Can Your AI Agent Edit the Tests That Check It?

Building software has always been a sequence of jobs. Work out what it should do, write it, check that it works, release it. Hand each of those jobs to an…

Continue reading
Where Does Your Dark Factory Stop?

At FANUC's plant near Mount Fuji, robots build other robots for weeks at a time with nobody on the floor. The part worth copying is duller than the robots: every…

Continue reading
The Software Factory You Didn’t Notice You’d Built

Sensible automations, each gated on its own, add up to a production line no one designed. Every automated loop in your delivery pipeline was reviewed, gated and argued over before…

Continue reading
When the Loop Rewrites Its Own Prompt, What Are You Approving?

"The end of manual prompt engineering" is the headline on GEPA. That is true for the job it is being sold to do, but GEPA is doing something else as…

Continue reading
Why the Simplest AI Agent Loop Beats a Sophisticated One

An AI agent is only as trustworthy as the check on its work. The loop that runs it barely matters. If you follow AI engineering at all, you have probably…

Continue reading
Model Sovereignty: How Much of Your AI Do You Actually Control?

Within a day of two frontier models going dark, the advice was everywhere and it was all the same. Own your model. Self-host. Get off the single API before someone…

Continue reading
The Illusion of Perfect Recall: Your AI Doesn’t Remember. It Reconstructs.

Ask someone to describe a vivid memory from ten years ago and they will give you detail. The weather. What was said. How they felt. They are not lying. They…

Continue reading
More Than a Model: A Memory Architecture for an AI Coding Agent

The first file my coding agent reads, every session, is a markdown file called CLAUDE.md. It is not configuration. It is not a prompt. It is the working-memory layer of…

Continue reading
The Forgotten Layer: Memory Is the AI Variable Most Teams Are Missing

In 2023 a research paper called Lost in the Middle showed large language models lose accuracy as relevant information moves toward the middle of their context window. Two years on,…

Continue reading
AI Supply Chain Security Is a Provenance Problem, Not a Vetting Problem

In May last year, someone opened a public GitHub repository and filed an issue. The issue contained instructions written for the AI assistant the repository's owner had connected to their…

Continue reading