2026 #1 Evals & Agent Workflows

We’ve got another portion of AI talks for you, so come to our second Prague Gen AI Meetup of the year.

## NEW VENUE (very important)

Pracovna & Laskafe
Vlkova 628/36, 130 00 Praha 3-Žižkov

## Venue Schedule

• 18:30 Doors open
• 18:45 Talks start
• 20:45 Talks end
• 21:00 Snacks and beer

## What’s On The Agenda

• Talks: Again, no hype, just the stuff you want to know.
• Snacks and Beer: Grab a bite and a brew while talking shop.
• Networking: Meet other people in the field. No fluff, just good tech talk.

## Talks

### Šimon Podhajský (Head of AI @ Waypoint)

The Eval Flywheel: From "Works on My Laptop" to Systematic Quality
Most teams shipping GenAI products have no evaluation system. They have vibes, a few saved prompts, and hope. This talk doesn’t start with “build an eval suite”, it starts with observability: if you can’t see what’s happening in production, nothing else matters. From there, we build the eval flywheel, a practical pattern where production observability feeds error analysis, error analysis generates eval cases, and eval cases prevent recurrence. Your evaluation suite isn’t something you design upfront, it’s something that grows out of understanding your production failures.

### Ondřej Romancov (Engineering Lead @ Duvo.ai)

Building agents with agents
Duvo is building a platform for AI agents, and we’re running our engineering on agents too. Sharing practical tips and workflows we’ve found useful along the way.
Let’s get down to the real talk.