$500 Fullstack Live Event Free With a Membership!
Welcome to the Workshop of Intelligence, the live event where code transforms into reasoning.
Dive deep into the world of Large Language Models (LLMs) and AI Agents, and discover how these technologies truly work beyond the hype. You’ll learn the real mechanics behind modern AI, from tokenization and attention heads to cutting-edge deep learning models, and how to put this knowledge into action for your own projects.
This live experience bridges theory and hands-on insight, helping you make AI tangible, understandable, and applicable.
In three hands-on sessions, you’ll learn how to deconstruct LLMs, understand how they operate, and identify both their strengths and limitations.
Explore alternative AI architectures beyond standard LLMs and learn how to build AI Agents from scratch, no frameworks, just code.
Step by step, you’ll implement memory, context management, tool use, and simple reasoning loops, while avoiding common pitfalls.
By the end of the workshop, you’ll have the practical skills to deploy AI systems and build your own intelligent agents for real-world tasks.
The hype around LLMs is unstoppable — and for good reason. But not every problem should be solved with an LLM, even a multimodal one.
In this session, Christoph explores other powerful and fascinating models beyond the mainstream LLM landscape. You’ll look at recent technical breakthroughs, research papers, and innovative architectures that could be exactly what your next project needs.
Expand your horizon and discover what’s really happening across the wider machine learning and deep learning ecosystem.
AI has been around for decades — we’ve had text-to-speech, speech-to-text, and facial recognition for years. But the true revolution started only recently, with the arrival of Generative Pretrained Transformers — GPT and its open-source relatives.
In this session, John takes you inside the anatomy of an LLM. You’ll explore how models like Phi 3.5, Qwen 2.5, Llama 3.2, and Mistral work under the hood.
Understand vocabulary, tokenization, embeddings, attention heads, quantization, and performance — all demonstrated locally with live code.
If you can, install Ollama and download one or more of these models beforehand to follow along.
Simple code, fascinating results — and a new understanding of what LLMs can (and can’t) do.
This is your hands-on guide to building AI Agents from scratch, using only Python and an LLM API.
Starting from a simple API call, you’ll progressively add:
Prompt engineering for consistent responses
Memory and context management
Tool usage and function calling
Error handling and retry logic
Basic reasoning loops
Along the way, you’ll learn to avoid common pitfalls — from context window limitations and tool hallucinations to infinite loops and error cascades.
Each step is backed by real, working code examples.
By the end, you’ll fully understand the core components of AI Agents and know how to build your own — no frameworks, no abstractions, just code.
how Large Language Models actually work, from tokenization to attention heads.
which new deep learning models go beyond LLMs and why they matter.
how to build AI Agents step by step, using nothing but code.
how to avoid common issues like context loss, hallucinations, and error loops.
Data Scientists exploring practical AI and deep learning applications for real-world projects.
Software Developers curious about generative AI and ready to turn hype into working solutions.
Christoph Henkelmann
Expert in Deep Learning, Transformer Models, enterprise AI applications, and strategic AI consulting.
John Davies
Expert in Software Architecture, Java Development, FinTech systems, and AI startup innovation.
Paul Dubs
Expert in Machine Learning, Natural Language Processing, and the development of large-scale AI Agents.