Practical AI systems for work that needs judgment.
About
I build the internal tools and automation companies run on, where AI meets the work teams actually do day to day.
My background runs from marketing operations and data analysis into AI engineering. I've built custom applications and data workflows in industry, and today I lead AI and marketing automation at Wrike as a Senior Project Manager. Most of the work is less about the model and more about everything around it: scoping the right tool with the people who'll use it, planning what to build, and managing the stakeholders who have to trust the result.
I write here about what holds up once a system meets the people who use it: the approval layers, the edge cases, and the unglamorous plumbing that decides whether AI work survives contact with the demo.
- Role
- Senior Project Manager, AI & Marketing Automation at Wrike
- Focus
- Internal tool development · AI automation · marketing operations
- Based
- Prague, Czechia
- Studied
- MSc Information Management, Aarhus University (BSS)
Writing
- 01 On-device AI Models with a Harness
Chrome's on-device Prompt API can power serve as a good LLM for small tasks. How does it do with tools?
- 02 LimitBar: A macOS Menu Bar for AI Usage Limits
LimitBar turns Claude, Codex, Gemini, and OpenRouter limits into glanceable battery icons, reset alerts, and live token activity.
- 03 FamilyClaw: An AI Agent for the Boring Parts of Family Life
A Budapest weekend test showed where a family AI agent earns its keep: research, trade-offs, follow-ups, and calendar coordination.
- 04 Personal AI Assistants Are Worth the Setup
The hard part is not the model. It is identity, memory, permissions, tools, and a workspace where the assistant's work stays visible.