ai

Most advice about making CLIs agent-friendly is just good CLI design. Only four principles are actually agent-specific.

Smart model plans, cheap model builds. The pattern everyone's converging on for AI coding agents — and the piece nobody's shipped yet.

I turned the seven patterns into a zero-dependency Python library. Then I added MCP bridge support. Here's what I learned about the gap between patterns and code.

Three independent authors converged on nearly identical patterns for CLIs that AI agents invoke. Here's what they agree on, what's missing, and why nobody has built a framework for it yet.

Multi-engine search agreement is not primary-source verification. A cautionary tale about hallucinating reference content from consistent secondary summaries.

Willison says CLIs beat MCP. Cloudflare says server-side code mode beats both. They're both right, because they're answering different questions.

A day of reading skill repositories taught me less about the skills themselves than about how much I'd missed of the surrounding ecosystem.

We blamed the LLM for a 54% task failure rate. The real culprit was seven layers of dispatch infrastructure between intent and execution.

Compliance-first governance produces paperwork. Design-first governance produces systems you can actually explain to a regulator.

Engineering metaphors give you clean abstractions. Biology gives you resilient ones. Twenty design heuristics from four billion years of R&D.

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/agent distinction isn't just compression ratio — tools are instruments, skills compose them with judgment. Same thing only at the leaf.

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

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.

Everything is organism. AI is the latest intensification.

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.