We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Get the output you are already paying for from every Copilot seat: the surfaces nobody opened, its part in the pull request, and the controls nobody configured.
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.
Get more out of inline suggestions by shaping what the code around the cursor tells the model.
Use chat for the questions it answers well, and recognise the ones it will answer confidently and wrongly.
Run one instruction across a set of files with agent mode.
Put Copilot to work in the pull request while a person still reads the diff.
Configure content exclusion, policy and the public code filter so the tool matches what your organisation has agreed to.
Gather the kind of evidence a sceptical finance director would accept about whether the seats are worth renewing.
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
Every Copilot surface beyond the grey text at the end of the line. The day most teams should have run a year ago.
2 days
Adds its part in the pull request, and the policy controls an organisation wants settled before it widens access any further.
4 days
Adds the rollout work: shared instruction files, extensions, seat management, and evidence that the licences are earning what they cost.
We settle the length when we talk about your team, and it can still change afterwards.
Your version starts from where your Copilot rollout stands: the seats and policies you already have, your repositories as the exercise ground, and custom instructions written for your codebase. On Copilot Business or Enterprise, the policy module works through your organisation's own settings.
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 ran a multi-module, German-language programme for engineering teams at Deutsche Telekom with GitHub Copilot as the main tool, alongside Claude Code and Codex.
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.
That is the room this course is built for. Teams who have had it for a year are usually still living in the completions, and the day is mostly spent on everything else. If your team is fluent across all of it, say so and I will suggest a different course.
Yes, an active seat each on the day. In most organisations booking this course the seats already exist, which is usually why the course is being booked at all. If some participants are unlicensed, tell me the split and I will pair them with somebody who is.
Yes, and it is worth doing with your administrator in the room. Content exclusion, the public code filter and audit logging are settings somebody has to own, and the usual state is that nobody has looked at them since the rollout. Bring the administrator and the decisions get made on the day.
Yes, wherever your policy allows it. Copilot's behaviour depends heavily on what surrounds the cursor, so a real repository with real conventions is where the exercises land. If content exclusion blocks parts of it, that is a far better thing to discover in a workshop than in production.
If Copilot is what everybody has today, yes, because those seats are already paid for either way. If the evaluation is still open, AI Coding Training is the better use of the day: it is built around choosing a tool, and this one around getting more out of the one you chose.
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.
GitHub Copilot Training
A few lines are enough
Engineering teams and providers I have delivered AI training for