A category has grown up selling businesses a way to get cited by AI, and most of what it sells does not survive a test. What holds up is server-render...

An instruction for an agent used to have four homes and all four leak. A skill file costs one line until the work matches its description, then it loa...

An agent writes most of the code here and no second engineer reads it before it ships, so a standard that depends on someone noticing does not survive...

On a codebase an agent writes and nobody else reviews, the lint gate is the code review. For nine months it was green, running a preset with the rules...

Giant Context is a marketing platform where the intelligence is the operator. A model reads what a business is, works out what its marketing is missin...

Ten days of frontend performance work on the public site, including the four hypotheses that turned out to be wrong. Images were served raw because a ...

The Go port of the TypeScript compiler promises full builds eight to twelve times faster. Whether a codebase can adopt it before the release settles d...

I price Giant Context at $25 per million tokens and had no defensible answer to what it costs to serve a thousand customers. Four of the five cost cla...

The test cache made the suite fast by replaying old results instead of running the tests. Deleting it was correct and it made everything slower. Then ...

The API doubles as tools an agent can call, opt in per route from the same description that generates the SDK. I tested it like an API and everything ...