I bring practical, experience-driven talks to conferences, meetups, and corporate events. My presentations blend live demos, real-world case studies, and actionable takeaways — and I tailor every talk to the audience.
I have spoken at EuroPython, dbt Coalesce, PyData, and many more. Whether your event is 30 people or 3,000, let's make it memorable.
I can tailor any of these to your audience, from introductory to advanced.
Building, shipping, and evaluating LLM-powered applications. From prompt engineering to production-grade agent systems.
How to evaluate AI systems rigorously — synthetic data, automated testing, and continuous evaluation pipelines.
Modern data stacks, dbt, DuckDB, and bringing data engineering practices to small teams and startups.
Running multiple AI coding agents in parallel, live demos of AI-first development workflows.
Pydantic, type safety, and practical Python patterns for the LLM era.
Catch me at one of these events.
CERNA.AI (Ostrava, Czech Republic)
Dobrodata (Czech Republic)
A selection of recent and notable presentations.
What happens when AI systems passively observe information without modifying it? Exploring the patterns and insights that read-only AI reveals — the cognitive byproducts humans overlook.
A presentation on the use of Pydantic in a variety of contexts, and how to avoid its pitfalls.
A showdown of LangGraph and AutoGen, two Python-based multi-agent frameworks.
Some of my latest talks and presentations.
| Date | Title | Event |
|---|---|---|
| 17 Feb 2026 | The Eval Flywheel: From "Works on My Laptop" to Systematic Quality | GenAI Meetup (Prague, Czech Republic) |
| 11 Feb 2026 | Evals, Benchmarks, and Guardrails: A Pythonista's Guide to Not Mixing Them Up | PyData (Prague, Czech Republic) |
| 03 Feb 2026 | When (& How) to Start Writing Evals | Evals.cz Meetup #1 (Prague, Czech Republic) |
| 20 Jan 2026 | Simultaneous Vibe Coding | TopMonks Caffé (Prague, Loft N8) |
Tell me about your audience, the theme, and the format — and I'll craft a talk that fits perfectly.