​More details on the location: Workin - Senatorska 2, Entrance B, 1st floor.

​

​AI demos are everywhere.

​But how do companies actually build AI products that work reliably with live data, low latency, and thousands of users?

​Join engineers as they share the architectures behind production AI systems - from streaming data and event-driven architectures to real-time databases, RAG pipelines, observability, and open-source infrastructure.

​No hype. Just practical engineering stories, lessons learned, and opportunities to meet others building modern data systems.

​Food and drinks included 🍻

​

​PS. Want to hear more great speakers? Sign up for the Open Source Analytics and AI Conference on Nov 2 (online and in-person). Register here.

​

​Agenda

• ​6 pm - Networking

• ​6:15 - 8:00 pm - Talks

• ​8:00 - 9:00 pm - Networking

​Speakers

• ​Robert Hodges, CEO @ Altinity

• ​Michał Ćwiok and Aleksander Bydłowski

• ​Michael Matloka, Member of Product Engineering Staff @ viktor.com

​Description of talks

​Tools and Tricks to Prepare Your ClickHouse® for AI

​Speaker: Robert Hodges, CEO @ Altinity

​Abstract: AI is coming! It's going to crush your ClickHouse database!!  Well maybe. This talk will cut through the FUD, focusing on three ground-level issues that are emerging across a wide range of installations.

​First, build sandboxes to protect data if (when) your agents go rogue. Second, lower costs of operating ClickHouse to free up resources for AI. Third, use AI models to diagnose problems and guide application improvements. We're working on all three at Altinity and will share lessons on solving them.

​Building AI Under Uncertainty: A 300-User Enterprise System

​Speakers: Michał Ćwiok and Aleksander Bydłowski

​Abstract: It is difficult to predict outcomes when the system, messy data and people start interacting. Sometimes the best way to find out is to deploy fast at a meaningful scale.

​This talk is about how we made that practical - grounded in a real, client-anonymized enterprise project for enhancing documentation audits with AI.

​Our open-source Odyss AI Flows framework, serverless Azure architecture and AI-assisted development are all parts of how we work this way.

​We’ll take a fast, down-to-earth tour through the things we found most interesting along the way — from expressing AI logic and scaling workloads to UI, costs, and the less tidy parts in between.

​

​Logs finally considered useful

​Speaker: Michael Matloka, Member of Product Engineering Staff @ viktor.com

​Abstract: We’ve been collecting more logs than we have time to investigate. Now agents can do that legwork. Here's how we roll with this at Viktor.

​I’ll cover three things your God agent needs: detailed records, all the company context plus a computer, and infra that solves work rather than creates more.

​We’ll follow a real investigation, and discuss when self-hosting saves you money but costs days.

​​Follow the OSA Community

​Make OSA COM your community.

​Website: www.osacom.io

​LinkedIn: /osa-con

​Slack: https://go.osacom.io/slack