design

Porting a tool's API ports its constraints. Design from the target environment's ideal, then reconcile against the source's primitives.

A clever optimisation that was a silent regression. The override flags survived out of habit. None of the reasons survived contact with the actual numbers.

Using cell biology naming not as metaphor but as engineering manual — how mTOR's biology predicted circuit breakers, autophagy, and negative feedback loops before we designed them.

When a dispatcher and an executor share a name, you don't have a naming problem. You have an architecture problem.

Naming as a design constraint: if a tool resists a name, the tool needs redesigning, not the name.

Repo boundaries enforce access control, not abstraction. Directories handle abstraction. If two things have the same visibility requirement, they belong in the same repo.

Every other component in the organism had a biological name. Agents didn't. Three failed attempts and a yeast cell later, they do.

Three components of a living system map cleanly to tool, skill, and agent. The biology isn't decoration -- it's the test.

The defining property of life is not metabolism or reproduction -- it's autopoiesis. A system that continuously produces and maintains itself. That's the north star.

Force every component to carry a biological name. Study the mechanism. The gap between biology and your system is the design insight.

A method for finding gaps in AI systems that architecture reviews miss. Force a naming constraint, and the breaks reveal what's missing.

Atoms have forces. Molecules have shape. Cells have organization. That's why cell biology is the design library.

Pick one biological level for all your naming. The constraint is the design exercise.

The LLM isn't dark matter. It isn't borrowed. It's a brain. The organism just needs to grow up.

The LLM isn't dark matter. Biology invented general-purpose reasoning. It's called a brain. We're just borrowing one.

Everything in my AI system maps to cell biology. Except the LLM. That's the point.

I tried to give LLMs a biological name. Every name broke. The failure was the finding.

Cells run thousands of simultaneous reactions without general-purpose reasoning. Shape is enough.

The tool/skill distinction isn't a property of the capability. It's a property of the context it operates in.

AI coding tools give you boxes to put things in. Biology suggests you should be thinking about how things flow instead.

Every biological name is a testable hypothesis about what your system should do.

Every skill you build is one of two things. Knowing which changes what you build next.

Biological metaphors in AI systems break at the autonomic-deliberate boundary. The fix isn't dropping biology — it's getting the neurology right.

How biological modelling determines system structure — not just naming, but what you build and what it can become.

Why the future of agentic trust depends on liquidating prompt-first reasoning for a metabolic core.

Design for the failure modes of your medium, not the capabilities. Then watch the rules dissolve themselves into programs.

On the metabolic necessity of pruning agentic context to survive the entropic heat death of the credit balance.

Why we should stop treating AI as a chatbot and start treating it as a metabolic organism governed by credit scarcity.

When epistemic trust runs dry, generative synthesis regresses into mechanical synchronization and eventual structural dissolution.

Tokens are energy. Text is mass. The context window is the budget. The rest is plumbing.