AI and digital development

AI automation that actually reaches production

Head of Digital at Gullström & Co. I build digital platforms and automate the work people should not be doing.

I work as Head of Digital at Gullström & Co, a concept and communications agency in Karlstad, Sweden. Engagements run through the agency, with its full production behind them. gullstrom.se

What I do

Four things, properly

AI automation
Read more about AI automation
Repetitive processes that run themselves, with an audit trail and a human still in the decision.
AI in product and site
Read more about AI in product and site
Search, assistants and generated content built in where the customer already is.
Digital development
Read more about Digital development
Sites, storefronts and integrations built to load fast and stay maintainable.
AI visibility and search
Read more about AI visibility and search
Getting cited when the answer is written by a language model instead of listed by a search engine.

All services

How it runs

The same order every time, whether the project is a four-week automation or a rebuilt storefront.

Map it
We walk the process step by step and cost out where the time goes. Sometimes it ends here because the numbers do not carry. That is a good outcome.
Build small
A working version on real data, usually within weeks. It has to be switchable off without anything else breaking.
Put it live
The flow is wired into your systems with logging, alerting and an approval step wherever the decision needs a person.
Hand it over
Documentation, code and accounts sit with you. You should be able to change supplier without a rebuild, and that holds when the supplier is me.

Common questions

The questions that usually come up in a first call, answered ahead of time.

What does an AI automation project cost?

It depends on how many systems have to be connected, not on how advanced the model is. Most engagements start with a bounded pilot lasting a few weeks, and the price is set after the process has been mapped, never before. If the saving does not cover the build, I say so and there is no project.

How long before an automation is live?

A bounded automation is usually live within four to eight weeks of the first meeting. What stretches the timeline is almost never the build, but system access, deciding who is allowed to approve what, and finding enough real data to test against.

Which tools and models do you work in?

Automations are usually built in n8n, or in Python when the flow needs more control. For language models I use Claude and OpenAI, chosen per task rather than by default. On the web side I work in Astro, WordPress and WooCommerce. The choice follows what you already maintain, because a tool nobody on your side can operate is a cost rather than a solution.

How is AI automation different from ordinary automation?

Ordinary automation requires the input to look the same every time. AI automation copes with input that varies: an email phrased three different ways, an invoice in five different layouts, a ticket with no clear category. The language model handles the interpretation step and the rest of the flow is ordinary integration. Where the input is already structured, no AI is needed and we build it cheaper without.

How do you stop the AI from making things up?

By constraining what the model is allowed to answer from. Instead of answering from memory it retrieves your documents and answers only from those, with a citation. On top of that, the flow includes an approval step before anything hard to undo happens, and logs both prompt and response so deviations are found in review rather than by a customer.

Do you work with companies outside Värmland?

Yes. Gullström & Co is based in Karlstad and some work happens on site in Värmland, but automation work runs just as well remotely and a large share of clients sit elsewhere in Sweden. What benefits from being in the room is the mapping at the start, and that fits in a day.