[email protected]

AI platform for manufacturing and engineering companies, without giving away your know-how

Service, engineering and documentation teams search manuals, analyse service reports and translate instructions without handing design or customer data to US services.

  • Know-how stays in Germany
  • Knowledge bases per department
  • Ready in a few working days
Reviews
Cloud Wolke HerausforderungServer NachhaltigkeitIT Beratung Service Consulting SoforthilfeTimo Wevelsiep Robin ZinsExperten für Innovation Migration AWSHetzner Hosting zuverlässig

Companies worldwide trust WZ-IT

  • Stadtwerke Brühl
  • DGHO e.V.
  • ABCO Water Systems
  • Golem.de
  • EVADXB
  • nextGYM
  • AInergy
  • ml&s
  • Odiseo Solutions
  • Annota
  • ARGE
  • SweetConnect GmbH
  • Aphy AG
  • CORGOS
  • Rekorder
  • SolidProof
  • Yonju
  • Keymate
  • Paritel
  • Mr. Clipart
  • Millenium
  • Negosh
  • Führerscheinmacher
  • Boese VA
Read client reviews

Starting point

Why design and customer data do not belong in ChatGPT

Knowledge sits in manuals, service reports and heads. The question is how to use it without losing its protection as a trade secret.

  • Trade secrets

    Design and costing know-how is only protected if you can show reasonable confidentiality measures (Section 2 no. 1 GeschGehG).

  • Your customers' NDAs

    Your customers' specifications and drawings are often under NDA. Every AI service is another recipient.

  • Scattered service knowledge

    Fault patterns and fixes sit in service reports, test records and with a few experienced technicians.

  • Private AI accounts

    Without an approved tool, staff copy customer documents into private chat accounts.

Use cases

AI in manufacturing: service, reports, translation

The AI delivers drafts and sources. Review and approval stay with you.

Analyse service reports

Today

Recurring faults only show up when someone lays reports side by side.

With the AI platform

Upload a quarter's service reports and the AI summarises fault patterns by frequency and assembly. Assessment stays with service and engineering.

Search service knowledge

Today

Technicians look for fault patterns in manuals, old service reports and test records.

With the AI platform

Questions to the knowledge base return the answer with its source, in the browser even at the customer's site.

Translate manuals and customer letters

Today

Texts go to external translators or public translation services.

With the AI platform

An assistant with your terminology list produces translation drafts. The documentation team checks and approves.

What it looks like

The platform in your team's daily work

Open WebUI in the browser, with models operated in Germany by German providers. Stops from your work, plus web search and your own knowledge base.

Full walkthrough
  1. 01Service knowledge

    Ask about a fault code, get the service manual section

    Manuals, service reports and test records sit in a knowledge base. Every answer cites its source, visible only to service and engineering.

    • Sources
    • Reranking
    • Access per group
  2. 02Service reports

    Upload a quarter, get fault patterns by frequency

    Upload service reports as PDF or Excel. The AI summarises fault patterns by frequency, assembly and customer; the assessment stays with you.

    • PDF
    • Word
    • Excel
    • PowerPoint
  3. 03Translation

    Translation assistant with your terminology

    Store the terminology list and style rules once. The documentation team picks the assistant and gets translation drafts in your terminology for review.

    • Assistants
    • Prompt library
    • Templates
  4. 04Web search

    Keep track of standards and regulations, with sources

    For new regulations, standard versions or supplier information the team switches on web search. Design and customer data stay in the instance.

    • Web search
    • Attach web page
    • Can be disabled per group
  5. 05Create a knowledge base

    Your own documents as a knowledge base, called up with # in the chat

    Create a knowledge base, upload files, sync whole folders or add web pages and text. In the chat, a # brings in the collection and the answer cites its source.

    • Collections
    • Folder sync
    • Access per group

GDPR and trade secrets

A contract chain in which every link is bound

Reasonable confidentiality means: contractually with a DPA and confidentiality agreement, organisationally with permissions per group, technically with a dedicated instance and no US provider.

Your team

Sign-in via SSO with your multi-factor authentication, permissions per group.

  • SSO
  • MFA

WZ-IT

Setup and operations, DPA and Section 203 supplementary agreement, staff bound in writing.

  • DPA
  • §203

Instance

Dedicated instance per organisation, no shared platform; data centres in Germany run by German providers, with DPA and Section 203 supplementary agreement.

  • Germany
  • DPA
  • §203

Models

AI hosting by a German provider in Germany, no transfer abroad, no US provider, no training.

  • Germany
  • DPA
  • §203

Process

Your own AI platform in four steps

You test with your team first, then decide.

  1. 01

    Initial call

    Clarify users, tasks, sign-in and requirements.

  2. 02

    Test instance

    Test for 7 days free of charge with non-critical data; the test instance is not Section 203 compliant.

  3. 03

    Quick start

    Within a few working days: set up instance, domain, users and SSO, plus a one-hour walkthrough.

  4. 04

    Operations

    We handle updates, backups, monitoring and new models.

Packages

One price per organisation, tiered by users

Usually one area with a lot of document work starts, such as service or technical documentation. Further departments join with the next package.

Start

For small firms, practices and teams.

€149.90/ month
  • 10 users included
  • 75M tokens per month (fair use)
  • SSO and Section 203 agreement included

Team

For growing firms and departments.

€399.90/ month
  • 25 users included
  • 300M tokens per month (fair use)
  • SSO and Section 203 agreement included

Business

For organisations with several teams.

€699.90/ month
  • 50 users included
  • 600M tokens per month (fair use)
  • SSO and Section 203 agreement included

Organisation

For larger organisations and public bodies.

€1,199.90/ month
  • 100 users included
  • 1bn tokens per month (fair use)
  • SSO and Section 203 agreement included
Terms and notes

All packages include

  • Dedicated instance on your own subdomain or domain
  • All models, knowledge bases, assistants and text recognition
  • Hosting in German data centres of German providers, no US clouds
  • DPA and Section 203 supplementary agreement
  • Updates, daily backup and 24/7 monitoring
  • Next-business-day support, various service levels available

Optional onboarding package for €990 once: knowledge base with your documents, assistant templates and two hours of training documented under Article 4 of the AI Act. Additional users €14.90 each per month, up to 150 users in the Organisation package; beyond that a custom offer. Cancel monthly.

All prices are net and exclude statutory VAT. The offers are addressed to businesses.

Frequently asked questions: AI for manufacturing

Professional rules, data protection, prices and use

Reviews & projects

What clients say about working with us

From local AI integration to architecture, data sovereignty and ongoing operations.

WZ-IT moved our studio infrastructure from decentralised individual devices to a central platform: every site is securely connected via VPN, new devices are onboarded automatically and an entire site is provisioned from a template, without manual steps on location. What impressed me most is the breadth and depth of their knowledge: Timo and Robin are not a typical IT provider who sets up a server and leaves. The two of them think their way into highly complex infrastructure and software topics, work through every requirement we put in front of them, and build networking, provisioning and operations so that everything fits together in the end. WZ-IT is an excellent partner for complex software, network and architecture projects.
Steve KirchnerManaging Director, nextGYM GmbH
View project

International

Built in Germany's Ruhr Valley. Running worldwide.

WZ-IT designs, develops and operates infrastructure and software for clients in Germany and internationally. We deliver projects remotely and continue supporting them in ongoing operations after go-live.

Selected projects

Read client reviews

  • Integrate a local AI solution
  • Modernize your infrastructure - sovereign
  • Design an open-source AI architecture
  • Plan a sovereign open-source stack
  • Secure your Proxmox & backup setup
  • Modernize your legacy software
  • Cut cloud cost - up to −81%
  • Build a high-availability Proxmox cluster
  • Virtualize with Managed Proxmox
  • Get collaboration fully managed
  • Ship your prototype to production
  • Connect sites and clusters securely

Enquiry

Test the AI platform or choose a package

Tell us your number of users and tasks. We set up the test instance or recommend the right package.

  • Straight with Timo and Robin - no sales team, no pitch
  • An honest take, including when we are not the right fit
  • Concrete next steps for infrastructure, software or AI

No risk: worst case, you leave with a clearer understanding of your project than before.

WZ-IT's advice on our Azure migration was technically sound and completely non-binding right from the intro call - we took away a great deal.
Jakob ÖschlbergerInno7 GmbH
Timo and Robin, founders of WZ-IT

How would you like to start?

The selection is non-binding. The test instance runs for 7 days free of charge and without payment details.

We usually respond within one business day. Please do not send access credentials yet.

WZ-IT's advice on our Azure migration was technically sound and completely non-binding right from the intro call - we took away a great deal.
Jakob ÖschlbergerInno7 GmbH