Your team has AI tools.
Nobody agreed on how to use them.
A 2-day hands-on workshop that turns scattered AI experiments into a shared engineering discipline. Day one we build the system. Day two we apply it to your codebase.
Request the workshopThe Problem
Every engineer on your team uses AI differently.
One writes everything by hand and distrusts the output. One pastes entire files into a chat window. One lets an agent run wild and ships code nobody can review.
The result is what you'd expect: inconsistent quality, unreviewable pull requests, and no shared practice. The tools are powerful. The way most teams use them is chaos.
Chaos is usually a missing system.
The Shift
Agentic engineering draws a clean line.
Agents do the implementation. Engineers own the architecture, the spec, and the correctness.
That means you start with a plan. You write the spec before you prompt anything. You break work into well-defined pieces. You build reusable skills so the agent gets better at your codebase over time, instead of starting from zero every session.
It's not a trick collection. It's a workflow your whole team can share, review, and improve.
The Two Days
Day 1 — The System
We build a real tool together, from scratch, the agentic way.
- Where everyone stands: a quick calibration of how your team works with AI today
- What agentic engineering actually is, and where the line to vibe coding runs
- Live build: brainstorm four epics, iterate the spec, then implement epic by epic
- Extracting skills as we go, so reusable agent instructions become a byproduct of real work
By the end of day one, everyone has run the full loop: spec, implement, review, extract.
Day 2 — Your Reality
No demo project. Your code.
- Brownfield skills: making agents useful in an existing, grown codebase
- Teams and individuals work on their own projects, with me coaching across the room
- Presentations and lessons learned: what worked, what broke, which skills you keep
You leave with skills built against your actual repositories, not a toy app you'll never open again.
What You Leave With
- A shared vocabulary and workflow for agent-driven development across your team
- 3 to 5 working skills, built during the workshop, against your own code
- A spec template and playbook you can use Monday morning
- An honest map of where agents help and where they don't
That last point is deliberate. I run a tech organization. I have to live with the code that gets shipped. I won't sell you the story that agents replace engineering judgment. They amplify it, if the system is right.
Why Day 2 Is the Point
Most AI workshops end with a greenfield demo and a good feeling. Then Monday comes, the real codebase is messy, and everything learned falls apart.
That's why half of this workshop happens inside your reality: your repos, your legacy decisions, your constraints. The skills you extract on day two are the ones that survive contact with actual work.
Who This Is For
Engineering teams of 6 to 12 people who already have access to an agentic coding tool (Claude Code or comparable) and want a shared, disciplined way of working with it. Product owners and engineering leaders are explicitly welcome too — those who don't just want to sign off on the workflow but understand it, because agentic engineering changes how specs, reviews, and ownership get distributed across the team.
You should bring: laptops, a working dev environment, and at least one real project per group for day two. I'll send a setup checklist a week before so we spend the first morning building, not installing.
This is not an intro to AI. It's for teams that are past "should we use this" and stuck at "how do we use this well, together."
About Daniel
I'm Daniel Hauck, Director of Technology at Europe's largest music retailer, where I lead engineering teams and the organization around them. On the side I build and ship a SaaS product solo, using agentic workflows daily. This workshop is the system I actually work with, not theory I collected.
Logistics & Investment
Format: 2 days, on-site at your office or remote
Group size: Up to 10 participants included, additional seats on request
Investment: 7,500 € plus travel. Preparation and setup checklist included.
Languages: German or English
One offer, no tiers. If the format doesn't fit your team, we talk and adjust it before you commit.
What Happens After
The workshop gets your team through the loop once, together. Making agentic engineering the default in your company is the actual goal — and that starts with a deliberate decision, not something that happens on its own.
From there, the work is building common standards: a shared way to get everyone to the same level of agentic fluency, not five different approaches living side by side.
A good first step is looking at your specific setup together — I join a real refinement, we work through an actual problem, and I help you figure out how this fits your stack. Every team's constraints are different, and that's where it gets real. From there, you can book me for this kind of work as needed.
Ready to give your team a shared system?
Send me a short note about your team, your stack, and roughly when you'd want to run this. I'll get back to you within two working days.
Request the workshop