Both camps in the AI-tooling debate are watching the wrong number. The cost lever you can actually control is the harness you run your models through.

A pattern for ingesting a continuous external stream in Go: a dumb, fast Kafka consumer that lands raw messages in Postgres, with per-partition fan-out, idempotent batched writes, and a landing table that never expires.

Headcode began as a way to learn UK rail data and how to use an LLM properly on something real. The product is a maybe; the research-to-PRD-to-tasks workflow I built alongside it, with review at every layer, is now how I work.

Headcode is a unified, developer-friendly JSON API that takes the fragmented, legacy feeds of the UK rail network and turns them into clean, enriched real-time data.

Introducing jjw, a small Go CLI for managing jj workspaces with bookmarks and lifecycle hooks, built to make parallel LLM coding agent workflows easier.

Why I built a reference Go project that doubles as a template an AI agent can clone, customise, and scaffold into a new service.

After losing a PostgreSQL database by blindly following AI-generated commands, I developed a structured approach to working with AI that separates generation from judgement

How CUE schemas eliminate type assertion boilerplate when handling multiple IoT sensor types in a home automation system

Build a production-ready MQTT client in Go with real examples from a Home Assistant smart home setup. Covers concurrent processing and device integration.

Go 1.25 introduces a new experimental JSON implementation that provides a improved encoding and decoding performance and more flexible approach to handling JSON data.