Join us for the third gathering of the AWS User Group Brno! 🚀
This time, we are meeting at Clubco, where you can look forward to a relaxed summer atmosphere, an open-air BBQ, cold draft beer, and a couple of great technical talks! 🍔🍺
### 🎤 Agenda & Talks
1️⃣ Amazon S3 Vectors 👤 Speaker: Tomáš Sezima — Head of Data Engineering at Datamole
Come hear about Amazon S3 Vectors, AWS's purpose-built serverless vector storage. It brings approximate nearest-neighbor search with metadata filtering directly into S3, scales to 2 billion vectors per index, and follows S3's pay-per-use model: no cluster to size, no idle cost.
We'll walk through the resource model, query semantics, and real pricing math, plus a live demo, so you leave knowing exactly when S3 Vectors beats a dedicated vector database and when it doesn't. If you're building RAG or semantic search on AWS, this changes the cost equation.
2️⃣ MyStep Functions DAG Was a Lie: Going Agentic on 8,000 Photos 👤 Speaker: Dmytro (Dima) Hlotenko — Sr. Cloud Ops Engineer at Sage
Once I decided to translate my photography experience into a serverless pipeline. I judged 8,000 photos of your faces, and it was a big success – we turned a problem into a solution with AWS. Lambdas, Rekognition, Bedrock, and the rest played together as a system, delivering a memorable AWS Community Day.
The talk traveled far – but it had a fatal weakness. It was good while it lived in the conference room. Outside, my taste – hardcoded into weights and thresholds, and a single Claude call guessing how to process every file – brought things to disaster. It ran rules I wrote for photographs I hadn't taken yet, and failed silently on every shot that didn't fit. Terraform destroy.
Vérité: This year I tore out every guess. With agents.
Imagine swapping the single photographer for the press agency. I'll show how to keep a mature orchestration relevant in the agentic era. How a chain of pipelines became a grid of agents – separate programs, each with its own tooling and skills distilled from real photography craft. Where the agent reasons about what belongs and judges against real craft, not one engineer's gut. Where v1 had a frozen rule, v2 has a program that thinks.
I'll draw the parallels – where we broke through, where classic approaches still win, which weaknesses got replaced, and what each agent does instead. You'll leave with a pattern for any rigid pipeline: which box is a guess, and what if it could reason instead?
Last year I automated my hands. This year, my judgment.
✨ More information coming soon!
🤝 Get Involved: If you are interested in becoming a speaker or helping with the organization of future meetups, please let us know at jan.bleha@datamole.cz.
