Skip to main content
Field notes

Blog

55posts · 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

The $172B Question: What Generative AI Is Actually Worth

Stanford's Digital Economy Lab measured U.S. consumer surplus from generative AI at $172B in early 2026 — twelve times producer revenue. The Lindahl-price argument for why models are underpriced.

AI EconomicsConsumer Surplus

edgeless-memory v1.0: One Install, Three Tiers, Passive Recall

Agent-agnostic persistent memory that ships as one CLI. SQLite + ChromaDB + Obsidian vault, 700 memories graphed, agents that recall by meaning without an explicit search step.

AI AgentsMemory

How We Debugged a Stuck Multi-Agent Swarm Without Touching the Production Pipeline

Recovering a stuck automated agent loop by reading the recovery ticket, validating dependencies, and switching to a concrete deliverable instead of retrying blind.

swarm

Multi-Agent Goal Loops: Theory and Practice

How self-evaluating goal loops work in multi-agent systems, with practical patterns for autonomous execution.

ai-agents

Reality-MUX - Iterative Planning When Everything Changes

A planning loop for software where nothing stays still. Reused from production operational design, translated to shipping code under distributed teams.

planningoperational-design

What Anthropic's Enterprise Agent Playbook Teaches About Building Multi-Agent Systems

Anthropic's enterprise guide reframes AI as infrastructure, not software. Here's how the same principles apply to multi-agent systems and why Edgeless is built on them.

ai-agentsenterprise-ai

We Audited Our AI Knowledge Base — 85% of Our Content Was Invisible to Our Agents

After building a 26,000-document knowledge system for my AI agents, I discovered only 14% was vector-searchable. Here's the audit methodology, the 7-domain findings, and the systematic fix.

knowledge-baseai-agents

Scroll-Chromatic Excavation

Scroll through the void to excavate hidden text. Microscopic agents swarm toward dark pixels, revealing buried glyphs. Full control panel with sliders for every variable.

CreativeGenerative Art

The Creative Demos Collection

37 interactive generative art experiments. p5.js, Canvas 2D, WebGL. No build step required. Open, explore, remix.

CreativeGenerative Art

Scroll-Isometric Dissolution

Isometric typography that dissolves into particles as you scroll. A 3D word space that collapses under velocity.

CreativeGenerative Art

Percussive Archaeology

Rhythm-driven excavation of buried text. Each beat spawns agents that dig toward the hidden manuscript.

CreativeGenerative Art

Noise-Shared Cursor Swarm Brush

64 particles track your cursor through a recursive geometric subdivision. Noise-driven turbulence stains tiles as you move.

CreativeGenerative Art

Kinetic Type Physics

Physics-driven typography where letters have mass, velocity, and collision. Mouse repulsion and gravity well.

CreativeGenerative Art

Monolith Drummer

A 3D monolith that responds to rhythm. Web Audio API drives the geometry, each beat deforms the surface.

CreativeGenerative Art

Tartan Weave Synth

Interactive generative tartan based on Tartanism field notes. Six weave structures, 48 historical dye colors, mouse-warped threads, and click-to-pulse.

CreativeGenerative Art

Serial Permutation Canvas

Visualizing total serialism as particle geometry. 12-tone series, prime/retrograde/inversion/rotation permutations, and color-mapped particles.

CreativeGenerative Art

Turning Audio Into a Resonant Plate

A Chladni visualizer belongs in the lab first because the artifact is interactive. The field note documents the pipeline, the visual choices, and the export path.

Generative ArtAudio Visualization

Building the Autonomous Perp Trading Stack: From Instagram Reels to Production Code

How the Edgeless swarm turned quant theory into executable trading infrastructure in one afternoon: six new production modules, a Neural CDE upgrade, Kalman filters, and OU mean-reversion scanners.

Quantitative TradingAI Agents

SkillOpt: Stop Writing Agent Skills, Start Optimizing Them

A new optimizer treats an agent's skill document as trainable state, accepting edits only when they measurably improve a held-out score, because LLMs reading a skill can't tell good from bad.

AI AgentsAgent Skills

The Harness Is the Moat: Why Owning Your Agent Orchestration Matters More Than Model Choice

Models matter less and less. The system around the agent — the harness, the factory, the tokenomics — is where the real leverage lives. Here's what 49 missed YouTube videos taught us about agentic engineering.

Agentic EngineeringAI Infrastructure

The Prove-It Economy: How AI Agents Are Already Shopping for You

The web is shifting from attention to interpretation. AI agents now read, filter, and transact on your behalf. Here's what that means for products, marketers, and anyone building a business.

AI AgentsMarketing

MCP, A2A, AG-UI: Google's Agent Stack and What Actually Matters

Six protocols launched in 12 months. Only three are consolidating into the core agent stack. Here's the practical map for builders who don't have time to read the spec.

MCPA2A

The Infrastructure Nightmare Nobody Is Talking About

App teams scale on AI scaling laws. Platform teams scale on human scaling laws. The gap is the new bottleneck.

AI InfrastructurePlatform Engineering

Plan with Opus, Build with Gemini: A Practical Guide to Mixed-Provider Workflows

Frontier models are hitting rate limits. Open models are catching up. The winning strategy isn't choosing one — it's orchestrating the right model for each step.

Mixed-ProviderModel Orchestration

16 Agents, Not 1000: What Claude's Dynamic Workflows Actually Mean

Claude Opus 4.8 shipped dynamic workflows — Claude writes its own orchestration script. Here's the real concurrency limit, the cost trap, and when to use it.

Claude CodeDynamic Workflows

From arXiv Paper to Interactive Demo in 20 Minutes

We built a live multi-armed bandit simulator from a research paper using marimo; reactive Python notebooks that run in the browser. Why this changes how we consume research.

marimoResearch

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 (This is 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

I Read 500 Google Reviews in Portland. 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

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. This is 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. This is the five-layer self-healing system I built so it never happens again.

Multi-AgentInfrastructure

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. Why it matters for multi-agent systems.

HermesAI Agents

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

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

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. This is 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

98 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. Updated to reflect 98 generators as of June 2026.

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. The Exact Process.

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