We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A course for people who will never write the code: choosing a task worth automating, assembling an agent out of blocks, and testing it before it is allowed near anything that matters.
Booked privately for your team. Dates and length are agreed when you book.
Every module ends with something participants can repeat on Monday morning, in your codebase and against your conventions.
Leave with a working agent handling a real task from your own week, not a demonstration built out of sample data.
Tell the processes worth automating from the ones where the automation quietly becomes the new problem.
Wire an agent into the apps and records your team already uses, with sign-off placed where it belongs.
Try to break your own agent deliberately, before it gets the chance to break something of yours.
Set out what it may do unsupervised and what stops for a person, then configure that rather than hope for it.
Know who maintains it, what it costs to run, and how anybody would notice if it quietly stopped working.
Built around hands-on work rather than slides. The running order and the depth of each module are adjusted to the group before delivery.
Every length is drawn from the same modules. A longer booking is more of the course, not a different one.
Half a day
A morning that ends with everybody having built something that runs. Enough to tell what this category of tool is genuinely for.
1 day
Adds the connections that make an agent useful rather than impressive: your apps, your data, and the approvals in between them.
2 days
Adds what happens when one goes wrong, what it costs to keep running, and who in the team owns it once the enthusiasm has moved elsewhere.
Not sure which one fits? The intake call settles it, and the length can still change afterwards.
The curriculum above is a starting point, not a syllabus. Before anything is booked I find out where your team actually stands, then rebuild the course around that. A team already running agents daily spends its two days somewhere completely different from one that installed the tool last week.
Step 1
A call before anything is agreed: what your team already uses, what has gone wrong so far, and what you need them doing differently afterwards.
Step 2
Language, framework, review process, CI. Exercises are rebuilt against your repository so nothing in the room is hypothetical.
Step 3
Modules get dropped, deepened or added. You see the adjusted outline and sign it off before the date is fixed.
Step 4
We run the course, then check in once the team has applied it to real work and the awkward questions have surfaced.
What gets adjusted
Same material either way. The format changes how much of it lands in the first week.
I come to your office and work with the team in the room. Usually the most effective option for a first rollout, because the sideways questions get answered as they come up.
Delivered live over video in focused blocks rather than one long day, with shared screens and hands-on exercises on your own work.
A day on site to get everyone moving, followed by shorter remote sessions once the team is applying it to real work and hitting real friction.
There is no public schedule. Every course is booked privately for a single team, and we agree the dates together.
Software engineer and AI coding trainer
I train engineering teams to work with AI coding tools, and I use the same tools to ship production software every week. The material comes out of building things, not out of a slide deck.
Before going freelance I spent six years as technical co-founder of a marketing agency, responsible for everything technical from automation infrastructure to coordinating a freelancer network. That is why the courses spend as much time on review, guardrails and rollout as they do on prompting.
The things teams ask before booking. If yours is not here, ask me directly.
Really none. Everything is assembled visually, and the half-day version exists because most groups need a morning rather than a full day to reach something that works. What the course does ask for is that you know one of your own processes properly, because that is the raw material.
One chosen to fit your group and your IT constraints, from the current no-code agent builders. The technique transfers, which matters in a category that changes this fast. If your organisation has already licensed one, we use that and the day gets more useful for it.
Vibe coding builds you an application: a thing with screens that people open. This builds a worker: something that runs on its own and does a job over and over. Different tools, different ways of failing, and plenty of teams eventually want both.
Handled in the room rather than left to chance: which data may reach these platforms, what they keep, where approvals belong, and how to get a proposal through your own IT department rather than around it. Bring the policy and we work against it.
Usually one or two things do, which is roughly the honest rate and better than it sounds. The last module is about exactly that: what to write down, who owns it, and how anyone would notice if it stopped. Most of what does not survive was a task that should never have been automated, and finding that out costs a workshop rather than a quarter.
Five to twenty. Everyone builds their own agent from their own process, and those get stuck in different places, so beyond twenty the queue for help gets too long to be useful.
Still not sure whether this is the right fit for your team?
Tell me the size of the group, the codebase they work in, and roughly when you want to run it. I will come back with a proposal.
Delivered in English or German, on site across Europe or remotely.
Trusted by teams & training providers
I deliver AI training for some of Europe's leading organisations and L&D platforms.
Cegos Integrata
Commissioned trainer via leading European L&D provider
NobleProg
AI coding workshops via one of the world's largest IT training marketplaces
Innomotics
In-house AI training for engineering teams
Bots & People
Commissioned trainer for developer workshops
Code First Girls
Course creator — 3-month AI & agentic tools curriculum
Nomad Summit
Conference speaker on AI tools, agentic development, and developer workflows (2025)
Vertiv
In-house AI-assisted coding training for engineering teams