We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Build AI agents that take whole workflows off your engineers' plates. Two or four days of building, breaking and fixing one until it is safe to run unattended.
Rebuilt on your team's work
Run privately for your team, on dates and at a length that suit you.
Every module ends with something participants can repeat on Monday morning in their own work and tools, so the team gets more done without adding people.
Spot the workflows an agent improves, and the ones a plain script handles better for less.
Design tool interfaces an agent calls correctly the first time, without being told three times what the arguments mean.
Break a long task into steps that can be retried, resumed and reasoned about after the fact.
Build an evaluation set that tells you whether each change helped.
Decide in advance what an agent may do unattended and what waits for a person, then enforce it in code.
Instrument an agent so your own dashboards flag misbehaviour before a customer does.
Most of the time goes on hands-on exercises. Module order and depth are set for your group before the first day.
Every length uses the same modules. A longer booking takes the team further through the same curriculum.
2 days
Two days to build a working agent and understand what it is doing. Enough to judge whether the use case in front of you is one an agent should handle at all.
4 days
Adds what turns a demo into a system people rely on: evaluation, failure handling, cost control and monitoring.
We settle the length when we talk about your team, and it can still change afterwards.
Your version builds an agent for a workflow your team actually runs, against your own APIs and data, in the language and framework you already use. The evaluation exercises draw on cases from that workflow, so the team leaves with a test set it can keep using.
How a booking worksIn your office, with the team in the room. Best for a first rollout.
Live over video, in shorter blocks across several days.
A day on site to start, then shorter remote sessions on real work.
Every course runs privately for one team, on dates we agree together.
Every module can be rebuilt on your team's own work and tools. Tell me what the team works on and I will tell you what I would change.
AI agent trainer and software engineer
I build LLM systems that run in production, from a multi-stage translation pipeline serving paying clients to a video Q&A tool that answers with cited timestamps.
From engineering teams I trained to work with AI agents.
I worked closely with Luka as the topic sponsor for a workshop on integrating AI meaningfully into everyday development work.
He took the time to understand our participants' needs and adapted his approach to the tools and working environments available.
Participant feedback reinforced my own positive experience, with especially strong recognition of his subject expertise and the balance between theory and practice.
I wholeheartedly recommend Luka as a trainer to any team looking to build practical AI skills.
What teams ask before they book.
Enough to have called an LLM API and seen what comes back. The course starts where you want a model to act on its own. Strong general engineering experience is the main requirement.
We build one agent with a framework and one without, so the team understands the loop whatever library it uses later. Tell me what your team already uses and the exercises run there. If nothing is chosen yet, the course is a good place to choose.
Yes, and the four-day version is mostly that. Bring a real workflow you are thinking of handing over. Some groups decide during the course that theirs should stay a script, and finding that out in a workshop costs days instead of a quarter.
Modest, but not nothing, and agent runs cost more than chat does. I send an estimate along with the requirements once we have a date. If you would rather cap it, most of the material runs against smaller models without losing the point.
It depends on the workflow, and the course gives the team what it needs to decide. A platform is quicker for common tasks that fit its shape. Your own agent pays off when the work touches your systems in ways no platform anticipates, or when you need to test and control every step.
Have a question about your team's setup?
Tell me what your team works on and how it uses AI today. A few lines are enough. I reply myself, usually within a day, and if this course is the wrong one I will point you to the one that fits.
In English or German, on site, remote or hybrid.
Building AI Agents
A few lines are enough
Engineering teams and providers I have delivered AI training for