Large companies have been working this way for a while. Now it’s the Mittelstand’s turn.
We connect your mailbox, ERP, accounting and company knowledge to AI assistants that prepare orders, enquiries and invoices. Your team reviews, corrects and decides, and gets more orders done in the same time.
At banks, insurers and industrial groups, AI assistants already prepare enquiries, orders and documents today. We have built such systems there ourselves and put them into production (references). What used to need dedicated IT departments and large budgets is now possible with open standards and off-the-shelf AI models, for businesses with 10 or 200 employees.
Once the searching and gathering goes away, every employee handles more cases per day. You grow without having to hire for every additional order.
Quotes, order confirmations and replies go out while the customer is still waiting. Whoever replies first and properly often wins the order.
The assistant checks everything, every time: previous order, stock, contract, prices. Discrepancies show up before they reach the customer or accounting.
How your team handles a case is written down in the work instructions. New colleagues get up to speed faster, and nothing is lost when someone retires.
Almost every application now comes with its own AI. But each one only sees its own slice. What makes the difference is how well your systems are connected.
The ERP has a chatbot, the mailbox a writing assistant, the document archive a search. A person still has to piece the case together, copying and pasting between five windows.
An assistant reads the e-mail, finds the case in the ERP, checks stock, contract and prices, and presents a finished proposal. Your team reviews, corrects and approves.
Three typical cases from everyday office work. Pick one and send the request to the assistant. You can change its proposal before approving it. Nothing is created or sent until then.
The workspace is a mock-up; companies, names and numbers are made up. In a real setup, the grey lines are queries to your systems.
The assistant takes care of searching and cross-checking. Your team steps in where needed: correcting quantities, changing texts, adding what the assistant cannot know. Wherever something becomes binding, a person decides.
E-mails and attachments, including scanned documents
Customer, supplier, case, contract
Stock, prices, dates, terms
Result and open points, each with its source
Correct, add, reject or approve
Create order, ticket or document, reply as draft
Send to customer, book, pay
Corrections are not lost: what your team changes often goes into the work instructions and, as a test case, into the test set.
Good candidates are cases that come up often, follow fixed rules and currently involve a lot of searching. A few examples:
Every workflow is made of the same four parts. None of it is secret knowledge: you can read, understand and shape them.
The Model Context Protocol is an open standard through which an assistant reads data and triggers actions. Built once, an interface works with many user interfaces and AI models.
find_customer · load_case · draft_orderA work instruction for the assistant, written as if for a new colleague. Your team can read and change it.
“Never silently replace discontinued items; flag the successor instead.”An assistant for one specific task. It knows its skills and only has the tools it needs for them.
Order intake: reads mailbox, CRM, ERP; only creates draftsThe framework around it: permissions, approvals, logging and test set. It keeps the assistant under control.
create_order → only after approvalWe build and run MCP interfaces to your systems: on your server, in a German cloud or with us. They do not belong to a single workflow or to a particular AI vendor. This is the part that stays.
Manuals, contracts, standards and guidelines, searchable for every assistant. Answers always come with document and page.
Read e-mails and attachments, create drafts. Microsoft 365, Exchange or IMAP.
Read orders, items, stock and purchase orders. Creating only as a draft or after approval.
Customers, contacts, contracts and the history of a case.
Hand over documents with a posting proposal, for example to DATEV.
Archive, network drive or Paperless-ngx: find, file and tag documents.
This is how we already work in software development: the workflow is described, connected to the systems, tested with real cases and then continuously improved. The same approach fits your office workflows.
With the colleagues who handle the case today: How do you recognise it? Where do you look things up? What exceptions are there? This becomes the work instruction for the assistant.
Each system involved gets an interface, read-only at first. The assistant sees what your team sees, and nothing beyond that.
What may it do on its own, where does someone have to approve, what gets logged? These rules are built into the technology and cannot be argued away.
A set of cases from last year, each with the result you expect. Every change has to pass this test set.
Two or three people work with it, every case with approval. What stands out goes into the work instruction.
Once the results are right, the next workflow follows. It builds on everything that is already there.
Start without risk: the analysis workshop and the first prototype are free. You only pay for the implementation once you are convinced. Interfaces, work instructions and code belong to you.
An assistant that works in your day-to-day business has to be accountable like a colleague. Three things make sure of that.
The assistant may read on its own. Anything that creates something in the ERP, goes to customers or moves money needs a click from you.
Which e-mail, which case, which source, who approved: everything can be traced later.
Before a changed work instruction or a different AI model goes live, it runs against the test set.
| Test case | Expected | Result |
|---|---|---|
| “same as in March” without order number | Correct previous order found | passed |
| Item since replaced by a successor | Flag instead of silent substitution | passed |
| Customer with framework agreement and special prices | Price from the framework agreement | passed |
| Order as scanned PDF, 6 line items | All line items recognised | 5 of 6 |
Interfaces, work instructions and rules do not belong to a single workflow. What was built for the first one is available to every further one. What is new is mainly the domain instruction and the test cases.
Find the previous order, cross-check changes in items, stock and prices, prepare the order for approval.
9 new building blocksAnswer questions about contracts and appointments from the knowledge base, with source. Mailbox, CRM and draft replies are already there.
4 new building blocksCheck invoices against purchase order and goods receipt, pass the document to accounting with a proposal. At its core, only the DATEV connection is new.
3 new building blocks| Building block | Repeat orders | Customer enquiries | Supplier invoices |
|---|---|---|---|
| Interfaces | |||
| Mailbox | new | existing | existing |
| CRM | new | existing | – |
| ERP & warehouse | new | – | existing |
| Knowledge base (EntropyZero) | – | new | – |
| Tickets & calendar | – | new | – |
| Accounting (DATEV) | – | – | new |
| Skills | |||
| Match case (customer, supplier, order) | new | existing | existing |
| Detect discrepancies | new | – | existing |
| Reply as draft | new | existing | existing |
| Back statements with sources | – | new | – |
| Propose posting | – | – | new |
| Harness | |||
| Permissions, approvals, logging | new | existing | existing |
| Test procedure for the test set | new | existing | existing |
| Test cases from real cases | new | new | new |
| To be built | 9 | 4 | 3 |
Every new building block is then also available to the earlier workflows. The knowledge base from stage 2, for example, can later back technical details in repeat orders with sources. The order of the stages follows your priorities.
Interfaces and work instructions stay the same, whichever user interface and AI model you end up using. We choose together, based on your requirements for data protection and cost.
From what you already use, to self-hosted web interfaces, to desktop assistants.
Chosen per task and replaceable without rebuilding interfaces.
On request we take over day-to-day operations, including updates and test runs.
No. It takes the searching and cross-checking off your team’s plate. Decisions, approvals and contact with the outside world stay with your people. They handle more cases in the same time, with fewer errors.
You decide. Typically: reading and creating drafts on its own. Anything binding, such as creating orders, sending e-mails to customers or handing over documents, only after a click from you. These rules are enforced technically, not just agreed.
Usually not. We connect the systems you already have. As the user interface, an AI tool you already use or a lean web interface on your server is often enough.
We sign a GDPR-compliant data processing agreement. If you wish, interfaces and models run entirely within your own infrastructure. For cloud solutions we only use providers with data centres in Germany or the EU.
Then you switch. Interfaces and work instructions are independent of the model. Before switching, the new model runs against your test set, so you can see whether it performs at least as well.
With a workflow that comes up often and can be described well. In the free workshop we pick it together and look at which systems are involved.
Tell us about it. In a free initial consultation we will tell you honestly whether and how AI can solve it.
Write to us — we will reply within one business day.