Offline AI for PLC programming means running the language model on your own computer or plant server, so prompts, programs and drawings never leave the building. For engineers working on machines for German customers, the main reason is confidentiality rather than convenience: the PLC program is usually a trade secret, many supply contracts forbid passing it to third parties, and many OT networks have no route to the internet at all.
This article sorts out what GDPR does and does not have to do with PLC code, why trade secret law is the bigger issue, the three ways to use AI tools on control projects, how a local model is set up, and where the web tool LADX does and does not fit. It is written by engineers, not lawyers: check contract terms with whoever signs them.
Is PLC code personal data under GDPR?
Mostly not. Personal data is information relating to an identified or identifiable living individual (European Commission). Ladder rungs and function blocks rarely qualify. The project around them often does: HMI user lists, operator IDs in audit trails, shift logs, comments naming the engineer who changed a rung, photos from site, and email threads attached to a change request.
If any of that is sent to a cloud AI service, the provider typically acts as a processor for you, which brings duties on both sides, including a written agreement (EDPB). The simplest way to avoid that question is not to send the data anywhere.
The bigger issue: trade secrets and NDAs
Under the German Trade Secrets Act, information is only protected as a trade secret if, among other conditions, its lawful holder protects it with confidentiality measures appropriate to the circumstances (GeschGehG 搂2). A machine builder's control software, with years of process know-how in its sequences and parameters, is a textbook example. If a supplier's engineer pastes that code into a public chatbot under a personal account, the customer can fairly ask whether appropriate measures were in place, and most non-disclosure agreements will already have answered that question.
Three ways to use AI on a control project
| Mode | Where the code goes | When it fits |
|---|---|---|
| Cloud model, free or with your own key | To the provider running the model, and to any service in between | Your own code, or customers who have approved that provider |
| Browser-only tools | Stays in the browser | Editing, simulation and conversion without AI generation |
| Fully local model | Stays on the computer | Customer code under NDA, air-gapped OT networks |
Where LADX fits, and where it does not
LADX is web only and free. It covers the first two modes and not the third. It has no desktop app, no offline mode and no installer, and "LADX Studio" is now only the name of the signed-in workspace at ladx.ai/studio. Its AI requests go from ladx.ai's server, so a local Ollama model on your machine cannot be used, and it does not belong inside an air gap.
Without a key of your own, chat runs on free models through LADX's shared OpenRouter account, rate limited per account; you can connect your own key for OpenRouter, Anthropic, OpenAI or any OpenAI-compatible endpoint to use paid models. LADX never sells data or uses it to train AI models, and provider keys are encrypted (AES-256-GCM). On the free tier, the company running the free model may keep prompts and answers, so customer code under NDA stays out. The ladder editor and simulator, converters, HMI builder and panel CAD run in the browser without an account, and chat needs a free account (LADX help). LADX suits non-sensitive drafting, learning and checking on a connected machine.
Generated ladder goes through the editor's own validator and a seal-in check, Structured Text is compiled by the LADV compiler, and problems are listed beside the answer. Code that passes can be run on a Wartens LADV virtual PLC in the browser at ladx.ai/vplc. The virtual PLCs are not real time, not safety rated and cannot control machinery, and LADX never connects to or downloads to a real controller.
How a local model is set up
- Install Ollama, or a similar tool, on a staging machine and pull a model. The weights are gigabytes, so plan the transfer.
- Check any published hashes for the installer and model files, and log the result.
- Move everything to the isolated workstation through your normal media control process.
- Leave automatic updates off and bring new versions in through the same route.
- Keep prompts, drafts and accepted code in a project folder you can back up or hand over.
What is Ollama? Running Local LLMs Made Simple
IBM Technology
This video is hosted on YouTube. Playing it loads content from Google, which may set cookies.
Watch on YouTubeIs a local model good enough for PLC code?
On its own, a local model is weaker than a large hosted one, and a small model on a laptop is limited by memory and speed. Test two or three models on the hardware the site actually issues. Treat every output as a draft: compile it with the vendor's tools, review it and test it.
A compiler proves the code is valid, not that it is right. Whether an interlock is sufficient for a hazard stays an engineering judgement, and simulation is not a safety case. Use a bench test such as the one in our PLC FAT checklist before anything reaches a panel.
Running a model server on an OT network
- Treat it as a machine component: documented, imaged, with a named owner. The usual failure is that the person who set it up has left.
- Put it in the engineering zone, not on the shop floor network. Our article on IEC 62443 zones and conduits shows where it belongs.
- Leave automatic updates off on isolated machines and bring new versions in through your normal media control process.
- Log which model version produced which accepted output, so a later question can be answered.
Where Wartens fits
Wartens engineers PLC software for German machine builders under the customer's confidentiality terms. If you want help setting rules for AI use in your controls team, or training on how to review generated code, see our automation engineering services and engineering training.
Next step: tell us how your customers' NDAs treat third-party tools and we will suggest a workable setup for your team. Contact us.
