Mental Models for the AI Economy
Practical essays on how AI actually changes work, product, and business economics — not hype, not fear.
Field notes on AI, product, and the economics underneath.
Essays, field guides, and interactive decks on what actually changes in knowledge work as AI gets cheaper, faster, and more embedded — and what stays exactly the same.
- AI Development
Claude’s 10 New Updates: Which Ones Change How You Build
Ten Claude launches in five weeks, sorted by a product leader who builds alone: the three that change what you delegate, the gated ones, the noise, and what to try first.
October 22, 202613 min read · interactiveRead - AI Development
Altitude, Depth, Range: More Ambitious AI Prompting
How to be more ambitious with AI: Felix Rieseberg’s altitude, depth and range framework, fourteen templates and a practical, bounded Prompt Elevator.
October 22, 202613 min read · templates & toolsRead - AI Development
Claude Code Mods: Which Are Worth Installing, and What They Cost
Nine Claude Code mods from Ben AI’s video, judged by a solo builder: what each one can see, what it spends, which to install, and how to vet any mod before it runs as you.
October 21, 202612 min read · interactiveRead - AI Development
Claude Duet: What to Delegate, What to Keep
How to use Claude Duet, compare it with OpenAI Dots and Meta Muse, and choose what to delegate. Practical workflows, approvals, access, usage limits and privacy.
October 21, 202611 min read · interactiveRead - AI Development
HTML or Markdown for AI Agents? Let the Reader Decide
A 72-run benchmark found freeform HTML costs up to 21x the tokens of Markdown, and a template kit erases the gap. When each format earns its cost, with a calculator.
October 17, 20268 min read · interactiveRead - AI Development
Four Rules in One File: The CLAUDE.md Behind 220,000 Stars
Think before coding, simplicity first, surgical changes, goal-driven execution. What each rule prevents, why it matters, and how many hours of cleanup it can save.
October 15, 20268 min read · interactiveRead - AI Development
Harness²: The Agent Harness That Rewrites Itself
A harness makes an agent reliable. A harness for the harness makes it get better: every correction is captured, promoted, enforced or deleted.
October 8, 20268 min read · interactiveRead - AI Development
AI Development: Evidence Before Autonomy
A convincing demo is not a release gate. How to evaluate agent-built software, contain failure, and measure the whole delivery loop instead of the typing speed.
September 23, 20267 min read · interactiveRead - AI Development
The Practice: Spec-Driven, Maker-Checker, Governed Scope
Two credible trials on AI coding point in opposite directions — 55.8% faster in one, 19% slower in the other. The difference isn't the model. It's the practice. Three patterns, with interactive math and cited data.
June 2, 20269 min read · interactiveRead - AI Development
Loop Engineering: The Definitive Field Guide
The leverage point in software has moved from writing prompts to designing the loops that prompt your agents. The complete field guide — Ralph, maker-checker, worktrees, AGENTS.md, memory, and MCP — from someone who runs these loops across a live portfolio.
May 28, 202624 min readRead - AI Development
The Agent Harness — Setting Up Claude Code Like You Mean It
An AI coding model on its own is a brilliant intern with amnesia. The harness — twelve parts of configuration, rules, and checks you wrap around it — turns it into a teammate you'd put on a real codebase.
May 26, 2026Interactive deck · 14 slidesRead
Get the next essay the day it publishes.
A few a month, written from real builds. Unsubscribe in one click.