Why AI and LLMs shouldn’t actually work and why they do anyway
BAYOOTEC CTO David Ondracek shows in the webinar on 20.05.26 how Large Language Models, Retrieval Augmented Generation, GraphRAG and autonomous agents really work. Step by step, without buzzword bingo, with clear explanations and concrete practical examples.
Teile diesen Beitrag:
Teilen Sie diesen Beitrag:
From tokens to RAGs and autonomous agents: How large language models really work
Large Language Models do not understand meaning. They know no truth. They statistically predict the next word. Nevertheless, they write texts, program complete apps, answer questions and solve complex tasks. How does that fit together?
In diesem Webinar zeigt David Ondracek, CTO bei BAYOOTEC, wie moderne KI Systeme unter der Haube funktionieren. Schritt für Schritt geht es durch die zentralen Bausteine: Tokens, Embeddings, Transformer, Retrieval Augmented Generation, GraphRAG und schließlich autonome Agenten.
Comprehensible examples are used to illustrate how pure statistics can be turned into powerful tools, where the limits lie and where their use in everyday working life is really worthwhile.
The webinar is aimed at anyone who not only wants to use AI, but also wants to understand it. Without buzzword bingo, but with clear explanations and concrete practical examples.
What participants will take away from the webinar
- A clear understanding of how LLMs actually work, with no prior knowledge of mathematics required
- A guide through the jungle of terminology: tokens, embeddings, RAG, GraphRAG, agents—all clearly organized
- The ability to distinguish AI hype from real value
- Concrete ideas for how AI can be meaningfully applied in your own daily work
- An overview of regulatory frameworks such as the EU AI Act, which helps inform project decisions
About the speaker David Ondracek
As CTO of BAYOOTEC GmbH, David Ondracek is responsible for the company’s technological direction and, in particular, drives the use of AI in software and business processes. His current focus is on the development and implementation of sustainable AI strategies.
For years, he has been intensively engaged with large language models, retrieval-augmented generation, and agent-based systems, and has overseen numerous AI projects from the initial feasibility study through to production. As a certified AI compliance officer (TÜV), David combines technical expertise with a clear understanding of regulatory frameworks such as the EU AI Act, risk classes, and compliance requirements.
How We Develop Secure AI Solutions for Businesses
Artificial intelligence only realizes its full value when it is technically sound, regulatory-compliant, and tailored to the specific use case. At BAYOOTEC, we combine deep engineering expertise with a clear understanding of the EU AI Act, risk classes, and compliance requirements—from the initial feasibility study through RAG and GraphRAG to agent-based systems in production.
Inquire Now
Would you like to implement an AI project, book David as a speaker, or do you have general questions about custom software engineering? We’d be happy to assist you and look forward to hearing from you.
