This post describes how we designed the Automattic / WordPress.com AI Agent "Framework", how it’s running (in PHP!), and what trade‑offs we made along the way.

seen from Sri Lanka
seen from Denmark

seen from United States
seen from China

seen from United States

seen from Germany
seen from Spain
seen from Saudi Arabia

seen from China
seen from Russia

seen from United States
seen from Tajikistan
seen from Lebanon

seen from Singapore

seen from United States
seen from Singapore
seen from Bulgaria
seen from United States

seen from Singapore

seen from Singapore
This post describes how we designed the Automattic / WordPress.com AI Agent "Framework", how it’s running (in PHP!), and what trade‑offs we made along the way.
Observability Practices in AI Engineering: A Complete Guide to LLM Monitoring
Here’s a truth that took me six months to learn the hard way: traditional observability doesn’t work for AI applications. You can have perfect uptime, sub-100ms latency, and zero errors—and your AI product can still be completely broken. Why? Because LLMs fail differently. They don’t throw errors; they confidently hallucinate. They don’t crash; they drift. They don’t timeout; they slowly become…