A bigger context window gave me a worse answer, repeatably
What you leave out of a context pack is a design decision, not waste.
llm
5 posts
The context window is not your constraint — what you put in it is
Scoping a shared instruction bundle saved 8.2% per worker, against 40% guessed. Why residency beats capacity, and the surface that was never loaded at all.
The prompt is not the artifact — the runtime is
A behaviour defect belongs in the command's runtime file, not in better instructions next time. What to edit, how to lock it, and where that stops working.
Stop parsing your AI's prose. Make it return a schema you can assert on.
Schema-forced returns move validation to the tool call, so the model retries instead of the caller parsing. What that buys, and the field that lied in the right format.
100 technical posts, and the gates that stopped them being slop
Publishing at volume with an AI agent is easy. Publishing at volume without shipping slop needs machinery that refuses, and refuses loudly.