Notes from my AI practice: agentic coding, multi-agent architecture, mid-market use cases.
waff Future Fit Festival, web3 hub vienna and the Vienna Software Architecture Meetup: three appearances back to back. Why I get on stages because I build, not the other way around.
A Whisper default cost me 13 minutes of transcript on my first real end-to-end run – replaced by a hallucination loop. The diagnosis, the fix, and four transferable lessons.
The bottleneck in AI-assisted development has moved from writing code to judging it. Why verification is the skill that matters now – from daily practice, not theory.
Qwen3.6-35B on an M4 Pro 24 GB: technically loaded, 100% GPU – and yet 0.1 tokens per second. An honest diagnosis, five lessons, and hardware recommendations for others.
After 3,000+ sessions with Claude Code: What systems prevent AI agents from drifting in long-running projects. CLAUDE.md, Rules, Session Handovers and Quality Gates.
What happens when you build over 100 AI prototypes? An honest account of the gap between prototype and product – and what 3,000+ development sessions reveal.