Skip to main content
Field notes

Blog

33posts · 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.

RSS feed

Topics

ai-agents 11creative-coding 6claude-code 6generative-art 5infrastructure 5automation 4multi-agent 4production 3hermes 3pen-plotters 3mcp 3developer-tools 3cost-optimization 2ai-safety 2

Flow Viz: Watching the Bitcoin Mempool Breathe

Live transaction data becomes fluid particle simulation. Flow Viz turns the Bitcoin fee market into something you can watch with your eyes.

Field NotesCreative Coding

We Built an Envelope Protocol to Stop Our AI Agents from Talking Forever

Seven Discord bots needed to coordinate without infinite loops. A five-field envelope header and a depth counter solved it. Here's the protocol.

AI AgentsMulti-Agent Systems

From Algorithm to Ink: How We Turn Generative Code into Physical Art

65 algorithms, a texture pipeline, and a pen plotter. The toolchain that turns SVG code into framed prints on the wall.

Generative ArtPen Plotting

A Circuit Breaker Saved Me $200 in Tokens. It Took 45 Minutes to Build.

One of my AI agents consumed 60% of its daily token budget in four hours. The circuit breaker throttled it automatically. Here's the pattern.

AI AgentsCost Management

The Most Useful Thing Your AI Agents Can Do Is Audit Themselves

We pointed our agents at our own knowledge base and asked what they should be doing that they weren't. Then we built the fixes.

AI AgentsSelf-Improvement

I Pointed 7 AI Agents at My YouTube History. They Found What I Couldn't See.

7 agents analyzed 1,062 YouTube videos and found 14 things they should be doing that they weren't. Topic clusters, channel ROI, knowledge gaps, and the meta-move: agents auditing themselves.

AI AgentsYouTube

The Real Cost of Running AI Agents in Production — A Monthly Breakdown (2026)

Your AI agent costs 5–15× more in production than your prototype. Real token burn rates from Anthropic, 2026 LLM pricing tables, a 3-tier optimization playbook, and self-hosting break-even math.

AI AgentsLLM Pricing

Your AI Newsletter Reads Like a Database Dump (Here's the Fix)

Our AI-generated digests had an 18% open rate. Five structural rules from Morning Brew, TLDR, and Ben's Bites doubled it. The template, the prompt trick, and the before/after.

AI AgentsNewsletters

How to Price AI Agent Services When Nobody Knows What They Cost

I surveyed 20 agencies and freelancers offering AI agent builds. The range was $500 to $150,000. Here's the framework I use to price Edgeless Lab's services.

AI AgentsPricing

Half My AI Agents Were Dead. I Didn't Know for a Week.

I discovered 10 of my 20 agents were ghosts — registered, visible in dashboards, producing nothing. Here's the five-layer self-healing system I built so it never happens again.

Multi-AgentInfrastructure

I Read 500 Google Reviews in Portland. Here's What Small Businesses Actually Need from AI.

Dental offices losing patients to voicemail. HVAC companies quoting three days late. The AI solutions Portland small businesses need aren't chatbots. They're answering the phone.

AI AgentsLocal Business

Hermes Curator: The Agent That Cleans Up After Your Agents

Nous Research shipped Hermes v0.12.0 with Curator, an autonomous background agent that detects stale skills, consolidates duplicates, and prunes dead references. Here's why it matters for multi-agent systems.

HermesAI Agents

The Agent Grounding Problem: How Hermes Knows What's Real

AI agents confabulate. They claim files exist that don't. They report tasks complete that aren't. The grounding problem isn't philosophical -- it's operational.

AI SafetyHermes

The AI Agent That Never Sleeps: Running Hermes 24/7 on a $5 VPS

Most AI agents die when you close the laptop. Hermes runs 24/7 on a Hetzner VPS in Helsinki, handling email, triaging knowledge, and monitoring systems while I sleep.

HermesAI Agents

Claude Code Hooks: The Harness Engineering That Actually Matters

Everyone's optimizing their prompts. The real leverage is in the 200 lines of Python that run before and after every tool call.

Claude CodeHooks

I Run a $12/Week AI Operations Team. Here's the Cost Breakdown.

Enterprise AI ops costs $50K+/month. I run 5 agents, 24/7, for $12/week. The architecture, the model routing, and why cheap doesn't mean fragile.

Multi-AgentAI Infrastructure

When Does Generated Plaid Become Tartan?

Six weave structures, 48 period-correct dye colors, and one question the Scottish Register cannot answer. A field journal on building a generative tartan engine.

Generative ArtCreative Coding

96 Algorithms, One Constraint: A Pen on Paper

A taxonomy of every generative art algorithm that survives the pen plotter constraint. Flow fields to fractals, reaction-diffusion to recursive trees. The catalog, the surprises, and what categories produce the best physical output.

Generative ArtCreative Coding

Meta's AI Has a Style Guide: What I Imported, What I Rewrote, What I Rejected.

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

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

I Built 75 Generative Art Algorithms. These 10 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

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

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

Most MCP Servers Break in Production. The 5 Failure Modes I Found.

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

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

The Hook That Saved My Codebase

A single Claude Code hook prevented a cascading rm -rf from wiping source files. The damage-control pattern, and 3 hooks you can steal today.

Claude CodeHooks

PreText: Typography That Thinks

Most web text is a dumb rectangle. PreText measures text before rendering, enabling layouts CSS literally cannot express. Six ways we use it.

PreTextTypography

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

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

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. Why that matters for building agent systems.

MCPArchitecture

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

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

How Claude Code Memory Actually Works

Claude forgets everything between sessions. File-based memory fixes that. The simplest setup, and why it changes how you work with AI.

Claude CodeMemory