AI & LLM applications
Building, shipping, and evaluating LLM-powered applications. From prompt engineering to production-grade agent systems.
Šimon Podhajskýprague + london · est. 2012
Menu
Speaking.
I bring practical, experience-driven talks to conferences, meetups, and corporate events. 29 talks shipped to date — from AI Engineer Europe to dbt Coalesce to EuroPython. Whether your event is 30 people or 3,000.
What I talk about.
Evals & testing for AI
How to evaluate AI systems rigorously — synthetic data, automated testing, and continuous evaluation pipelines.
Data engineering
Modern data stacks, dbt, DuckDB, and bringing data engineering practices to small teams and startups.
Vibe coding
Running multiple AI coding agents in parallel; live demos of AI-first development workflows.
Python patterns
Pydantic, type safety, and practical Python patterns for the LLM era.
Your topic?
Tell me about your audience and theme; I'll craft a talk that fits.
talk to me ↗Catch me next.
Past engagements.
Hover any entry for the one-line version; fuller abstracts on the talk pages, where I have them. Featured talks are markedin flame.
2026Všechny evals frameworky jsou tak trošku na nic. Jak je přesto využít?Moderní stack #7 (Ostrava, CZ)AI jako zrcadlo, ne sluhaCERNA.AI Festival (Ostrava, CZ)Evaly v praxi: od narativu ke ground truthCERNA.AI Festival (Ostrava, CZ)Airplane mode for your second brainPKM × AI Meetup #1 (Prague, CZ)RAG a evalyAI Monday Jihlava #7 (Jihlava, CZ)Choose Your Ground Truth: A Field Guide to Synthetic Data for EvalsEvals.cz Meetup #3 (Prague, CZ)Financial modelling in OpenClaw & safely deploying itOpenClaw Demo Night (Prague, CZ)Cognitive Exhaust Fumes, or: Read-Only AI Is Underratedai.engineer/europe (Online)The Eval Flywheel: From "Works on My Laptop" to Systematic QualityGenAI Meetup (Prague, CZ)Evals, Benchmarks, and Guardrails: A Pythonista's Guide to Not Mixing Them UpPyData (Prague, CZ)When (& How) to Start Writing EvalsEvals.cz Meetup #1 (Prague, CZ)The European AI Builder's DilemmaAgent-Driven Meetup (Prague, Slevomat HQ)Simultaneous Vibe CodingTopMonks Caffé (Prague, Loft N8)2025Jak se učit s AIZvídavá nadílka 2025 (Prague, Kino Pilotů)What Makes Us Human?Data Day 2025 (Prague, CZ)Getting buy-in for data infrastructure setupdbt Coalesce (Las Vegas, NV, USA)Simultaneous Vibe CodingAI Bootcamp 2025 (Chocerady, CZ)Evals & Synthetic DataHacker Camp 2025 (Rožmitál pod Třemšínem, CZ)Pydantic, Everywhere, All at OnceEuroPython (Prague, CZ)Debate ConciergeAI Tinkerers (Prague, CZ)2024Multi-Agent FrameworksPyData Prague, Rapid7 offices, CZLLM & TDD? Maybe! (& AutoGen & DeepEval)pyvo Praha (Prague, CZ)2023Impromptu Talk at Data Mesh @ World Data Congress 2023World Data Congress 2023, Prague, CZWebinář: Umělá inteligence a její hrozbyPrague, CZ2022dbt and MDS in small-batch academic research: a working exampledbt Coalesce (New Orleans, LA, USA)Data Modeling as the First Data HireSTRV, Prague, CZNeuroscience to MDS, or: On Data As ExhaustSummer Community Days (Online)2017Data Curation WorkshopCharlottesville, VA, USASIPS Lightning TalkCharlottesville, VA, USA
Eval frameworks promise more rigor than they deliver. What they get right, where they mislead, and how to use them anyway.Sep 2026
A 12-minute keynote on the case for a personal AI that only reads: it sees more, breaks less, and gets along with GDPR.Sep 2026
A hands-on workshop with Veronika Kráľ: evals on one small real project, and the three ways we got the grading wrong.Sep 2026
Can a local model in a customized pi harness do what Claude Code does for my notes, offline? Enough for bounded work, not yet for an always-on observer.Sep 2026
Naive RAG is still a sensible default. This talk is about how to tell whether yours works.Jun 2026
Synthetic eval data mostly produces garbage on the first try. The techniques that work, chosen backwards from the eval you want.Jun 2026
Using OpenClaw to build a Bayesian buy-vs-rent model for Prague real estate, and how to deploy something like that without setting your money on fire.Apr 2026
Read-only AI: what an observer that never acts can tell you from your cognitive byproducts.Apr 2026
Most GenAI teams have vibes, saved prompts, and hope. Observability first, then a loop where production failures become eval cases.Feb 2026
Three things that sound alike and map to different Python patterns. Pytest can work for evals; guardrails aren't tests at all.Feb 2026
LLMs have an infinite failure surface, so test-first doesn't work. Deploy, observe, then write evals for what actually broke.Feb 2026
A response to the Agent-Driven Manifesto: Europe's AI values need a strategy, and refusing to build protects nobody.Jan 2026
The parallel coding-agents workflow, demoed live.Jan 2026
How to learn with AI, for high-school students.Dec 2025
Closing panel with Kateřina Lesch and Daria Hvížďalová.Nov 2025
Introducing dbt so it sticks: the right entry point, the right first features, and a rollout the org is ready for.Oct 2025
Running several coding agents at once, and keeping track of what each is doing.Sep 2025
Evals, and how to make synthetic data for them.Aug 2025
Pydantic in every layer of the stack, and the pitfalls each one hides.Jul 2025
Demo of a PydanticAI agent that writes debate cases.Feb 2025
LangGraph and AutoGen, head to head.Nov 2024
Test-driven development with LLMs in the loop, via AutoGen and DeepEval.Apr 2024
How did I come to find myself on a stage, talking about data? How does anything ever happen, really?
Mar 2023
Webinář pro středoškolské debatéry o AI a jejích hrozbách.Jan 2023
dbt, DuckDB, and Meltano/Dagster, run on academic-scale data.Oct 2022
What I wish I'd known as a company's first data hire. (dbt helps.)Sep 2022
How I got from neuroscience to the modern data stack, and what carried over.Jul 2022
A half-day workshop on curating research data at SIPS 2017.Aug 2017
Five minutes on PsychTaskFramework at SIPS 2017.Aug 2017
Make your event unforgettable.Get in touch ↗