AcademyMy Course

Applied
AI

From prompt engineering fundamentals to autonomous agent systems: a four-week intensive I teach in person, through machine learning, automation and agentic workflows. Every concept practised hands-on, every tool used on real problems.

Prompt Engineering, 1 module. You leave with a custom AI assistant of your own.

Read week 1 in full

Four weeks, thirteen modules

The course from the first prompt to the final film, in the order it is taught. Every week ends with something you have built yourself.

  1. Week 1

    5 days

    Prompt Engineering

    “Before you can build with AI, you need to speak its language.”

    Five days of structured practice, from zero to writing system prompts. By Friday, everyone has built a custom AI assistant with memory and personality.

    1 module, plus prompt practice, machine learning, deep learning, neural networks, automated assistants

    1. Also this week

      Prompt practice

      Writing system prompts that control tone, format and reasoning depth. Students work inside Claude and the OpenAI Playground and learn temperature, top-p and stop sequences hands-on, not from slides.

      Tools and platforms

      • Claude
      • OpenAI Playground

    2. Also this week

      Machine learning, deep learning, neural networks

      The foundations behind every AI tool: how machines learn from data, what makes learning deep, and how neural networks turn examples into predictions.

    3. Also this week

      Automated assistants

      Assistants built and tested in the Playground, with an eye on how far they can be automated and personalised, for example a finance assistant with access to company data.

      Tools and platforms

      • OpenAI Playground

    4. The week's module

      Local LLMs

      Not every model needs a cloud. This module covers running language models on your own hardware: when it makes sense, how to set it up, and what you trade off in speed, privacy and capability. Students install Ollama, pull quantized models and benchmark inference on consumer GPUs.

      Tools and platforms

      • Ollama
      • LM Studio
      • Open WebUI
      • GPT4All
      • Hugging Face

      Course materials

      • PDF
      • PPTX

    Week 1 ends with

    A custom AI assistant of your own

  2. Week 2

    5 days

    AI in BusinessFrom Strategy to Content

    “The real skill isn't using AI tools — it's knowing which problem to point them at.”

    This week bridges technology and business thinking. Students identify real use cases, build a business plan with AI support, develop marketing assets with generative tools and present a startup pitch, complete with AI-generated visuals, a value proposition and a market analysis using Tree of Thoughts prompting and Porter's Five Forces.

    4 modules

    1. Module 1 of 4

      AI-Powered Applications

      A hands-on comparison of tools that write, format and optimize job applications. Students test each tool with their own CV and measure the output quality. The module ends with a critical analysis: where does AI save time, and where does human judgment still win?

      Tools and platforms

      • Kickresume
      • Rezi.ai
      • Teal HQ
      • Enhancv
      • ChatGPT

      Course materials

      • PDF
      • PPTX

    2. Module 2 of 4

      Research & Business

      From Perplexity deep-dives to AI-driven competitive analysis. Students use search-augmented generation for market research, build a Business Model Canvas with AI assistance and develop a value proposition with the Ventures Kit.

      Tools and platforms

      • Perplexity
      • Consensus
      • Ventures Kit
      • Piktochart
      • Gamma
      • HeyGen

      Course materials

      • PDF
      • PPTX

    3. Module 3 of 4

      Content & Design

      Canva, Adobe Firefly, Ideogram, Piktochart: the tools are easy. The hard part is a visual language that works across channels. Students create a cohesive brand kit: logo, social media templates, infographic and presentation deck.

      Tools and platforms

      • Canva
      • Adobe Firefly
      • Ideogram
      • Piktochart
      • Leonardo.ai

      Course materials

      • PDF
      • PPTX

    4. Module 4 of 4

      Image & Video Generation

      Diffusion models at a conceptual level, then in practice. Students run the same creative brief through Midjourney, DALL-E 3, Stable Diffusion and Runway: prompting strategies, negative prompts, style transfer and the current limits of generative consistency.

      Tools and platforms

      • Midjourney
      • DALL-E 3
      • Stable Diffusion
      • Runway
      • LTX Video
      • Kling AI

      Course materials

      • PDF
      • PPTX

    Week 2 ends with

    A startup pitch with value proposition and AI visuals

  3. Week 3

    5 days

    Automation & Data Analysis

    “Data without decisions is noise. Automation without understanding is fragile.”

    Week three makes the abstract concrete: students process real datasets in Python and Julius.ai, build dashboards that tell a story and wire up their first Make.com automations end to end. The capstone: design, build and present a newsletter automation that runs without human intervention.

    3 modules

    1. Module 1 of 3

      Machine Learning

      The mathematical intuition behind every AI tool on the market: not formulas on a whiteboard, but why a model predicts what it predicts. Students train a simple classifier in Google Colab and evaluate it with real metrics.

      Tools and platforms

      • Google Colab
      • Python
      • Julius.ai
      • Scikit-learn
      • Pandas

      Course materials

      • PDF
      • PPTX

    2. Module 2 of 3

      Automations

      Make.com from first principles. Students build three scenarios of increasing complexity: a simple webhook listener, a multi-step data transformation pipeline and a full newsletter automation with conditional logic.

      Tools and platforms

      • Make.com
      • Miro
      • Zapier
      • Notion
      • Slack
      • Google Sheets

      Course materials

      • PDF
      • PPTX
      • HTML

    3. Module 3 of 3

      Learning & Research

      How to learn faster with AI as a research partner. Students use NotebookLM for source synthesis and Consensus for scientific paper search, and build a personal knowledge system that turns unstructured reading into structured insights.

      Tools and platforms

      • NotebookLM
      • Consensus
      • Elicit
      • Semantic Scholar

      Course materials

      • PDF

    Week 3 ends with

    A newsletter automation that runs on its own

  4. Week 4

    5 days

    App Development & Agents

    “The final week is where everything converges — code, models, and autonomous systems.”

    Students go from consuming AI to building with it. They host models on Hugging Face, prototype apps with v0 and Lovable, understand MCP (Model Context Protocol) and build an agentic workflow that chains several AI steps into an autonomous system. The course ends with a creative challenge in which teams produce a short AI-generated film.

    5 modules

    1. Module 1 of 5

      Hugging Face

      The GitHub of machine learning. Students navigate the model hub, test models in Spaces, deploy one through the Inference API and embed it in a simple application. Along the way: model cards, licensing, and the difference between a 7B and a 70B parameter model.

      Tools and platforms

      • Hugging Face
      • Spaces
      • Transformers
      • Gradio
      • Inference API

      Course materials

      • PDF
      • PPTX

    2. Module 2 of 5

      Agentic AI

      From single-turn prompts to multi-step autonomous systems. Students build an agent that reasons about a task, breaks it into subtasks, executes them in sequence and validates its own output, and learn when an agent should ask for human approval.

      Tools and platforms

      • Taskade
      • n8n
      • Claude API
      • LangChain
      • CrewAI

      Course materials

      • PDF
      • PPTX

    3. Module 3 of 5

      App Development

      AI-assisted coding, also called vibe coding. Students build a working prototype in v0, extend it in Lovable and see how Claude Code turns natural language into full-stack applications. Includes a live app challenge: teams have 90 minutes to go from idea to deployed prototype.

      This module’s deck on Skills and MCP runs below

      Tools and platforms

      • v0
      • Lovable
      • Bolt
      • Claude Code
      • Cursor
      • Replit
      • Vercel

      Course materials

      • PDF
      • PPTX
      • HTML

    4. Module 4 of 5

      Website Development

      From landing page to deployed web application without writing code by hand. Students use AI tools to generate, iterate and deploy websites, and answer the key question: when is no-code enough, and when do you need a developer?

      Tools and platforms

      • Vercel
      • Netlify
      • Gamma
      • Framer
      • Webflow

    5. Module 5 of 5

      Video & Voice Synthesis

      Text-to-speech, voice cloning, lip-sync avatars and automated video production. Students clone their own voice with ElevenLabs, create a talking-head video with HeyGen and build a complete video pipeline, the toolset for the closing film challenge.

      Tools and platforms

      • ElevenLabs
      • HeyGen
      • SadTalker
      • GPT Image
      • Gemini Video
      • LTX

      Course materials

      • PDF
      • PPTX

    Week 4 ends with

    An agentic workflow and a short AI film, made in teams

From the classroom

The deck on Skills and MCP from the App Development module in week 4, as it runs in class. The slides are in German.

Loading the deck

Taught in the room

  • Taught live and in person, in small cohorts, so everyone gets to speak
  • Live sessions with Q&A and feedback on your own cases
  • Real tasks from projects, discussed as we go
  • The material and slides I use in my own work
Weeks
4
Days
20
Modules
13
Decks
11