Notes from my AI practice: agentic coding, multi-agent architecture, mid-market use cases.
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 two months and 1,052 commits, I swapped the AI layer in my autonomous infrastructure system from OpenClaw to Hermes Agent by Nous Research. Why the learning loop made the difference.
OpenClaw Hackathon Vienna, House of Innovation, 150+ participants. What happens when four people build an AI-powered B2B Sales Agent in one night. An honest experience report.