AI automation
AI automation means a workflow is executed by software instead of a person, with language models handling the steps that require interpretation: reading an email, understanding an invoice, routing a ticket, drafting a reply. I build these flows in n8n and Python, connect them to the systems you already run, and leave logs behind so every execution can be audited afterwards.
How the flow runs
The trigger
An email arrives, a form is submitted, the clock hits seven.
The interpretation
The language model reads and works out what it is about.
The checks
Code sums, looks up and validates. Never the model.
The approval
A person confirms anything hard to undo.
The execution
The system updates, the reply goes out, everything is logged.
Where it usually pays off
Ticket routing, inbound quote requests, invoice processing, product data for e-commerce, report assembly and internal knowledge search. What they share is variable input with a rule-driven decision, which is precisely the gap language models fill.
Humans in the loop
Automations that decide without visibility get switched off within six months. So every flow ships with an approval step where one is warranted, alerts when something deviates, and a full log of what the model saw and what it answered.
What it costs not to
Before anything gets built we measure the current state: how often the process runs, how long it takes and what it costs in salary. If the numbers do not work, we do not build it. Reaching that conclusion in a meeting is cheaper than reaching it after a project.
In this area
n8n development
Workflows built in n8n, self-hosted or in the cloud, with code where code is warranted.
Document and invoice flows
Invoices, orders and contracts read, checked and posted without manual entry.
Customer support and ticketing
Incoming tickets sorted, prioritised and answered with the draft already written.
Reporting and data flows
Data pulled, assembled and commented on automatically, on a schedule.
In this area
AI automation 101: what it is and when it pays off
What AI automation actually is, where the line sits against ordinary automation, and how to decide whether a process is worth building.
Seven processes that are almost always worth automating
Concrete workflows where AI automation tends to pay off, and what makes those particular ones suitable.
How to cost an automation before you build it
A concrete method for deciding whether an automation project carries, including the costs people routinely forget.
Other services
- AI in the productSearch, assistants and generated content built in where the customer already is.
- Digital developmentSites, storefronts and integrations built to load fast and stay maintainable.
- AI visibilityGetting cited when the answer is written by a language model instead of listed by a search engine.
