Workstation in the Punktexe engine room: separate devices for separate tasks

Home / Engine room

Engine room · our own operations

How we put AI to work ourselves.

Before we build something for you, we run it ourselves. Here you can see which processes at Punktexe run with AI, how we separate data according to the shell model and how we test our own agents. Everything comes from our own operations, no client references.

In use at Punktexe Partly in use at Punktexe In progress As of November 2026
01 · Architecture

The shell model: the more sensitive, the further inside.

The more confidential a piece of information, the further inside it is processed, at the core with local models. We define for each application which data may leave which shell. Open a shell to see what runs there.

  • Permissions per shell
  • Budget per model
  • Separation per area
  • Log
Core · local models
What runs
Speech recognition with Whisper and local language models such as Llama or Qwen, on our own hardware.
Which data
Confidential material: drafts, personnel data, internal documents.
Boundary
We deliberately process confidential material with local models. Only what has been approved for each application goes outside.
Shell 1 · tools, APIs, research
What runs
Web search, interfaces to the website, email and file storage, our own scripts.
Which data
Public or approved content.
Boundary
Each tool receives only the access it needs, with its own key.
Shell 2 · EU and specialist models
What runs
European models and specialist models, for example for speech or documents.
Which data
Internal content according to classification. Personal data is masked beforehand where the process runs through the gateway.
Boundary
Approval for each application, costs and permissions via the gateway.
Shell 3 · frontier models
What runs
The most powerful cloud models for demanding tasks such as code, research and writing.
Which data
Only non-critical or cleansed content.
Boundary
No confidential data. Where the classification is unclear, no external processing is intended.
In use at Punktexe

The gateway: the door between the shells

Our own AI gateway brings several models together behind one access point, local as well as European and cloud models. Routing, permissions, budget and logging sit in one place. If a local model fails, another local model takes over automatically. A model can be swapped without rebuilding the application.

02 · Processes

What runs with AI at Punktexe

Seven processes from our own operations. Each one states how it is reviewed and where a person decides.

In use at Punktexe

Tax return from end to end

Receipts arrive by email, are recognised, read and filed in a traceable way. From these, the documents for the annual accounts and the electronic submission to the tax office are produced. We show the process, not the figures.

Check: Review steps check the allocation. A person confirms the submission to the tax office.

In use at Punktexe

This website, built automatically

The pages are created as source code in our own repository. Agents write drafts, the reviewer agent checks brand and facts, and publishing takes place via an interface. For AI search, we automatically generate a Markdown version of every page.

Check: The reviewer agent and automated checks review every change, and everything is traceable in the history. A person decides on larger changes.

In use at Punktexe

Onboarding new staff

New staff and partners receive a curated package: a knowledge base, guides, and explainer videos and audio summaries generated from our own documents. The time saved goes into getting to know each other in person.

Check: Content is reviewed before it is passed on.

In use at Punktexe

Speech to text, locally

Speak freely, and the computer turns it into an email, note or post in the desired tone. Speech recognition runs locally with Whisper. We build voice agents on the same technology.

Check: The text is read before it is sent.

In use at Punktexe

Inbox and knowledge

Information sent by email to a dedicated address first lands in quarantine and is then filed in the right place in the knowledge store. Long audio recordings and documents are converted locally into searchable text.

Check: The quarantine checks content before anything is added to the knowledge store.

In use at Punktexe

Sales

Several sources produce a cleansed target list with clear criteria. Drafts for first messages are created within guardrails and checked by the reviewer agent.

Check: The reviewer agent checks every draft, and messages are sent after approval.

In use at Punktexe

Market monitoring

A daily overview of relevant public signals, read only, with suggestions on where it is worth joining the conversation.

Check: Whether and how we respond is our own decision.

Beyond our own operations

Applied AI: what is possible in your company

Here we show what we use ourselves. Where AI can also work alongside your people on a factory site is shown in the floor plan.

Start the tour →
03 · Security in our own operations

How we test ourselves

What we build for others must pass with us first.

In progress

Attacks on our own agents

For our own agents, we have built a test matrix of more than 200 prompts in 16 attack classes, in English, German and Bavarian, mapped to the OWASP Top 10 for LLM Applications and MITRE ATLAS. We are currently setting up regular testing with it. This is our own quality assurance, not a testing service for third parties.

Partly in use at Punktexe

Masking personal data

When a request runs through the gateway, it attempts to mask detected personal data such as names, email addresses and telephone numbers locally before the cloud call. Detection can miss details, and not every one of our processes uses this route yet.

In use at Punktexe

Credentials do not belong in source code

Before every commit, automated checks look for known patterns of credentials and private keys. If something is found, the commit is blocked.

In use at Punktexe

Separate devices for separate tasks

Sensitive and experimental processes run on their own devices, separated from each other.

In use at Punktexe

Regular housekeeping

A recurring check searches the knowledge store for secrets, breached separations and outdated content.

A verification agent checks, and a person decides where it is necessary.
Actions are logged and traceable, insofar as they run through the gateway and the history. The aim is completeness.
Better an honest no than a maybe sold as a yes.
04 · The team in the background

Our agents

They have names because we work with them. People make the decisions.

Trudi

Red team

Works with our test matrix for attacks on our own agents. Regular testing is being set up.

Backy

Backup

Backs up data and makes sure nothing leaves the house by accident.

Judy

Night shift

Starts scheduled runs every morning, even when nobody is sitting in front of the screen.

The Reviewer

Brand and facts

Checks every text before approval: formal address, evidence, no empty promises.

05 · From practice

Knowledge we share

Talks by Günther Kriele in a personal capacity, independent of client projects.

  • 24th OWASP Stammtisch Augsburg, July 2026: AI firewalls put to the test. More than 200 prompts, some in dialect, and the question of when a hit really is a vulnerability.
  • Compliance as code with OSCAL: describing and checking requirements in machine-readable form.

On the road: where we speak, listen and learn

One talk of our own and events we attended.

Günther Kriele in the audience at GITEX AI Europe 2026 in Berlin
GITEX AI Europe 2026, Berlin: right in the middle of it.
Günther Kriele at the 24th OWASP Stammtisch Augsburg in July 2026, slide: two separate test levels with 215 prompts
24th OWASP Stammtisch Augsburg, July 2026: AI firewalls put to the test.
GITEX AI Europe 2026 in Berlin: panel on governance and cyber defence under the EU AI Act
Panel on governance under the EU AI Act.
Humanoid robots at GITEX AI Europe 2026 in Berlin
Humanoid robots: Industrial AI you can touch.
GITEX AI Europe 2026: talk on the European AI pyramid of applications, models, infrastructure, chips and energy
Europe's AI pyramid: from energy to application.
Microsoft AI Tour for Partners: fireside chat by Microsoft and NVIDIA
From the audience at the Microsoft AI Tour for Partners: fireside chat by Microsoft and NVIDIA.

Which of these do you need?

Get in touch with no obligation or suggest a meeting straight away. We will respond personally.

Where do you stand? Take the AI check (4 minutes) →
Nach oben scrollen