Read & reflect
Blog
Stories, lessons, and quiet reflections from the journey. Every article here is my own — not copied or republished from anywhere else.
Latest
Jev: when your agent doesn't need an LLM for every decision
My little agent called a model eleven times just to guess which emails were urgent. TypeSafe AI's Jev does not write prose — it returns probabilities for typed questions. Here is where I would wire it into a harness, and where I would still leave the LLM alone.
·6 min read
Read moreMore posts
GitHub repos that actually help with AI coding: tokens and productivity
Caveman, Karpathy skills, Addy Osmani's Agent Skills, and a few others — mapped to real jobs: talk less, code leaner, load skills on demand.
·14 min read
Building a side project with AI agents: what's fast, what's slow
Honest notes from building mylittleworld.dev: scaffolding is fast; polish, ownership, and production still take time — told like a café conversation.
·8 min read
Release checklist when you don't have a dedicated QA team
For founders, solo devs, and teams of 3–5: before/after deploy checklist and rollback criteria. If you already have QA, they usually own and extend this list.
·7 min read