Diary of an AI Practitioner
Workflows
The real sequence of steps, mapped before anything gets automated.
7 entries
August 5, 2026
Triggers: What Starts an Agent When You Don't
A trigger is what starts the work without you typing anything. It is the actual line between using a convenient tool and having something work for you, and it is the piece most people skip.
August 4, 2026
Do It Twice, Then Write It Down as a System
Once is a task. Twice is a pattern. The third time you are about to do it, stop and write the steps down instead. You need three things first, and none of them is software.
August 4, 2026
Ask Your AI to Show Its Work, Not Just Do It
AI work is invisible, which is why it feels out of control. Ask the agent to show you the work, not just do it, and the whole thing becomes something you can actually manage.
August 4, 2026
What Is a Second Brain? A Coat Check for Your Ideas
The term is oversold, which puts people off before they try it. Your first brain has ideas and is bad at holding them. A second brain is just somewhere outside your head where they live.
August 1, 2026
Human in the Loop vs On the Loop vs Out of the Loop
Human in the loop means a person approves every output. On the loop means it runs and a person watches. Out of the loop means it runs unattended. Most businesses use one setting for everything. Here is how to decide per workflow.
July 10, 2026
How I Use Voice Notes and Brain Dumps to Think
My process is audio first, not outline first, and forcing myself into the standard advice would have broken the way I actually work.
July 10, 2026
Why Micromanaging Claude Holds You Back
Most people fail with Claude because they treat it like a vending machine for tiny tasks instead of giving it a real goal and letting it work.