DTC operator turned AI builder. Writing on agentic commerce, AI systems, and the future of commerce.
The piece I wrote on harnesses described five component layers that every production agentic system needs: orchestration and planning, an execution environment, validation and quality control, context and memory management, and logic and interaction.
Shop CLI: A Tool Built for AI Agents, Not Humans
Not all business relationships do the same job. Research shows which ones survive the agentic economy, and which were always just expensive due diligence.
The short version: When an AI agent gets a task 80% right, you can patch the last 20% by hand and ship today, or fix the instruction behind it and never touch that task again. The patch is faster now. The fix compounds. Most people, me included, pick the patch too often, because the economics that should govern the choice have changed and our instincts haven't caught up.
The skill that actually makes AI useful: meta-prompting
Fable is back. And it's changing how I think about thinking.
Antony Evans argues that building an AI system is farming, not hunting: there is no finished, shipped state, only a system you keep tending as models change.
The honesty test for AI-assisted writing isn't who typed the words, it's whether the idea is genuinely yours: a first-person account of one writer's pipeline.
Antony Evans on why AI agents that work all night push founder-operators toward the same always-on habits, and why he has not solved it yet.
I asked my AI to audit its own product's code for what was making development slow and expensive. I expected it to blame the code. It blamed me.
This week I gave my company mind away as something anyone can actually install, and the hardest part was making it boring.
I spent today deciding what my own product is allowed to reach. The answer I kept landing on was: nothing of yours.
I had someone from outside look at code my AI wrote this week. Not the output, the actual work. Every file, every test, every corner where a tired human would have cut one.
For weeks my company mind could read itself but not change itself. Today I let it write back, and the hard part wasn't the writing. It was deciding what it's allowed to change without me.
Tonight my own system refused to do what I told it to.
Last updated: 2026-07-05
AI-redpilled gets claimed constantly and checked rarely. Here's the screen-share test a Laurel CPO uses to tell real AI use from talk, for people and teams.
Today I did something that would have sounded reckless to me a year ago. I gave an AI permission to merge my own code into my repositories without asking me first.
I used to think kids were the end of my freedom. Two of them in, I've found almost the exact opposite.
Stop telling me the world is ending. You don't know that. Neither do I.
<!-- Ready if we decide to also publish to blog; LinkedIn-only by default, matching C076. --
Google launched AI checkout at scale. Your store is in the system. You still won't appear. Here's the part nobody is explaining.
I set out to build a DTC store almost entirely with AI.
Not all business relationships do the same job. Research shows which ones survive the agentic economy, and which were always just expensive due diligence.
The COO's job in an AI-first company is to build the operating system the company runs on. Here is what that OS looks like and how to build it.
Agents won't kill business relationships. They'll sort them. The ones doing low-value information work will quietly become unnecessary. The ones doing the hard human jobs will become rarer, and more valuable.
Five things AI can't replace: trust, context, distribution, taste, and liability. These aren't product categories. They're structural layers that become more valuable as AI gets better, not less.
I spent the first three months treating AI like a calculator. Type a question, get an answer. Occasionally useful, mostly generic.
You're probably sick of being told to learn AI tools. But this isn't that post.
The agent hype isn't about AI capability. It's about human org design, and we're copying the wrong thing.
You've probably noticed I'm writing a lot. Here's why I keep going anyway.
For most of human history, the most valuable place to be was the middle.
Nobody designed the org chart as a management philosophy. It was infrastructure.
!The LLM is the engine. The harness is the car.
Unpopular opinion: building AI workflows that stop for human confirmation isn't careful design. It might just be discomfort dressed up as caution.
Dad. Yogi. Searching for what to build next. That's the order for a reason.
Two CEOs used AI to cut headcount dramatically. They made opposite bets to get there.
The brand work we did at Wild Earth was real. We were selling through Instagram and Facebook, and on those channels emotional resonance isn't a nice-to-have, it's the mechanism. The photography, the dog stories, the community, the tone of voice. People were scrolling and we had about two seconds to make them feel something. It worked. Brand investment drove revenue in a way that was measurable and…
My goal: run my entire work life through a terminal. I'm about 60% there. Here's what the setup looks like.
OpenClaw is the fastest-growing open-source AI agent of 2026, with over 100,000 GitHub stars and a skills ecosystem anyone can extend. I built a skill that replaced my HelloFresh subscription, and what it took to build it says something about where a lot of billion-dollar convenience businesses are headed.
OpenAI launched Instant Checkout in September 2025. By March 2026, it was dead. Five months, roughly 30 merchants out of millions adopted it, and they've since pivoted back to routing users to merchant sites. Most coverage focused on what went wrong technically: product data too messy to standardize at scale, no sales tax infrastructure, merchant onboarding described as "arduous." Those things are…
Urgency works on humans. Scarcity works on humans. Beautiful photography works on humans. You've spent years getting these things right — the above-the-fold her
Amazon blocks agent crawlers. That's not a technical decision. It's a strategic one.
When an AI agent visits your store, it doesn't see your homepage or your brand story. It reads product identifiers, schema markup, protocol manifests, and check
The next wave of buyers won't have feelings about your brand. They'll have decision criteria. AI agents are already making purchasing decisions in software, and
91% of online stores are invisible to AI agents. The gap isn't traffic and it isn't brand. It's that the data isn't structured correctly.
For 30 years, commerce ran on two categories. Both assumed the buyer was a human. That assumption just broke.
Private equity figured out where durable value lives before most founders did. Not software. Boring businesses with an AI layer on top.
ChatGPT Instant Checkout launched on February 16. Within days, 800 million users had a direct checkout path through an AI agent. Glossier, SKIMS, Vuori — alread
I've started calling it the simultaneous truth.