Skip to content

What you can commission us for.

We connect knowledge, AI and existing software into solutions for operational tasks – from the first conversation to roll-out.

Do you recognise your situation?

Choose the situation closest to yours.

1Recognise the situation
Our knowledge is stuck in emails and files.

We bring scattered information together and make every statement traceable to its source.

2See the effect
BeforeOrder: delivery Friday, 3 pm. That receiving closes at 12 noon is only written in one message.
AfterOne week later: suggested 11 am – with Sandra's message as evidence.
Try the knowledge scene →
3Commission the result

A pilot that connects project messages, plans and reports for one selected workflow into an evidenced project status – with your documents.

Discuss this situation with us →
At the centre

AI and automation

Recognise, prepare and complete recurring tasks traceably – with a person as the reviewing authority.

  • Evaluate documents and requests
  • Prepare replies, tasks and postings
  • Automate workflows between systems
Your own AI systems & harness engineering →
Making it usable

Custom software, interaction design and graphic design

Applications that fit the workflow and have a clear visual identity – at the desk, on the shop floor and on the move.

  • Workflow mapping with the team
  • Interaction and interface design
  • Web and desktop applications
When the project needs it

Hardware, sensors and embedded systems

Devices and sensors that deliver data or control processes – together with the software that makes them understandable.

  • Sensors and data acquisition
  • Embedded software and firmware
  • Connectivity and remote maintenance
DW

One technical project lead

Dirk Wilkens leads projects technically. We bring in specialists for AI and data, software development, design or electronics on a project basis. Your contact is Wilkens Engineering – from idea to operation.

Profile →
Your own AI systems

AI systems for your own workflows.

We develop AI systems with you for your own workflows. Together we define which knowledge a model may use, which tools it can operate and when your team approves a decision. To do this, we integrate locally run models, commercial AI services or a combination of both into your existing software.

Harness engineering

A prompt describes the task. The harness is the environment in which a model completes that task reliably:

Working contextprovides exactly the knowledge the task needs and is allowed to use – with origin and date.
Controlgoverns which model works and which tools it may use, locally or via a service.
Checksverifies results against sources, rules and calculations before they move on.
Recordkeeps track of what was executed, handed over to whom and approved by whom.
For management

You decide what AI should work on, which data may leave the company and where a person approves. The harness makes these decisions binding and traceable in daily operation.

For technical leads

Model access, tool calls and data releases run through a defined layer with roles, check rules and a log. Models stay interchangeable; deterministic logic such as scheduling or quantity calculations stays outside the model.

What you can commission – using project control as an example

  1. Find a suitable workflowTogether we pick a workflow with clear value, such as status reports from project messages, and define sources, roles and approvals.
  2. Testable pilotA first harness with real workflows and acceptance criteria: which statements are evidenced, which dates are calculated, who approves?
  3. IntegrationConnection to your existing software, data sources and permissions – local, via a service or combined.
  4. HandoverDocumentation, training, logs and check rules go to your team.
  5. Further developmentNew workflows, other models or stricter rules are added in the harness without rebuilding operations.

What may leave your company?

Compare local, external and hybrid AI for the same task – and withdraw a release.

Compare model paths →
Data protection and security

Integrating AI securely into your operation

For us, security and data protection are part of the integration, not an appendix. What this website shows as a simulation and what we only define and build with you in your project are marked separately.

Shown in the demo as a simulation on this websiteIn your project designed and built with you

Who sees which source?

Shown in the demo Every statement stays linked to its source – down to the original sentence.

In your project Who may see which source is taken from your existing permissions, for example from your directory service, project or document system. The demo has no user roles.

What does an external provider receive?

Shown in the demo Only what a rule explicitly releases: in the demo, sanitised wording without names or original text – visible character by character.

In your project Which data types may reach which service is defined with you. You review the contract with the provider – data processing agreement, use for training, retention, region – with us before the first hand-over.

Where is the data?

In your project Locally run models run on your infrastructure or in a data centre you choose. With external services, location and region depend on the provider and contract; transfers outside the EU need a basis under Chapter V GDPR.

How are permissions, releases, logging and deletion defined?

Shown in the demo Release, withdrawal and every hand-over with recipient and scope appear in the simulated history.

In your project You decide who may release, how long inputs, results and logs are kept and when they are deleted. We implement and document it.

What happens in an outage or after a release is withdrawn?

Shown in the demo After a withdrawal there is no new hand-over. What the local model can do continues locally; everything else waits visibly. Content already handed over remains visible in the history.

In your project Whether and when the provider deletes content already handed over is governed by the contract. For a service outage we define the same pattern: continue locally or wait visibly – the scheduling logic keeps working without a model.

Legal framework – orientation, not legal advice

Official sources as of 19 Nov 2026

GDPR – when personal data is involved

  • Your company remains the controller (Art. 4(7)). Legal basis (Art. 6), principles such as data minimisation (Art. 5), data protection by design (Art. 25) and security of processing (Art. 32) apply – whether a model runs locally or externally.
  • An external AI service usually acts as a processor; a contract under Art. 28 is then required. Transfers to third countries follow Chapter V (Art. 44 ff.), for the US for example the adequacy decision (EU) 2023/1795 if the provider is certified.
  • Depending on the processing: records (Art. 30) and a data protection impact assessment (Art. 35). Art. 22 limits automated decisions with legal effect – in the example, the project lead decides.
  • A local model reduces the number of recipients. On its own it does not demonstrate data protection compliance.

AI Act, Regulation (EU) 2024/1689 – role and use case

  • Whoever develops an AI system and places it on the market or puts it into service under their own name is a provider (Art. 3(3)); whoever uses it under their own authority is a deployer (Art. 3(4)). We clarify the roles between you, us and the model provider explicitly in the project.
  • Since 2 February 2025, Art. 4 applies: providers and deployers support the AI literacy of their staff. Since 2 August 2026, the regulation applies generally, including the transparency obligations under Art. 50.
  • An assistant that drafts internal project reports typically does not fall under the high-risk areas of Annex III – unlike, for example, one that evaluates the performance or behaviour of employees (Annex III point 4). For high-risk systems under Annex III, the obligations apply from 2 December 2027 following the amending Regulation (EU) 2026/1744.
  • Whether a specific system is high-risk and who carries which obligations is assessed per use case – together with your legal or data protection advisers.

In your project Technical measures we implement

  • Data classes and release rules per recipient, enforced in the harness
  • Sanitising before every external hand-over – names, original wording and reasons stay internal
  • Source permissions from your existing systems instead of a parallel administration
  • A log per hand-over: time, recipient, scope, release
  • Retention periods and deletion routines for inputs, results and logs
  • Continue locally or wait visibly after a withdrawal or outage
  • Dates, quantities and rules computed deterministically outside the model
  • Encryption in transit and at rest

Decisions that remain yours as the operator

  • Which data may leave the company – and for which tasks?
  • Which provider, which region, which contract terms?
  • Who grants and withdraws releases?
  • Which retention and deletion periods apply?
  • Is a data protection impact assessment required?
  • How are employees informed and trained (Art. 4 AI Act)?
Collaboration

Discuss a similar workflow with us.

Which decision costs your team too much coordination? Prepare your request in a few minutes – if you like, with a short brief in three answers.

Wilkens Engineering · technical lead: Dirk Wilkens · Kiel

Sketch a project

Three short answers are enough. They become a short brief you can edit and carry over into the project enquiry.

Your draft stays on this device. Nothing is sent.

Contact