Notes on building AI that ships.
Short essays — evals, agent architecture, no-code's ceiling, and what's actually working in production.
- 12 Apr 20264 min↗
Evals before features
An agent without evals is a liability. Here's the smallest possible eval harness I ship before letting any LLM touch a customer.
- 28 Feb 20263 min↗
The boring half of agents
Everyone wants to talk about reasoning loops. Almost nobody wants to talk about retries, idempotency, and the queue that quietly carries the whole system.
- 15 Jan 20265 min↗
No-code is a superpower (until it isn't)
n8n and Make let me ship a working ops backbone in days. Here's where I draw the line between glue code and real code.