Why I'm Writing So Much
You've probably noticed I'm writing a lot. Here's why I keep going anyway.
Posts grouped by category and tags, with searchable archives.
Results update as you type.
You've probably noticed I'm writing a lot. Here's why I keep going anyway.
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.
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 direct.
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 all true. But there's a more fundamental reason the post-mortems have mostly missed.