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 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.
- 02 Google AI Search Is Replacing the Map
AI search is changing the contract of discovery from finding sources to receiving answers, and that changes what content is worth building.
- 03 AI Graphics Need Systems, Not Vibes
Image models are useful raw-material generators, but consistent graphics come from arguments, layout systems, deterministic rendering, and taste.
- 04 The Approval Layer Is the Product
AI automation only becomes useful when human review, permissions, correction, and auditability are designed into the workflow from the beginning.