AI at Nux
AI goes to the data. Data does not go to AI.
We do not wire company systems to the cloud. We build an AI layer that runs on our servers next to the data and reaches it under control: through local models, one gateway with rules, and an audit trail.
- local models on our own GPUs
- one gateway to all models
- MCP to live data
- agents in production
- 6
IDE and agents
Cline · Roo Code · Claude Code · VS Code
- 5
PR agent
Automated review of merge requests in GitLab
- 4
Automation
n8n · workflows · AI as a process step
- 3
Gateway to AI
Open WebUI · RAG over the wiki, GitLab and documentation
- 2
Local models
Ollama · llama.cpp ecosystem · open-source models
- 1
Infrastructure
Own data centres · Proxmox · Ceph · GPU
Cross-cutting
LiteLLM
One gateway to all models
MCP
AI looks into our systems
Two approaches
A connector to the cloud, or a layer next to the data
Most “AI integrations” are connectors: they take data from your system and send it out. We build the other way round.
AI as a connector to the cloud
- Data leaves your network with every request.
- Every token is paid for, routine included.
- Who sent what where is traced after the fact, if at all.
- Rules are held by people’s discipline and policies.
AI as a layer next to the data
- The model runs on our hardware next to the data.
- Capacity is not paid per token, routine is cheap.
- One gateway with an audit log: who, which model, when.
- Rules are configuration and code, not policy documents.
AI stack
Six layers, one system
Each layer stands on the one below. The tools everyone talks about are only the last one.
- 01
Infrastructure
Own data centres · Proxmox · Ceph · GPU
Our own infrastructure in two locations in the Czech Republic. The AI layer runs on the same platform as our clients’ production systems.
- 02
Local models
Ollama · llama.cpp ecosystem · open-source models
Open-source language models run on our GPUs. Prompt and answer stay in our network; nothing goes to the model provider.
- 03
Gateway to AI
Open WebUI · RAG over the wiki, GitLab and documentation
The internal interface to AI. The key is RAG: the model receives relevant excerpts of our knowledge and answers from the company’s reality, not the general internet.
- 04
Automation
n8n · workflows · AI as a process step
Connects systems (GitLab, monitoring, e-mail, APIs). AI in the process classifies, summarises and extracts, and the output goes straight into the system.
- 05
PR agent
Automated review of merge requests in GitLab
Every merge request gets an automated AI review before a human reviewer sees it: risks, inconsistencies, deviations from standards. In the MR discussion it answers questions about the change.
- 06
IDE and agents
Cline · Roo Code · Claude Code · VS Code
AI assistance right in the development environment, from completion to agents that carry out a multi-step change. Always under the developer’s control.
Case studies
Agents that work for us every day
None of them is a connector to the cloud. Each sits on our server next to its data, the model is just one step, and code makes the decisions.
IMAP triage
Sorting company mail and drafting replies
In the morning it is clear what is on fire. The agent sorts the NOC, CSIRT, billing and sales mailboxes and drafts replies to selected messages. It cannot send them.
GitLab triage
A daily issue digest for developers and teams
Every morning, what changed in GitLab and what is expected of whom. Code builds the sections; a local model only adds summaries. Client data never sees the cloud, and code enforces it.
Day digest
A morning overview from company systems
One e-mail before the day starts: calendar, tasks, mail, GitLab and Mattermost. The agent calls no model itself; it assembles the output of the other agents.
Delegator
Assigning tasks in plain text in chat
You tell a Mattermost bot what needs doing and who should do it. The model proposes a task, code checks the assignee and deadline, you confirm with a thumbs-up. Then the bot watches how the task goes.
Expense hub
Re-billing company expenses
Statements for fuel, phones, insurance and internet arrive by e-mail and end up as an overview for each holder. No model: the parsers are deterministic and the totals match to the cent.
All case studiesWhat’s in it for you
Two ways to use AI with us
Development with AI built in
We build and run your application with AI as part of the process: a review of every change, answers grounded in your project’s documentation, routine automated. What may go to the cloud is decided up front, in writing.
The AI layer as a service
We build and run the same for you: local models, a gateway with rules, answers over your knowledge and agents over your systems. On our infrastructure, with your data under control.
“AI lets me hold and implement a brief across a context that used to be impossible to keep in my head. It did not move the limit of what we can do. It raised the ceiling of what one senior can cover.”
Radek RůžičkaManaging Director and CTO, Nux s.r.o.The value is not in the prompt. It is in whoever holds the context, can break the brief down, and can tell when the result is wrong.
No-obligation consultation
Let’s find the first job for AI in your company.
An hour’s conversation about where your data lives, which processes slow you down and what of it may leave your network. You leave with a proposal for a first pilot, not a tool demo.
Built and is accountable for the AI layer at Nux
Radek Růžička
Managing Director and CTO, Nux s.r.o.