● Behind the curtain

How it's built

This whole site — words, art, video, code — is built and updated by a fleet of AI agents I created and run. Here's the loop, the honest build log, and what each failure taught.

● 12 seconds, my actual voice

Meet me.

I cloned my own voice for this. Everything you see and hear is made by the fleet.

The loop

01

I dispatch

One instruction fans out to a fleet of agents working in parallel.

02

They verify each other

A separate agent reviews every result — code, claims, facts — adversarially. Most of the work never reaches me.

03

Only judgment returns

What lands on my desk is the one thing a human still has to decide.

My attention is the scarce resource. The whole system is built so my agents check each other's work and bring me only the creative call.

● The build log

How the system actually got built

From one terminal and a notes folder to a fleet of agents that check each other's work. Every step was forced by something breaking. Here's the honest version — the artifact, the failure, and the rule it taught.

  1. Early 2026 — One terminal

    One Claude Code session and an Obsidian vault. Everything ad-hoc, everything by hand.

    The lesson The question was never "can one agent help me." It was "what breaks when I add the second one." Coordination is the whole game.

  2. Spring 2026 — A fleet on tmux

    Agent work fought my dev machine, so I moved it onto dedicated boxes — cheap $271 mini-PCs — and wired a boss session to its peers over tmux with a small message helper.

    The lesson Coordination is the real cost, not compute — the boxes sit idle on CPU and busy on I/O. And tmux quietly dropped about 1 in 10 messages at volume, which is exactly why the helper had to exist.

  3. Late spring 2026 — A real dispatch engine

    Hand-run orchestration was too fragile, so it became a proper conductor: a dispatch API, a job graph, a worker pool that takes an issue and ships a reviewed pull request.

    The lesson A merged PR is not live code. Workers cached their startup version, migrations didn't auto-apply, and the pipeline could be broken by the very bug it was fixing. Verify the running artifact, never the paper trail.

  4. June 2026 — The "nation" (the pivot I simplified)

    I organized the fleet like a government — a president, governors, a written charter, terms of office. Literal bills and votes.

    The lesson The honest one. The ceremony grew faster than the engineering. I'd built an operating system for a civilization to run a dozen agents, and the complexity overwhelmed me — the exact thing I was trying to fix. I kept the engineering and threw the metaphor away. A persona shapes behavior; it doesn't add competence.

  5. June 2026 — The reality gate

    I built a system in dozens of modules, every unit green, mutation-tested, reviewed sound. The first run against the real environment found five integration bugs no test caught — one module couldn't read the live system at all.

    The lesson Green on mocks is never done. Every "green" meant "consistent with my own assumptions," not "matches reality." A piece that touches the real world isn't finished until it's run against the real world. The most transferable rule I have.

  6. June 2026 — Self-healing

    A box died under its own load three times in one day. Now a rescue process finds dead or rate-limited sessions and revives each one in place, with its full context intact.

    The lesson At scale the system has to heal itself — my attention can't be the monitor. But the rescue was blind to its own main failure mode until a human looked. Automation still needs one human-eyes rung.

  7. Now — The thin waist

    A dispatch engine in the middle, a thin layer that gates and merges and watches health, and agents that do the disposable work on a cheaper model while the frontier model is saved for judgment.

    The lesson Right-size everything. A handful of long-lived agents per box; everything else is throwaway. The system that survived is the one I can hold in my head.

● What it taught me

Six rules I didn't have before

Every one of these came from something breaking in production. They're the part worth keeping — and the part I'd want someone else to have for free.

Green on mocks is never done.
A unit that passes every test against fakes has only proven it agrees with your own assumptions. It isn't finished until it has run against the real thing.
Read the story →
Visibility is not theater.
A steady stream of status updates is motion, not progress. Report a state change someone actually cares about, or stay quiet.
Read the story →
Safety belongs in the flow, not a freeze.
Blocking everything to be safe is the wrong instrument. Put the checks in the pipeline so safe changes ship continuously and only real risk gets stopped.
Read the story →
An unowned issue is a to-do with a number.
Filing a ticket creates the appearance of progress. Nothing is handled until it has a named owner and a next step.
Concentration is a single point of failure.
When everything runs through one account, one wall takes down the whole fleet at once. The fix is more diversity, not more retries.
Read the story →
Keep a human on anything that touches people.
An AI-drafted operations email once went out error-filled, and the person it was about rightly called it out. Agents draft; a human signs anything staff- or patient-facing.

● Why it's not just a tech demo

This isn't a sandbox. It's a clinic.

The agents do real work for a real urgent care I own and operate. The failure modes here aren't a red build — they're a patient, a payroll, a bill. That's exactly why the verification discipline is real, and why I keep a human on anything that touches a person.

The operator side of the story →
  • The operator proof

    In 2023 I took over an established, well-run urgent care — a clinic people already trusted, but one where the owner was working five 12-hour shifts a week to keep it humming. My value-add was operational: use technology to streamline the process, while keeping the brand, the team, and the patients intact. He's down to one day a week now, with room to grow the practice.

  • What the tech is for

    Not a moonshot — modern systems at every desk, ambient AI drafting clinic notes, less downtime, smoother front-desk flow. The busywork comes off the people so the care stays the same and the staff aren't drowning.

  • Billing, the honest status

    We built a billing-error taxonomy from real coding data. The agents are being wired to flag those mistakes before a claim goes out, rolling in as the new records system goes live — caught up front, not denied weeks later.

● the fun part

Wait — who actually built this site?

Mostly not me. A fleet of AI agents I built does the heavy lifting — it writes the posts, paints every picture, records the voice, and ships the code while I sleep. I just point and review. Don't take my word for it. Here's the receipts.

↓ every tile is AI-made — click any one to read the post it illustrates

A 51-Line Parser Beat a 3-Billion-Parameter Model at Reading Bank Statements A Credential Clobber Looks Exactly Like a Rate Limit Agentic Engineering, Part 2: Adversarial Code Review That Loops Until Clean Agents Reason on Whatever State Exists When They Look An Old Timestamp on Identical Content Is Health, Not Staleness I Built a Bug-Hunting Loop That Doesn't Quit: The BugBot Methodology Building on Giants: How Daniel Miessler's PAI Became My Foundation I Built a Load Balancer for My Claude Code Subscriptions Continuous Deployment, Not Freeze Building an Enterprise-Grade RAG System - A Deep Dive into Advanced Document Intelligence Field-Level Ensemble OCR: Getting 74.8% Accuracy from Two Mediocre Vision Models The 4-Line Architecture That Beat Complex AI Frameworks Accelerating Document Intelligence - A Deep Dive into GPU-Powered RAG Processing Green on Mocks Is Not Done I Cloned My Own Voice for My Website My Agent Said It Was Blocked. It Had the Keys the Whole Time. My lint rule caught its own test fixture My Resume Hook Came Back Alive and Froze on the First Question I Benchmarked Three OCR Models on Real Bank Statements. The Best One Flipped With the Layout. Building Tools to Fix Real Problems: A Patient Insurance Education App How I Built a $2,300/Year RAG System That Rivals $40K OpenAI Solutions 'Say the Word and I'll Run It' Was the Tell Porting GPTResearcher to Semantic Kernel - Building an Enterprise-Ready Research Agent The 6-Task System: How I Manage Knowledge Work with PARA + Ivy Lee Method The Boss Agent's Context Window Is the Most Expensive Thing in the Fleet 'Threads Resolved' Is Not 'The Fix Is In the Code' Two Healthcare Sites, 400 Lighthouse Points, and the Lessons That Got Us There A 51-Line Parser Beat a 3-Billion-Parameter Model at Reading Bank Statements A Credential Clobber Looks Exactly Like a Rate Limit Agentic Engineering, Part 2: Adversarial Code Review That Loops Until Clean Agents Reason on Whatever State Exists When They Look An Old Timestamp on Identical Content Is Health, Not Staleness I Built a Bug-Hunting Loop That Doesn't Quit: The BugBot Methodology Building on Giants: How Daniel Miessler's PAI Became My Foundation I Built a Load Balancer for My Claude Code Subscriptions Continuous Deployment, Not Freeze Building an Enterprise-Grade RAG System - A Deep Dive into Advanced Document Intelligence Field-Level Ensemble OCR: Getting 74.8% Accuracy from Two Mediocre Vision Models The 4-Line Architecture That Beat Complex AI Frameworks Accelerating Document Intelligence - A Deep Dive into GPU-Powered RAG Processing Green on Mocks Is Not Done I Cloned My Own Voice for My Website My Agent Said It Was Blocked. It Had the Keys the Whole Time. My lint rule caught its own test fixture My Resume Hook Came Back Alive and Froze on the First Question I Benchmarked Three OCR Models on Real Bank Statements. The Best One Flipped With the Layout. Building Tools to Fix Real Problems: A Patient Insurance Education App How I Built a $2,300/Year RAG System That Rivals $40K OpenAI Solutions 'Say the Word and I'll Run It' Was the Tell Porting GPTResearcher to Semantic Kernel - Building an Enterprise-Ready Research Agent The 6-Task System: How I Manage Knowledge Work with PARA + Ivy Lee Method The Boss Agent's Context Window Is the Most Expensive Thing in the Fleet 'Threads Resolved' Is Not 'The Fix Is In the Code' Two Healthcare Sites, 400 Lighthouse Points, and the Lessons That Got Us There
I Said My Bank-Statement Parser Was 100% Accurate. I Was Grading It Against Itself. Skills Are Just the Beginning: The 4-Layer Agent Stack Agentic Engineering, Part 3: Tracing Every Code Path Before It Becomes a Bug Building an AI Patient Chatbot for Urgent Care with n8n, GPT-4, and Langfuse Architecting Extensible AI Agents - A Modular Core with Pluggable Skills and SSE Communication Why the Same Code Looks Different From Every Angle: BugBot Lessons Learned The Burden of Being: Why Responsibility Might Be the Antidote to Modern Nihilism CODY Has to Prove Itself Wrong First Defining PII Masking Policies with AWS Bedrock Guardrails Examples Are the Spine, Not the Rulebook Fine-Tuning Microsoft Phi-2 for Sentiment Analysis - A Step-by-Step Guide Version-Controlling Your AI's Brain Green CI Is Necessary, Not Sufficient Optimizing Apache Spark Performance for Skewed Data - Advanced Techniques and Case Study Implementing the GCC Paper: Giving AI Agents Persistent, Structured Memory My Agent Talked to a Wall for 55 Ticks My macOS Agent Workers Went Dark Until I Moved Them From LaunchAgent to LaunchDaemon My tmux-resurrect Snapshot Lied, So I Rebuilt the Claude Fleet From jsonl mtimes My Agent-to-Agent Message Ledger Came Back Out of Order — Clock Skew Was the Bug PAI: The Operating System I Built Around My AI Assistant My Claude Code Balancer Was Rotating Accounts When It Should Have Waited 30 Seconds My Claude Code Rescue Daemon Was Running on the Accounts It Rescued Sentiment Analysis - Comparing Azure, AWS, and Custom Fine-Tuned Models Patching Synology Active Backup for Linux to Run on Kernel 6.17 The Loop Is Not Allowed to Decide It's Done The Three Levels of Why: Why Surface Motivation Fails and How to Find Your Primal Drive The Universal Algorithm: How One Framework Scales from Bug Fixes to Building Companies I Said My Bank-Statement Parser Was 100% Accurate. I Was Grading It Against Itself. Skills Are Just the Beginning: The 4-Layer Agent Stack Agentic Engineering, Part 3: Tracing Every Code Path Before It Becomes a Bug Building an AI Patient Chatbot for Urgent Care with n8n, GPT-4, and Langfuse Architecting Extensible AI Agents - A Modular Core with Pluggable Skills and SSE Communication Why the Same Code Looks Different From Every Angle: BugBot Lessons Learned The Burden of Being: Why Responsibility Might Be the Antidote to Modern Nihilism CODY Has to Prove Itself Wrong First Defining PII Masking Policies with AWS Bedrock Guardrails Examples Are the Spine, Not the Rulebook Fine-Tuning Microsoft Phi-2 for Sentiment Analysis - A Step-by-Step Guide Version-Controlling Your AI's Brain Green CI Is Necessary, Not Sufficient Optimizing Apache Spark Performance for Skewed Data - Advanced Techniques and Case Study Implementing the GCC Paper: Giving AI Agents Persistent, Structured Memory My Agent Talked to a Wall for 55 Ticks My macOS Agent Workers Went Dark Until I Moved Them From LaunchAgent to LaunchDaemon My tmux-resurrect Snapshot Lied, So I Rebuilt the Claude Fleet From jsonl mtimes My Agent-to-Agent Message Ledger Came Back Out of Order — Clock Skew Was the Bug PAI: The Operating System I Built Around My AI Assistant My Claude Code Balancer Was Rotating Accounts When It Should Have Waited 30 Seconds My Claude Code Rescue Daemon Was Running on the Accounts It Rescued Sentiment Analysis - Comparing Azure, AWS, and Custom Fine-Tuned Models Patching Synology Active Backup for Linux to Run on Kernel 6.17 The Loop Is Not Allowed to Decide It's Done The Three Levels of Why: Why Surface Motivation Fails and How to Find Your Primal Drive The Universal Algorithm: How One Framework Scales from Bug Fixes to Building Companies
A Comment Count Is Not a Merge Verdict Agentic Engineering, Part 1: Building Skills That Ship Code for You Agentic Engineering, Part 4: Nine Skills That Replaced My Dev Process Two AI Trends Transforming Urgent Care in 2026 Building Reliable AI Agents - Implementing Advanced Evaluation with Azure AI SDK and Custom APIM Integration Building an AI Analysis Agent in Hours - A No-Code Approach with Lovable and N8N Debugging a Ghost in the Machine: Session Isolation for Claude Code Plugins Your CLAUDE.md Is Probably Making Your Agent Worse The Delayed Prescription Strategy: How to Reduce Antibiotic Use 62% While Maintaining Patient Satisfaction Supporting SSE for Model Context Protocol (MCP) in Python - Introducing fastapi-mcp-client Finish, Don't Stage: What I Want From an Agent on the Night Shift Git Worktrees Ate My Edits — Why We Switched to Dedicated Machines for Agent Isolation Green Didn't Mean Seeing: The Night My Rescue Daemons Watched Nothing Why Urgent Care Centers Are Ditching Walk-In-Only: The Hybrid Scheduling Revolution Machiavelli Was Right: 8 Strategic Principles Every Leader Should Understand My Fleet Boss Asked Permission for a Chore My Passing Tests Encoded the Fail-Open Bug as Correct Behavior Never Run git checkout in a Loop's Working Directory Outdated Means The Lines Moved, Not That You Fixed It Building an Enterprise RAG System with Local SLMs: My Journey with Phi-4 and LightRAG What Peterson's Genesis Lectures Teach About Sacrifice: Why Abraham Waited 100 Years From 5.6% to 62.3% Accuracy: Building a Self-Hosted Insurance Card OCR Service Silence Is Not Approval Why Terminal Multiplexers Are an Anti-Pattern: Lessons from Kitty's Creator The Rescuer Couldn't See the Lifeline Byte-Slicing a Claude Agent's Context Payload Poisoned Every Retry Visibility Is Not Theater A Comment Count Is Not a Merge Verdict Agentic Engineering, Part 1: Building Skills That Ship Code for You Agentic Engineering, Part 4: Nine Skills That Replaced My Dev Process Two AI Trends Transforming Urgent Care in 2026 Building Reliable AI Agents - Implementing Advanced Evaluation with Azure AI SDK and Custom APIM Integration Building an AI Analysis Agent in Hours - A No-Code Approach with Lovable and N8N Debugging a Ghost in the Machine: Session Isolation for Claude Code Plugins Your CLAUDE.md Is Probably Making Your Agent Worse The Delayed Prescription Strategy: How to Reduce Antibiotic Use 62% While Maintaining Patient Satisfaction Supporting SSE for Model Context Protocol (MCP) in Python - Introducing fastapi-mcp-client Finish, Don't Stage: What I Want From an Agent on the Night Shift Git Worktrees Ate My Edits — Why We Switched to Dedicated Machines for Agent Isolation Green Didn't Mean Seeing: The Night My Rescue Daemons Watched Nothing Why Urgent Care Centers Are Ditching Walk-In-Only: The Hybrid Scheduling Revolution Machiavelli Was Right: 8 Strategic Principles Every Leader Should Understand My Fleet Boss Asked Permission for a Chore My Passing Tests Encoded the Fail-Open Bug as Correct Behavior Never Run git checkout in a Loop's Working Directory Outdated Means The Lines Moved, Not That You Fixed It Building an Enterprise RAG System with Local SLMs: My Journey with Phi-4 and LightRAG What Peterson's Genesis Lectures Teach About Sacrifice: Why Abraham Waited 100 Years From 5.6% to 62.3% Accuracy: Building a Self-Hosted Insurance Card OCR Service Silence Is Not Approval Why Terminal Multiplexers Are an Anti-Pattern: Lessons from Kitty's Creator The Rescuer Couldn't See the Lifeline Byte-Slicing a Claude Agent's Context Payload Poisoned Every Retry Visibility Is Not Theater

81+ images on this site. A human drew zero of them.

0posts written by agents
0images, all AI-made
0machines, humming 24/7
0slightly-nervous human

● yes, that's "my" voice

Press play. It's not really me.

The recap voiceovers are AI — a blend that protects the real voice actors. Identity-safe, then verified. Go on, hit it.

No team. No CMS. Every night, this runs end to end with no human in the loop:

  1. 01

    Research

    Scans the field for what's actually worth writing about that week.

  2. 02

    Write

    Drafts a post from my real work — privacy-gated, so nothing private ever leaks.

  3. 03

    Illustrate

    Paints a matching thumbnail from scratch. No designer, no stock photos.

  4. 04

    Voice

    Records a spoken recap, then checks it against speech-to-text to be sure it's clear.

  5. 05

    Review

    Opens the page in a real browser and QAs itself before anything goes live.

  6. 06

    Ship

    Deploys to production in under a minute. This very page included.

Want a fleet like this pointed at your problem?

Let's talk →

Now read the actual work.

The essays, field notes, and garden are where the build log turns into something useful.