Tag: Agents

This site already talked to agents through A2A and JSON-LD. But an agent that simply fetches a post still downloaded 158 KB of HTML to read 17 KB of writing. So I added Cloudflare's convention, markdown on request, made it run on Vercel and Cloudflare from one set of rules, and found three traps on the way that no local test caught.

At my day job, I was asked to be more efficient with AI spend. The honest answer was a semantic router in front of every model, so I pointed my own coding agent at one. It broke. Five bugs later, the fixes are upstream, which means everybody gets them.

I wanted one place to decide which model answers and how hard it thinks. That surfaced a bug one event from the end of every stream. I fixed the wrong thing first, the schema proved the router right, and the real fix is now upstream in vLLM.

A laptop, a single GH200, and a semantic router between them, built to answer trivial requests locally and send the hard ones to the big card. Along the way, eleven things in that stack told me a confident falsehood. Not one of them was the model, and three of them were my own measurements.