Why Your AI System Is Never Done
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.
Category: engineering
Fable is back — what using an expensive, deeply capable model teaches about discriminating AI use
Fable is back. And it's changing how I think about thinking.
500 agents at Edge Esmeralda — the missing layer is discovery and mediation
<!-- Ready if we decide to also publish to blog; LinkedIn-only by default, matching C076. --
When to fix AI's work by hand vs fix the system that produced it
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.
Google launched AI checkout at scale. Your store is in the system. You still won't appear.
Google launched AI checkout at scale. Your store is in the system. You still won't appear. Here's the part nobody is explaining.
Meta-prompting — the thinking skill that makes AI useful
The skill that actually makes AI useful: meta-prompting
Launching Shop CLI
Shop CLI: A Tool Built for AI Agents, Not Humans
How AI Agents Reshape Business Relationships
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 Is Building the AI Operating System
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 sort business relationships — not destroy them
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 — and Why Combining Them Is the Real Moat
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.
The Problem Wasn't the Model
I spent the first three months treating AI like a calculator. Type a question, get an answer. Occasionally useful, mostly generic.