San DiegoBuilding since 2015Early adopter

MikeHodgen

I build companies that run themselves.

I co-founded a vertically integrated manufacturer and apparel brand. Now I'm building the agents that run it, and writing down everything I learn along the way.

Subscribe to my newsletter Read the story
10,477
code changes shipped since
I switched to building
with AI agents in February.
2015
$200 of fabric
Chapter one · 2015

The fabric

Morning light on a small table with folded printed fabric, scissors, and a home sewing machine
$200

That's what we started with. Fabric, an apartment, and an Etsy shop.

My co-founder and I hand-sewed the first pieces ourselves. I learned the business by doing every job in it: making, shipping, answering customers, and figuring out what to make next.

Off the clockFormer Division I soccer player. These days I ride the coast of North County San Diego with my family.
A festival crowd at golden hour, seen from behind, wearing printed, op-art, holographic and mesh outfits
Where it ended up

Made for the dance floor.

We made clothes for festivals and dance floors, and sold them straight to the people wearing them.

Chapter two · 2017 onward

The factory

We didn't hand the making to someone else. We built a microfactory in San Diego.

Design, UV printing, cutting, sewing, and shipping, all in one building. Every operating decision was ours to make, which made it a good place to test better systems.

Top-down view of a sunlit cutting table with pattern pieces on printed fabric

One roof, the whole chain

Vertically integrated
01

Design

Prints and patterns made in-house

02

Print

UV printed on fabric in-house

03

Cut

Cut to size from digital patterns

04

Sew

Sewn to order

05

Ship

Shipped from the same building

06

Sell

Sold direct, online

+38%

Revenue per employee

2024 · my company
42%

Less manual operations time

2024 · my company

Cash tied up in inventory

Results from my own company. The inventory drop came from better forecasting and operating decisions and was reported by Fashion Capital.

The turn

Then the craft became code.

The same instinct that built the factory now builds software. The printer still runs. Now agents run the work around it.

Chapter three · 2026

The machines

I've been building software for years. This year the work flipped: now I build every day with AI agents beside me.

These numbers come straight from my own code history.

10,477

Code changes shipped since the switch to agents on February 10

76

Repositories

162

Build notes published

Code shipped per month

01,0002,0003,000Feb: 291 code changes291FebMar: 686 code changes686MarApr: 596 code changes596AprMay: 877 code changes877MayJun: 1,070 code changes1,070JunJul: 1,748 code changes1,748JulAug: 2,530 code changes2,530AugSep (through the 24th): 2,679 code changes2,679Sep*0k1k2k3kFeb: 291 code changes291FebMar: 686 code changes686MarApr: 596 code changes596AprMay: 877 code changes877MayJun: 1,070 code changes1.1kJunJul: 1,748 code changes1.7kJulAug: 2,530 code changes2.5kAugSep (through the 24th): 2,679 code changes2.7kSep*

Code changes per month across 76 repositories, counted from the switch to agents in February. September runs through the 24th.

When AI took over

  1. Feb 10

    The flip

    I moved my day-to-day building onto AI agents, starting with Claude.

  2. Jul 20

    Agents ship on their own

    Scheduled agents start making changes under their own name. 50 so far.

  3. Aug 15

    Grok joins

    A second AI model, used where it's strongest.

  4. Sep 8

    Codex joins

    A third model. 16 of its changes merged since.

  5. Sep 25

    This site

    Images made with GPT Image 2.5, video with Seedance 2.5.

Chapter four · How trust is earned

The ladder

A hand resting on a softly glowing button on a light console, dashboards blurred behind

More autonomy means tighter guardrails, not looser ones.

  1. 1

    Agents propose. I approve.

    Every system starts with a person making the call.

  2. 2

    Every decision gets recorded.

    What I approved, changed, or turned down, and why.

  3. 3

    Results get measured.

    Each kind of task has to prove it gets it right, again and again.

  4. 4

    Autonomy widens.

    First it suggests, then it drafts, then it acts with an undo button. One step at a time.

One company, three systems.

Each system runs its own part of the business. They share one rule: the decisions that matter come to me.

Demand

Finding customers

Marketing, ads, email, search, content

Supply

Making the product

Products, inventory, orders, production

Back office

Running the company

Money, people, tax, compliance, paperwork

I make
the callOn what matters

Departments of agents.

Each department has a job, a team of named agents, and everything it has learned so far. One agent in each checks what's missing and asks me before the department takes on more.

Video studio
19
Competitive intelligence
15
Organic growth
14
Email
11
Trading
10
Two more departments
25

Agents per department. 94 roles across 7 departments.

A sunlit microfactory at sunrise with quiet printers and sewing stations and dashboards on the wall
Chapter five · What's next

The company that runs itself.

Agents find the work, do it, check it, and learn from every decision I make. The ones that prove themselves get more room. I'm building it in the open.

Every system I ship knows when to stop and ask.
Read the build note

Build notes

All 162 notes →
Pace

A full quarter of building with agents

What 1,900 code changes in three months actually looked like.

ReadQuality

An AI that catches its own mistakes

Building the check into the system instead of hoping for good output.

ReadJudgment

Where my systems stop and ask me

The decisions I keep for myself, by design.

ReadFactory

Running a factory floor from a chat bot

Production updates where the team already talks.

ReadGrounding

Keeping AI honest about what we sell

Locking answers to the real catalog and the real prices.

ReadDay to day

A day working with AI agents

How the work actually gets split between me and the agents.

Read