✎ PROWRIT the lab
THE LAB

Field notes on making AI actually work

The interesting problem of this decade isn't making models smarter — the labs are handling that. It's the layer between human intent and model capability: context, memory, prompts as contracts, verification, orchestration. That layer is where outcomes are decided, and it is nowhere near solved. This is where we publish what we learn while building in it.

positions taken · claims sourced · counted in tokens, not vibes · wrong in public when wrong

FIELD NOTE 01

The model is not the product

The application layer — not the model — decides what people actually get from AI. On what a harness owes the model, what it owes the human, and why the iteration loop is the real interface.

2026-07-11 · 8 min · read →
FIELD NOTE 02

The burden of proof is on splitting

Multi-agent systems look like org charts and cost like them — about 15× in tokens, plus coupling. Why one excellent prompt is the right default, and the one split that is almost always worth paying for.

2026-07-11 · 8 min · read →
FIELD NOTE 03

The training shows through

How a language model is actually made — pretraining, tuning, and the side effects installed along the way — and why every prompt practice that works is a patch for a specific scar in that process. With the full ledger, traced.

2026-07-21 · 9 min · read →
FIELD NOTE 04

The rules file that made things worse

Two 2026 studies measured the same instruction file and disagreed — one found agents 28.6% faster with it, the other that generated ones cost 23% more and slightly reduced success. The experiment that reconciles them, and the line-by-line test it gives you.

2026-07-26 · 8 min · read →
FIELD NOTE 05

Your check is already an eval

A 13B model with custom rubrics matches GPT-4 at judging; agreement with humans swings from 0.17 to 0.86 depending only on how specifically you asked. The judge is a commodity — the rubric is the asset, and you probably wrote one already.

2026-07-26 · 7 min · read →
In the notebook, not yet written up: assumptions as the interface (requirements-gathering without the interrogation) · fresh-context verification (why models grade their own homework kindly) · skill files (killing domain ambiguity with conventions, not steps) · context budgets (what to put in the prompt, what to leave on disk).