Which format works for your team?
Same workshop, same content. You choose the schedule.
The team training for development teams
In 4 days from “we installed Copilot”
to “AI agents are part of our workflow”.
Your team writes software and is expected to deliver faster with AI – without quality tipping over. In this training you'll learn to use AI agents productively: building features, finding bugs, writing tests, modernising legacy code. Tool-neutral, with Claude Code as the common thread and an honest comparison of Codex, Antigravity & Cursor.
For your whole team
Online or on-site at your company – you pick the format, we tailor the content to your project
Compact sessions
Half days online or full days on-site – leaving room for your daily business
Your own agent from day 1
No spectating: from the very first hour you'll have an agent working on real code
No AI experience needed
Programming experience is enough. We build everything else together from the ground up.
Learning in small groups
More time for individual topics: we recommend groups of up to 12 participants.
More than just a video course
Live and interactive: hands-on exercises, open exchange and time for your questions
4 days of AI training
Online
From your first agent to a team-wide workflow.
Everything for productive work with AI agents – from Claude Code to your own MCP server.
As an online training: 4 × 5 hours.
Topics & content
BLOCK01- How LLMs tick: tokens, context windows, limits
- Why agents fail – and why they don't
- Claude Code: setup and first tasks Hands-on
- Project memory with CLAUDE.md
- Delegating tasks the right way
- Letting agents work on real code
- Reading and evaluating the results
Understand & get going
From the model to your first productive agent
No wizardry: if you understand how these models really work, you'll work better with them. In the first block we lay the foundation – and then head straight into practice. By the end of day 1, everyone has had an agent working productively on real code and understood why it does what it does.
- Context engineering: the right knowledge at the right time
- Spec-first: specification before code
- Reviewing plans before the agent gets going
- Guardrails
- Tool comparison: Codex, Antigravity, Cursor Live
- Reviewing AI code: typical classes of bugs
- Tests as a safety net
BLOCK02Stay in control
From toy to tool
The difference between frustration and flow is context. You'll learn to prepare your project so agents can find their way around – with specifications, reviewed plans and guardrails. And you'll learn to check AI-generated code systematically instead of trusting it blindly.
BLOCK03- Understanding MCP: the power socket for AI systems
- Using MCP servers: browsers, databases, internal APIs
- Building your own MCP server (TypeScript SDK) Hands-on
- Skills: encapsulating recurring tasks
- Subagents and parallelisation
- Multi-agent workflows
Extend & connect
Plugging agents into your world
The Model Context Protocol (MCP) connects agents to your systems – databases, browsers, internal APIs. In the course you'll build your own MCP server and learn to encapsulate recurring tasks in skills and let several agents work in parallel.
- Agents in CI/CD: GitHub Actions
- Automated code reviews
- Headless: tasks that run overnight
- Legacy refactoring with agents Hands-on
- Team workflows and knowledge sharing
- Understanding and controlling costs
- Roadmap: your first 30 days afterwards
BLOCK04Automate & anchor in the team
From personal workflow to team practice
It gets really exciting when agents work unsupervised: automated code reviews, tasks in the CI pipeline, refactorings overnight. In the hands-on case of legacy modernisation you'll bring it all together – and take home a concrete roadmap for how your team anchors these workflows in its first 30 days.
All participants receive a certificate plus all the setups, configs and cheat sheets from the course to take home.
Ready? Get a quote.
Tell us briefly where your team stands – you'll receive a binding fixed-price offer within 24 hours.
Your trainer
Your trainer Johannes Hoppe is a Google Developer Expert (GDE)and co-author of the German-language standard reference
„Angular: The Practical Guide – from the basics to advanced development with Signals".
Johannes Hoppe
is a Google Developer Expert (GDE) for Angular and works as a freelance software architect, consultant and trainer focusing on agentic coding, Angular, Node.js and C# / .NET. Outside of teaching, he is a lead frontend developer at a mid-sized company.
Johannes lives & works in Leimen near Heidelberg.
Bluesky: @johanneshoppe.de
LinkedIn: @johanneshoppe
X (Twitter): @JohannesHoppe
Frequently asked questions
◢ Who is this training for?
Development teams that want to use AI agents productively – whether web, backend or both. You don't need any AI experience: we build up the concepts together from scratch.
◢ What are the prerequisites?
To take an active part in the training you should bring some programming experience. Our examples lean towards TypeScript, but the concepts apply to any stack. All participants need their own laptop; you'll receive a detailed setup guide in advance. If you have any questions about the preparation, we'll support you personally.
◢ Which tools do you cover?
The common thread is Claude Code (our recommendation). Alongside it we compare Codex, Antigravity and Cursor – honestly, with strengths and weaknesses. Trial accounts are enough for the exercises; what continuous use costs and how to keep those costs under control is part of the course itself.
◢ How much of the course is hands-on?
The course is a mix of theory and practice: from day 1 you'll have an agent working on a real sample project. Every topic is covered in theory first and then put into practice right away. Selected exercises are worked on independently in small groups. The code for the sample project is always available on GitHub.
◢ Do we practise on our own code?
You'll practise on a sample project we provide – your company code stays with you. On request we run a code review beforehand and tailor the focus to your project; for AI features in your own product there is Build for AI.
◢ Are there learning materials for the training?
For every topic block we prepare a handout. Our detailed, up-to-date slide decks let you follow every topic comfortably. Of course you'll get all the slides. You'll also take home all the setups, configurations and cheat sheets from the training – ready to use in your own project.
◢ Can we ask individual questions?
Yes! For every topic we run open Q&A and discussion sessions. We work with AI agents every day ourselves and can answer many questions first-hand.
◢ When does the training take place?
We align the date together with your team. Online we recommend half-day sessions (e.g. 9:00 to 15:15), on-site compact full days – coffee and lunch breaks included.
◢ Who is the trainer?
Your training is run by Johannes Hoppe – book author, Google Developer Expert (GDE) and trainer with over 100 workshops since 2016. He works with AI agents in real projects every day and shares his hands-on knowledge first-hand.
◢ Is the training a recording?
The training takes place live with your team. You can ask individual questions and stay in direct contact with the trainer. The workshop is not recorded.
◢ In which language is the workshop held?
In German or English, as you prefer; the course materials are in German, many cheat sheets and setups in English.
◢ Why a 4-day training?
You can click around a tool in two hours – productive workflows, control over the results and anchoring it all in your team take practice. Four half days online (or three full days on-site) are the sweet spot for us: enough time to go deep, and between sessions you can apply what you've learned directly in your daily work.
◢ How do things go on after the workshop?
Even after the training we're happy to keep supporting you, subject to availability, with individual consulting – for example through our Office Hours.
◢ How can we book?
Booking works by enquiry: drop us a quick line and you'll receive a binding offer with all the details within 24 hours.
◢ Why us?
We put quality over quantity, and learning success is our top priority. In small groups we can address every question and support all participants individually. We work with AI agents every day ourselves and publish our findings openly on the blog – you get an honest picture of what works. And what doesn't.
Still have questions?
+49 151 / 681 222 66 (Johannes Hoppe)
Standard rate to German mobile networksWe'll get back to you within 24 hours.Ready? Get a quote.
Tell us briefly where your team stands – you'll receive a binding fixed-price offer within 24 hours.