There are thirty items on the list. So you type the prompt, paste an item, read the answer, fix it, and do it again. Twenty nine more times.
That is the ceiling on everything you have learned so far. However good your prompt is, you are still the one finding the work, checking the work, and pressing go. The job scales with your afternoon, and your afternoon does not scale.
Forty five minutes and you will be able to write a goal a machine can actually grade, run one real loop on a folder of files, watch it check its own work, and put four stop rules on it so it cannot run forever or burn your usage.
This is the biggest step up in the course so far, and it is still not code. If you have a job with many items in it and a clear finish line, you can run this today.
The proof behind this
Liz Elliott runs her whole operation on AI automations spread across several computers, and she is not an engineer. None of it started with clever prompts. It started with jobs that repeat and have a clear finish line.
What this lesson is
Lesson 4.6 of the free AI for Entrepreneurs course, in Module 4: Talking To AI.
A thermostat is a loop. It does not heat your house once and hope. It checks the temperature, turns the heat on if the room is colder than your number, then checks again, and stops when the room hits the number. Three things make that work. A number you set, a check that compares reality to that number, and a stop rule so it does not run all night. A prompt is one instruction: you ask, you get one answer, and you are the one who checks it. A loop is a system that does the prompting for you. It finds the work, does one piece, checks that piece against a bar you set, writes down what happened, and goes again until the bar is met or a limit stops it. The skill stops being write a really good prompt and becomes describe a finish line clearly enough that a machine can tell whether you crossed it. That last part is where most loops die.
New here? Use the free AI for Entrepreneurs course outline to read this series in the best order.
Behind the paywall
The five steps inside every loop, and how to agree the plan before anything runs
The Loop Charter, filled in for a real job
A goal loop for a folder of files, and one that checks its own sources
The two commands, and how to run a loop on a rhythm or a schedule
The four rails that stop it running forever or burning your usage
What still needs your approval before it goes out with your name on it
The ten mistakes, and the checklist
What paid subscribers get overall
Paid subscribers get every part of AI for Entrepreneurs in full. Every numbered step, every prompt in a block you can copy, the mistakes list, and the checklist at the end. You also get the rest of the run as it goes out, and the whole paid archive on Liz on the Web.
<!-- NATIVE BLOCK: unlock-this-article-now -->
The free half above is the concept, and it stands on its own. The locked half is the work, and it stays in your archive for as long as you are subscribed.
Click the button, subscribe, and the locked section below opens right away. You get this article now, and every other part in the series.
<!-- NATIVE BLOCK: upgrade-button -->
The full walkthrough is below the paywall.
Click the button, subscribe, and the locked section below opens right away. You get this article now.
