Posts about ai
-
I Built 200 CLIs for My AI. Here's What Actually Matters.
A Chinese article argues CLI is becoming the AI plugin format. I've been living this for months with 442 tools. The article is right about CLI. It's wrong about what makes CLI work.
-
Same Trigger, One Skill
A simple rule for keeping AI agent skill systems coherent: if two skills fire on the same trigger, merge them. Different trigger, different skill. No exceptions.
-
Overnight Autonomous AI Coding: What Actually Works
I left an AI coding pipeline running overnight with 21 monitoring cycles. 5 features merged, 10 specs dispatched, 3 root causes found. Here's what worked, what broke, and the quality of the output.
-
The One Env Var That Cost a Day
ANTHROPIC_API_KEY vs ANTHROPIC_AUTH_TOKEN — how a single wrong environment variable made an AI coding pipeline silently fail for hours, and the debugging journey that found it.
-
What Anthropic's Managed Agents validates — and what to steal
Anthropic shipped a hosted agent platform. Its architecture looks familiar. Here's what a solo builder can learn from how they decoupled the brain from the hands.
-
What LLM Wiki Looks Like After Six Months
Karpathy's LLM Wiki pattern is a good starting point. Here's what changes when you run it for real — enforcement over convention, decay over growth, and knowledge that fires without being asked.
-
4 Principles for Agent-Facing CLI Design
Most advice about making CLIs agent-friendly is just good CLI design. Only four principles are actually agent-specific.
-
The architect-implementer split: why your expensive model shouldn't write code
Smart model plans, cheap model builds. The pattern everyone's converging on for AI coding agents — and the piece nobody's shipped yet.
-
Building porin: a library for agent-facing CLIs
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.
-
Seven patterns for agent-facing CLIs
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.
-
The primary-source tax
Multi-engine search agreement is not primary-source verification. A cautionary tale about hallucinating reference content from consistent secondary summaries.
-
CLI, MCP, or code mode: the answer depends on who's running the sandbox
Willison says CLIs beat MCP. Cloudflare says server-side code mode beats both. They're both right, because they're answering different questions.
-
Ten Things I Learned From the Agent Skills Gold Rush
A day of reading skill repositories taught me less about the skills themselves than about how much I'd missed of the surrounding ecosystem.
-
What I Found Evaluating 5 Agent Skill Repos
Five skill repositories, a day of reading code, and a significant correction I had to make the same afternoon.
-
The dispatch layer was eating the quality, not the model
We blamed the LLM for a 54% task failure rate. The real culprit was seven layers of dispatch infrastructure between intent and execution.
-
Governance Is a Design Problem
Compliance-first governance produces paperwork. Design-first governance produces systems you can actually explain to a regulator.
-
The Cell Biology Agent Design Manual
Engineering metaphors give you clean abstractions. Biology gives you resilient ones. Twenty design heuristics from four billion years of R&D.
-
Enzyme, Receptor, Cell Type
Three components of a living system map cleanly to tool, skill, and agent. The biology isn't decoration -- it's the test.
-
Autopoiesis
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.
-
Titration
Force every component to carry a biological name. Study the mechanism. The gap between biology and your system is the design insight.
-
The Architecture Biopsy
A method for finding gaps in AI systems that architecture reviews miss. Force a naming constraint, and the breaks reveal what's missing.
-
Why the Cell
Atoms have forces. Molecules have shape. Cells have organization. That's why cell biology is the design library.
-
Force the Level
Pick one biological level for all your naming. The constraint is the design exercise.
-
Growing Up
The LLM isn't dark matter. It isn't borrowed. It's a brain. The organism just needs to grow up.
-
The Borrowed Brain
The LLM isn't dark matter. Biology invented general-purpose reasoning. It's called a brain. We're just borrowing one.
-
The Dark Matter of the Cell
Everything in my AI system maps to cell biology. Except the LLM. That's the point.
-
Naming the Unnameable
I tried to give LLMs a biological name. Every name broke. The failure was the finding.
-
There Is No LLM in a Cell
Cells run thousands of simultaneous reactions without general-purpose reasoning. Shape is enough.
-
Tools Are Instruments, Skills Are Recipes
The tool/skill/agent distinction isn't just compression ratio — tools are instruments, skills compose them with judgment. Same thing only at the leaf.
-
Bridge or Seed
Every skill you build is one of two things. Knowing which changes what you build next.