Training for your team after go-live
  • Ongoing maintenance

Deployment packages

Indicative scopes and prices, so the scale of the conversation is clear. Amounts are net, in Polish zloty. The final quote is prepared after an audit, because it depends on the hardware, the number of users and the scope of integrations.

Readiness audit for local AI

A review of your infrastructure, hardware and model recommendations, and a written report. This is the starting point when you want to know whether local AI makes sense for you and where to begin.

PLN 2 500 net

More about the audit

Entry package

Local AI – Start

Ollama + Open WebUI installation

We set up a local model and a chat interface on your server. This gives you an environment for first tests, without a full company document knowledge base.

PLN 3 500–5 000 net

More about the Start package

AI pilot with a simple knowledge base

A local assistant on one department's documents, with security tests. It lets you see how staff use company knowledge before you widen the scope.

PLN 8 000–12 000 net

More about the knowledge-base deployment

Company-wide knowledge-base deployment

A knowledge base from procedures and documents, access rights for selected people, and team training. The assistant answers questions about your materials without sending them to a public chatbot.

PLN 15 000–25 000 net

More about the knowledge-base deployment

Advanced AI deployment

A full installation with integrations, monitoring and support after go-live. For companies that need several knowledge sources, broader access rights or more demanding infrastructure.

from PLN 30 000 net

More about advanced deployment

AI maintenance

Updates, supervision of the environment and help when something needs attention. A subscription service, independent of the number of assistant users.

from PLN 1 000 net / month

More about maintenance

AI training for administrators, 2 days

A workshop for the people who will maintain the environment and teach others to use it. The programme is on a separate page, together with the other courses.

PLN 4 000–6 000 net

AI under control course programme

How a deployment works

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.

  1. Analysis

    We discuss your tasks, data and servers. We determine whether a local assistant makes sense and where to start.

  2. Hardware and model selection

    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.

  3. Installation and go-live

    We install Ollama and Open WebUI on your servers, set up accounts, HTTPS and backups, and, in the agreed scope, add a knowledge base from your company documents. As part of the deployment we configure limits on outbound connections, disable telemetry and control external integrations. Updates, integrations, external services and licences may need the internet or incur extra cost.

  4. Training and maintenance

    We train the team that will use the assistant. We leave documentation and can look after the environment after go-live.

Who we are

iTech AI is a brand of iTech Group.

Deployments are led by an experienced IT engineer and trainer, with nearly 30 years of practice in Linux systems administration, computer networks, virtualisation and cybersecurity, supported by a team of specialists.

We work with networks, Linux systems, containers, security and local language models. We deploy what we teach: the AI assistant has to run on your servers, not just in a slide deck.

  • CCNA (Cisco)
  • CCNP (Cisco)
  • CCNA CyberOps (Cisco)
  • CCAI — Cisco Certified Academy Instructor
  • SSCP (ISC2)
  • MCT — Microsoft Certified Trainer
  • MCSA (Microsoft)
  • MCITP (Microsoft)
  • LPIC-1 (Linux Professional Institute)

Training

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

“AI under control”

Local language models in the company, running on your servers. Two days of practical workshops for administrators.

Course agenda

Course · 2 days

Docker: containers, Harbor, Trivy and Portainer

From installing Docker, through Compose and a private Harbor registry, to image scanning and host management.

Course agenda

Course · 2 days

Kubernetes: from k3s to a kubeadm cluster

From the k3s mini-distribution to a kubeadm cluster built from scratch. 16 labs for administrators.

Course agenda

Course · 2 days

Linux security and hardening

From a threat model and an audit, through SSH with MFA and a firewall, to SELinux, AIDE and monitoring with Wazuh.

Course agenda

Common questions

Who carries out the deployment?

Deployments are led by an experienced IT engineer and trainer, supported by a team of specialists. Hardware, models and scope are agreed individually. More about the team is in the Who we are section.

Do we need a graphics card?

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.

Does the model know current information and our procedures?

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.

Does any data leave the company?

The aim of a local installation is that questions, documents and the model stay on your servers. As part of the deployment we configure limits on outbound connections, disable telemetry and control external integrations, and we also set up the network, HTTPS and backups. This does not relieve the company of its own obligations under GDPR.

Does the environment work without the internet and without a per-user subscription?

Day-to-day work with the assistant can run locally, and you do not pay a per-user subscription just for using the model. Updates, integrations, external services and licences may still need an internet connection or incur extra cost.

How long does a deployment take?

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.

What about GDPR and the Artificial Intelligence Act?

A local installation, configured properly, 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.

Will this replace public cloud models?

For work with company data and procedures, a local assistant lets you keep questions in-house when we configure the environment that way. 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.

Let’s talk about your environment

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.