Long-form writing

Field Notes.

Where the thinking happens in paragraphs instead of products. Long-form essays on cognitive engineering, the Garden framework, and the lineage of Gardeners — plus the serialized chapters of the Cognitive Engineering treatise as they ship.

Under construction

The first chapter is being written.

Chapter I of the Cognitive Engineering treatise — “Prompts are software, and here's why that matters” — is the inaugural long-form piece for this section. It will ship here first and serialize outward from there. Check back or see what I'm working on right now for updates.

The planned structure

Cognitive Engineering — a field manual

I

The thesis

Prompts are software. Why that framing unlocks everything that follows, and why the current state of "prompt engineering" is closer to superstition than to engineering.

II

What cognition actually is in an LLM

Tokens, attention, RLHF, modes of failure. What the substrate you're engineering on top of actually is, mechanistically, so you can design for its real properties.

III

The four primitives

Prompt, brain, blueprint, circuit — abstracted from Brainboot's branding. The taxonomy of composable cognitive work, and why each tier exists.

IV

Typed I/O for cognition

Why putting Zod schemas on the edges of a brain changes its failure shape. How type contracts make cognition testable in the way functions are testable.

V

Invariants as the unit of engineering

Every brain has properties that must hold. Building them in as enforced runtime checks instead of hoping for them is the difference between software and wishful thinking.

VI

Composition

Why a brain graph is not just a chained prompt. How to design sub-brain handoffs, budget propagation, and error surfaces across compositions.

VII

Cost as a design input

The model cascade, prompt caching, batch economics. Why the pricing decision comes before the architecture decision, not after.

VIII

Test harnesses for probabilistic systems

How to test a function whose output is non-deterministic but whose properties are not. The role of property-based tests in the cognitive engineering stack.

IX

The garden principle

Why every commercial AI product must grow its user, and how that rule makes itself visible in the architecture when you honor it.

X

What is still hard

Open research. Honest limits. Where the framework runs out of traction and what would have to change upstream in the model layer for it to stop running out.

XI

What this replaces

The honest comparison to agents, LangChain, prompt marketplaces, and every other existing thing the framework relates to. What this is, what it isn't, what it subsumes, what it doesn't.

XII

Where this is going

The 3-year vision. The creator economy for brain authors, the Brainboot Index, and the question of what happens to software engineering when a non-trivial fraction of it is cognitive engineering.