We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Hand engineering tasks to Codex, run several at once, and review what comes back, so each developer gets more of the backlog done.
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.
Write a brief complete enough that the task comes back finished.
Keep several independent tasks in flight without losing track of which branch is holding what.
Define the container a task runs in so it has every dependency it needs and none of your credentials.
Read a change that was written without you watching, and know which parts of it to check first.
Drive Codex locally for the work that is quicker to supervise than it is to specify.
Separate the tasks worth delegating from the ones where writing the brief costs more than the work.
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.
1 day
The delegation model and how to scope a task so it comes back finished. One day, and for most teams that is the whole of it.
2 days
Adds the local command line and the work of fitting delegated changes into a review process that was designed for humans.
We settle the length when we talk about your team, and it can still change afterwards.
Your version uses your repositories and your environment: the setup script installs your real dependencies, the task briefs come from your backlog, and the review exercise looks at changes Codex made to your own code.
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
Codex was part of the programme I ran for engineering teams at Deutsche Telekom, next to Copilot and Claude Code, and I hand work to coding agents every day to ship production software.
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.
No. The delegation model is easier to pick up than pairing with an agent, because there is far less to steer in real time. Working knowledge of pull request review matters much more, since that is the skill the entire day rests on.
A Codex-enabled account each, plus a repository they are allowed to open pull requests against. Both are worth arranging a week ahead. I send the exact requirements once a date is agreed, including which plan covers the parallel task work.
Yes, and the environment setup module only pays off if they do. Half of what makes delegation work is a container that can install your dependencies and run your tests, and getting that right for your stack is the best use of workshop time.
Yes, because the working model is different: one is a conversation you steer, the other is a brief you hand over and come back to. Teams using both tend to split their work between them. If you only want one course, the Claude Code one is broader; this one goes deeper on delegation.
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.
Codex Training
A few lines are enough
Engineering teams and providers I have delivered AI training for