What a Time to Be Alive
My father had the internet. I have an agent in a terminal. I think we are feeling the same thing, one generation apart, and I wanted to write down what that feels like from the inside.
Notes on agents, AI products, and the way software gets built when the tooling writes back.
My father had the internet. I have an agent in a terminal. I think we are feeling the same thing, one generation apart, and I wanted to write down what that feels like from the inside.
DeepSeek open-sourced the program that wraps its model. The interesting decisions are all in that program, not in the model, and they are the same decisions you are about to make in your own AI product.
RuFlo bets that coordinating many agents is a systems problem, not a prompt problem. I think the bet is right, and I also think most teams reach for it two months early.
Every agent I run authenticates with a human's credentials or a shared service account. The audit log records the wrong actor, and I don't think I'm unusual.
Context rot is a memory problem, not a model problem. Here is the spec-driven loop I use to work around it as a solo builder.
Something weird is happening in the repos of a small but growing group of developers. They're pushing commits at 3am, 4am, 5am, not because they're grinding through the night, but because they're asleep. Their agent isn't.
The people getting the best work out of coding agents aren't writing better prompts. They're writing SOUL.md, STYLE.md, SKILL.md. Here's the mechanism I think is actually doing the work, and the part of the idea I don't buy.
Jesse Vincent's Superpowers turns prompts into files with rules. I opened the copy installed on my machine and read every line.
Gemini 3 Flash outperforms Gemini 3 Pro on coding benchmarks while costing 75% less and running 3x faster. This counterintuitive result reveals how knowledge distillation inverts model hierarchies and what it means for agentic development workflows.
Claude Code has the best agentic experience but costs ~$1k/month for heavy use. I built a Claude Skills-compatible system for Antigravity that makes AI coding preferences portable across platforms.
Cross-platform frameworks solved expensive labor. When AI makes labor cheap, the abstraction overhead remains but the savings vanish. Native is coming back.