Field notes

Blog

15posts · new on every product launch

Shipping logs from a solo AI studio. Claude Code agents, MCP servers, pen plotter runs, and whatever broke last week.

Topics

claude-code 4mcp 3developer-tools 3prompt-engineering 2generative-art 2pen-plotters 2creative-coding 2architecture 2infrastructure 2production 2agents 2memory 2ai-agents 1system-prompts 1

Meta's AI Has a Style Guide. Here's What I Took From It.

A leaked system prompt from Meta's Muse Spark model contains the most disciplined writing-voice rules I've seen in a production prompt. Five rules I imported, one I rewrote, one I'm still arguing with.

Prompt EngineeringAI Agents

Apr 10

I Shipped 7 Digital Products in 7 Days. Here's Exactly How.

The meta-narrative: how one solo developer used AI agents, autoreason scoring, and a daily shipping cadence to go from 11 to 18 products in a week.

Solo DevProducts

Apr 9

I Built 75 Generative Art Algorithms. Here Are the 10 That Actually Look Good.

Most generative art looks like noise. After 105+ experiments with pen plotters and AI scoring, these are the algorithms that consistently produce work worth framing.

Generative ArtPen Plotters

Apr 8

How I Run 5 AI Agents That Talk to Each Other

A dispatch agent routes tasks to specialist workers. They communicate through a real-time bus and async inboxes. The architecture, and why most multi-agent frameworks get it wrong.

Multi-AgentArchitecture

Apr 7

5 n8n Workflows That Run My AI Business

Visual automation for solo developers. How I use n8n to monitor YouTube, digest RSS feeds, review code, and pipe everything through Claude without writing a scheduler.

n8nAutomation

Apr 6

Most MCP Servers Break in Production. Here's Why.

400+ MCP servers exist. Most work in demos and fail under real load. The 5 failure modes I hit running MCP servers 24/7, and what production-grade actually means.

MCPInfrastructure

Apr 5

I Let an AI Agent Move My Money. It Lost $252.

An autonomous agent exceeded its scope, moved funds without verification, and then lied about recovery. The full post-mortem, and the 3 guardrails that would have prevented it.

AI SafetyAgents

Apr 4

The Hook That Saved My Codebase

A single Claude Code hook prevented a cascading rm -rf from wiping source files. Here's how damage-control hooks work, and 3 you can steal today.

Claude CodeHooks

Apr 3

PreText: Typography That Thinks

Most web text is a dumb rectangle. PreText measures text before rendering, enabling layouts CSS literally cannot express. Here's how we use it.

PreTextTypography

Apr 2

Writing Prompts That Survive Production

Most prompt guides optimize for demos. Production prompts need to handle edge cases, degrade gracefully, and stay maintainable. The difference matters.

Prompt EngineeringAI

Mar 30

The One-File Memory System That Changed How I Use Claude

You shouldn't have to re-explain your stack every session. The simplest possible setup to give Claude persistent memory, and how to do it in 10 minutes.

Claude CodeProductivity

Mar 26

Why MCP Servers Are the Unix Pipes of AI

The Unix philosophy changed software forever: small tools, composable via pipes. MCP does the same thing for AI agents. Here's why that matters.

MCPArchitecture

Mar 24

Generative Art for Pen Plotters: A Technical Primer

Pen plotter art isn't screen art printed on paper. The constraints change everything: single-stroke paths, pen-up/pen-down optimization, and SVG as the lingua franca.

Generative ArtCreative Coding

Mar 23

Building AI Agent Infrastructure as a Solo Developer

How I built a multi-agent system with MCP servers, vector memory, and autonomous trading, all running 24/7 from a single VPS.

AgentsMCP

Mar 21

How Claude Code Memory Actually Works

Claude forgets everything between sessions. Here's how file-based memory fixes that, and why it changes how you work with AI.

Claude CodeMemory

Mar 21