Get the prompt that builds AI loops for you

It interviews you, defines success, tests examples, and creates the reusable skill, rubric, and loop script for Codex or Claude Code.

The fastest way to make AI useful is to build a loop

A one-off prompt can produce a decent first draft. A loop can test the output, revise it, and keep reusable lessons inside the skill.

It interviews you first

The agent asks one question at a time so it understands the job, audience, inputs, trigger, constraints, and success criteria.

It defines the quality bar

You describe great and weak examples, then the agent turns your judgment into a pass/fail rubric.

It tests before it builds

The agent runs sample outputs, evaluates what passed or failed, revises, and asks for your feedback.

It creates reusable files

When the loop is ready, it creates the skill, eval, examples, output folder, and run script.

You end with a workflow that can generate, evaluate, revise, and learn from approval feedback.

Use this when you want AI output you can trust more than once.

The Loop Builder Prompt turns one repeated AI task into a workflow with a trigger, test examples, a pass/fail rubric, and a revision loop.

Paste it into Codex or Claude Code. Answer the questions. It builds the structure for you.

Start with one workflow. Give it a quality bar. Improve it with examples over time.

Choose the task

Pick something you already ask AI to produce, analyze, write, review, or organize.

Set the trigger

Decide what should start the loop: a keyword, file, email, task, schedule, command, or manual run.

Generate the setup

Create the skill, eval rubric, examples file, output folder, and loop script.

What you get after you opt in

01

A copy/paste Loop Builder prompt

Use it to turn a repeated AI task into a tested workflow for Codex or Claude Code.

02

A built-in interview sequence

The prompt asks for the job, audience, inputs, trigger, examples, constraints, and approval criteria.

03

A testing and evaluation process

It runs examples, grades outputs, explains what passed or failed, and revises before building.

04

A reusable loop file structure

It creates SKILL.md, eval.md, examples.md, outputs/, and scripts/run_loop.sh.

This is for you if...

You use AI for repeated work and want more consistent results

You want your prompts to test and revise their own output

You work in Codex or Claude Code

You want reusable skills, examples, and evaluation criteria