Your Agent Is Enforcing Rules You Never Gave It

Anthropic already ships a warning about this in the system prompt. It loses to a note the model wrote about me last month, and the reason is not…

Jul 27 • Leon Ho

1

I Stopped Hand-Writing My Agents

Claude Code writes them from the runtime's own live manual. The agents write back.

Jul 21 • Leon Ho

2

1

2

The Five Shapes of an Agent Fleet

A team used to run LifeHack. Today 129 agents do, and every one of them takes one of five shapes.

Jul 16 • Leon Ho

3

1

June 2026

Approve the Decisions. Watch the Work.

What to put your hand on while an agent runs, what to keep your hand off, and how the same line decides when it runs without you.

Jun 30 • Leon Ho

1

1

You Don't Trust the Agent. You Trust the Loop.

The three-stage loop I run to make an agent reliable enough to put near my customers

Jun 18 • Leon Ho

2

6

May 2026

You Don't Need Fewer Agents. You Need Agents That Don't Need You.

Addy Osmani named the orchestration tax. The fix isn't fewer agents. It's agents that close their own loop.

May 29 • Leon Ho

1

4

April 2026

Open Loop Companies Forget. Closed Loop Companies Compound.

Most companies execute. Few learn from themselves. AI is what finally makes closing the loop cheap.

Apr 28 • Leon Ho

1

Your AI Integration Is Stuck in 1992

Most AI agents are pointed at the person, not the business. Steve Jobs warned us about this trap 34 years ago

Apr 20 • Leon Ho

2

1

March 2026

AI Made You More Productive. The Question Is: For Whom?

AI created a massive productivity surplus. Now there's a fight over who gets to keep it.

Mar 13 • Leon Ho

February 2026