Little Might
Illustration of Cathryn Lavery at a desk, surrounded by a laptop, a 3D printer, a small robot, and an open notebook of handwritten notes.
Cathryn Lavery

Cathryn Lavery · Builder & Operator · Est. 2013

I learn by doing. Then I write down how.

For operators getting technical, and builders learning to operate.

I go deep on one hard thing at a time, then write down exactly how to do it yourself. The topic keeps changing; the method doesn’t.

My best stuff is in my email.

My goal is for it to be the most useful email you read that day.

No spam. Unsubscribe in one click.

Gone deep on: Productivity Kickstarter DeFi Business AI

Writing since

2013

13 years of annual reviews, wins, and wrong turns.

Essays in the archive

161

From Kickstarter to crypto to AI agents.

These days

Building & learning

I own BestSelf, consult, and invest in building what’s next.

The latest

the two-line config that makes my AI agent actually reliable

Claude Code hooks turned repeated instructions into enforced behavior. Cat explains the difference between agent context and automation guardrails.

Little Might newsletter illustration for the two-line config that makes my AI agent actually reliable

Recent Writing

Full archive →

$ start ai-native

Free 7-day challenge

Make AI work
the way you work.

You're using AI. It's giving generic answers because it doesn't know who you are. Seven emails fix that — a context file, a skill, and four terminal commands. I went from never opening a terminal to 9,896 GitHub commits. This is the starting line.

No fluff. Each email has one thing to do.   See what's inside →

  1. 01 A year ago I'd never opened a terminal
  2. 02 What does ChatGPT actually think of you?
  3. 03 The one file that changes every AI conversation
  4. 04 I fired our Shopify agency and built my wife an AI assistant
  5. 05 Open the terminal. I'll tell you exactly what to type.
  6. 06 The things I didn't expect AI to change
  7. 07 Tell me what you built