Team training:
Build for AI
Book a callWhich format suits your team?
Same workshop, same content. You choose the split.
What your team takes away
An AI feature from the API to the safeguards, with evals that make quality measurable.
LLM APIs, agent architectures, MCP and AI interaction beyond the chat window. The base is the same for everyone, and you choose the focus topic: MCP server, RAG, Agentic UI, local models or n8n. We clarify the starting point and focus with you beforehand.
Code review beforehand
We look at your project beforehand: a code review shows where AI features fit into your product and which focus topic pays off.
Hands-on in your stack
We code together on a sample project: first API calls, agents with tools and how to secure them.
No AI experience needed
Programming experience is enough. We work out everything else together.
Live online, worldwide
Live and interactive with your team, no travel needed: hands-on exercises, open discussion and time for your questions.
Four days of 5 hours each
For example 9am to 3pm including breaks. Between the sessions you put what you learned to work in your day-to-day business.
Learning in small groups
We recommend up to 12 people per course, which leaves time for your questions. For larger teams we suggest splitting up, for example into 2 × 10; one joint course works too.
4 days of AI training
Online
From the API to a finished feature.
The base for everyone, plus the focus topic that fits your product.
As an online training: 4 × 5 hours.
Topics & content
BLOCK01- Models, providers, costs: the right choice for your feature
- Integrating LLM APIs: streaming, structured output, tool use Hands-on
- Prompts as code: versioning, tests, evaluation
- Error cases, timeouts and fallbacks
- Controlling latency and cost in production
- The first AI feature in the sample app
Your first AI feature
Integrating LLM APIs
An AI feature has to answer reliably, handle errors and stay within budget. In the first block you choose a model, integrate the API and build a first feature into the sample project.
- When an agent, when a workflow?
- Designing tools: interfaces a model understands
- State, memory and context limits
- Testing non-deterministic features with evals
- Guardrails: prompt injection, permissions, output control
- Observability: tracing, cost and quality in production
- An agent for a task from your domain Hands-on
BLOCK02Agent architectures
Tools, state, evals
Agents plan, call tools and decide on the next step themselves. That takes architecture. You learn to design tools, manage state, and test and secure non-deterministic features so you can stand behind them.
BLOCK03- MCP server as a product interface
- Agentic UI: A2UI, AG-UI, WebMCP and MCP Apps
- RAG & your own knowledge
- Sovereign AI: local models on your own hardware
- Automating workflows with n8n
Your focus topic
A topic of your choice
The last block belongs to a topic of your choice: day 3 on site, day 4 online. You pick it below when you book the call; we adapt examples and order to your project.
All participants receive a certificate plus the sample code, setups and cheat sheets from the course to take home.
Your trainer
Johannes runs every training himself, with the knowledge from his ongoing projects.All workshops since 2016 in the Hall of Fame →
Johannes Hoppe
is a Google Developer Expert (GDE) and works as a freelance software architect, consultant and trainer with a focus on agentic coding, Node.js, .NET and Angular. He is co-author of the standard German-language book on Angular. Alongside the trainings he works as a lead frontend developer in client projects and applies what he teaches there.
Johannes lives in Leimen near Heidelberg.
Bluesky: @johanneshoppe.de
LinkedIn: @johanneshoppe
Frequently asked questions
◢ What does the training cost?
Base plus focus topic cost €6,600 net online (4 × 5 hours) and €8,250 net on site (3 × 7 hours) including travel, expenses and accommodation. It is a fixed-price offer for your team; the actual number of participants does not change it. For comparison: with twelve participants that is €550 or €688 per person.
◢ Who is the training for?
Development teams that want to bring AI features into their own product, backend as well as frontend. Programming experience is enough; prior LLM knowledge only shortens the introduction. We align the sample project with your stack; without a preference we use TypeScript.
Online everyone needs a laptop with webcam and microphone, Node.js and an IDE. The installation guide arrives well in advance, and shortly before the training we run a tech check.
◢ Which models and SDKs are covered?
We work with the official SDKs of the major model providers and with open models via Ollama or vLLM. The architecture keeps the model interchangeable. If only one specific provider is allowed at your company, we align the exercises accordingly.
◢ How does the hands-on part work?
The course is a mix of theory and practice: you practise on a sample project that we tailor to your stack and your questions after the code review. Each topic is explained first and then implemented in code; you work on selected exercises in small groups. Your company code stays with you; concepts and sample code are built so that you transfer them straight into your product. You get the code for the sample project in the course. For working with coding agents as a team there is Build with AI.
◢ Are there learning materials?
For every topic block we prepare a handout. Our detailed slide decks let you follow every topic comfortably. You get all the slides after the training. You also take home the sample code, setups and cheat sheets from the course and can reuse them in your own project.
◢ When and how long?
We agree on the dates with your team. Online it is four days of 5 hours each (e.g. 9:00 to 15:00), on site three days of 7 hours each, breaks included. Between the online sessions you try out what you learned in your daily work.
◢ Which language is the workshop held in?
In German or English, as you prefer; the course materials are available in both languages.
◢ What about data protection and confidentiality?
You do not need any company data for the exercises: you practise on the sample project, with trial accounts for the AI providers. Your code and your data stay with you; for the code review beforehand you send us only what you want to show, we treat it confidentially and delete it after the training. If only certain providers or local models are allowed at your company, we align the exercises accordingly. From the participants we only need names for the certificates. If your compliance requires a non-disclosure agreement or a data processing agreement, just let us know.
Still have questions?
+49 151 681 222 66 (Johannes Hoppe)
Standard rate to German mobile networksWe'll get back to you within 24 hours.Book a call
Tell us briefly where your team stands. We’ll get back to you with suggested times.
- Call30 minutes, free of charge. We clarify the starting point and the focus topic.
- Quote within 24 hoursOne fixed price for your team.
- A date that suits your calendarWe suggest dates that suit your team, online worldwide or on site in Germany, Austria and Switzerland.
Focus topic for the last block
If you already know it, pick it here. Otherwise we clarify it in the call.
net, €550 per person for 12 participants
Four online days of five hours each: three days for the base, the fourth day belongs to your focus topic. We agree on the exact schedule with you.