Budapest | Claude Code for Everyone
Join us for the next Claude Community Budapest Meetup, hosted by Tamas, Attila, Balazs, and Jamie.
Whether you’re already integrating Claude Code, Cowork into your daily workflow, curious about agentic coding, or simply looking to connect with others exploring AI-powered development, this event is for you.
Who Should Attend?
This meetup is open to everyone, regardless of experience level—just be curious:
Founders & Operators: Learn how to scale efficiently and move faster.
Business Professionals: Discover how to delegate repetitive tasks to AI agents.
Engineers & PMs: See firsthand how Claude can significantly reduce development cycles.
The AI-Curious: Transition from theory to practice with hands-on insights rather than just another lecture.
Agenda
05:30 PM: Doors open. Registration, Networking & Drinks
06:00 PM: Welcome Remarks
06:15 PM: György Márk Varga is Product Developer at Shiwaforce.com Inc.
Claude Managed Agents: A Build-on-Myself Walkthrough at Shiwaforce
At Shiwaforce I work on figuring out where AI actually fits in the day-to-day of a real workplace - beyond the demos and the hype, into the actual flow of getting things done.
The hardest question I keep coming back to is the simplest one: where does an agent belong in a real knowledge worker's day?
So I built one for myself. Not as a reference architecture - as the fastest way I could think of to learn the Managed Agents primitives end-to-end on real work, on tools I actually use.
Live demo from cold start to a working agent. The talk is for anyone past "let's try Claude" and asking "let's actually ship this": where Managed Agents earns its keep, what the primitives are good for, and which parts of this pattern would change before any of it went near a real deployment.
06:50 PM: Demet Dagdelen is VP of Growth × AI at Automattic
Demet Dagdelen is VP of Growth × AI at Automattic (WordPress.com, WooCommerce, Tumblr — ~1,500-person fully remote). 15 years in data science, experimentation, and ML engineering.
She built Automattic's ML platform (scoring 50M+ users weekly) and GeoX, a geo-experimentation framework that exposed $35M in wasted ad spend and paused WordPress.com's paid media for two years. She then rebooted that paid media and built end-to-end funnel optimization across ads, landing pages, signup, and lifecycle. In parallel, her ML Sales program — a causal-ML lifecycle system autonomous since 2021 — drives ~25% of new subscription revenue.
Now she's leading a cross-functional team of software engineers, data scientists, and marketers and building AI-first growth systems: an in-house email platform built for 500M+ monthly sends and Agentic CRO for WordPress.com. She contributed chapters to [Shaping AI Without the Hype](https://shapingaiwithoutthehype.com/) and blogs at [demet.blog](https://demet.blog). Based in Budapest & occasionally NYC.
## Two Faces of Production AI: Tools and Systems
AI-first marketing systems have two faces:
**Face one** is genuinely one-shottable wrapper-magic. Paste a landing page, get a full marketing playbook in ninety seconds — no knowledge base, no plumbing, no foundations. The result is surprisingly close to work that normally takes months and six-figure research budgets. That face is real, and it's changing what marketing teams can explore in an afternoon.
**Face two** is different. When AI acts on your data and your users, the model is the last five percent of the build. The other ninety-five percent — attribute catalogs, validated schemas, layered validation — is plumbing that AI now forces you to do right, because unlike every wave before it, AI punishes sloppy foundations in production.
I'll demo both faces: an AI ICP Strategist that one-shots a tactical playbook for marketing, and our production AI audience builder for our email platform — system prompt, JSON schema, validator, gotchas, data governance effort, and the timeline. Then where we're going — and the foundations we're building right now to get there: Agentic CRO, i.e. paid media, landing pages, and lifecycle flows that update themselves.
The argument: not everything needs foundations, some work is genuinely solved by AI. But for the things that do, AI forces you to get them right.
07:25 PM: Online fireside chat with Eduard Ruzga is CEO & Co-Founder at Desktop Commander , that is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities.
Eduard Ruzga is the Founder and CEO of Desktop Commander, the operating system for AI-driven workflows. A former Staff Engineer at Prezi and Infogram, Eduard bridges the gap between deep tech engineering and rapid, user-centric product iteration. He is an AI youtube content creator and writer focused on building local execution layers that empower professionals to go from words to actions, collapsing the gap between AI chat and computer control.
Important Information
Registration: Claude Code Community reserves the right to approve or reject any registration. Please ensure your information is accurate, as incomplete or fake profiles will be declined.
Capacity: To ensure everyone's safety, we reserve the right to deny entry at the door if the venue reaches its maximum capacity.
Thank you and feel free to contact me, my DMs are always open!
tamas