26 Jan, 2026Agent-Driven Meetup (Prague, Slevomat HQ)event ↗

The European AI Builder's Dilemma

The Agent-Driven Manifesto argues Europe should lead AI by philosophical depth rather than raw speed. I want that to be true. Then come the numbers: 3 notable European models in 2024 against 40 American ones, roughly 6% of global private AI investment, and 60% of European small tech companies reporting regulation-driven product delays versus 44% in the US. A response talk, given from inside the tension of building AI products on US venture capital from Prague, arguing that the manifesto prescribes values without a strategy and that refusing to build something harmful protects nobody when someone else ships it anyway. It closes on the question I'd rather be discussing, which is what a realistic European AI company looks like in 2028.

Open slides ↗

SlidesThe European AI Builder's Dilemma

"RAG is dead" is the take in every other thread in 2026 — and it's wrong: naive retrieval-augmented generation is still a sensible default, beaten only in some cases, and measurement is the only way to know if you're one of them. This talk walks the retrieval pipeline end to end, then turns to the part that matters — telling whether your RAG actually works, with ground truth, retrieval metrics, RAGAS, LLM-as-judge, and error analysis feeding an eval flywheel.view ↗

Choose Your Ground Truth: A Field Guide to Synthetic Data for EvalsEvals.cz Meetup #3 (Prague, CZ)

You need an eval set but don't have a hundred real production failures to build it from, so you reach for synthetic data — and most first attempts quietly produce garbage. A field guide to the techniques that actually work, from real-incident seeds to personas to RAG-grounded generation, with one throughline: synthetic data needs its own eval, so choose your technique backwards from the eval you want.view ↗

Financial modelling in OpenClaw & safely deploying itOpenClaw Demo Night (Prague, CZ)

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.view ↗

Cognitive Exhaust Fumes: What Read-Only AI Sees That You Can'tai.engineer/europe (Online)

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.view ↗

¶Want this talk for your audience?Invite me to speak ↗