The Self-Improving Prompt System That Gets Smarter With Every Use
Instantly build, score, and improve your AI prompts. Even if you “aren’t technical.”
TL;DR
The Builder-Evaluator Loop is a two-prompt system that writes, scores, and rewrites AI prompts against a 35-criteria rubric across 7 categories (Clarity, Specificity, Context, Format, Tone, Output, Edge Cases). The Prompt Builder drafts the prompt. The Prompt Evaluator scores it from 0 to 175 and returns a revision. This is the 2026 evolution of The Self-Improving Prompt System I published in July 2025. Works in ChatGPT, Claude, Perplexity, and Gemini. Saves credits, kills trial-and-error, and turns prompt writing into a measurable workflow.
I still hear: ‘‘I’m not technical’’ or ‘‘The results were meh’’ from some of my friends.
You’re not alone if your AI experience still feels not quite right - or a bit like tossing darts blindfolded: sometimes they hit, sometimes they puncture your hard-won patience.
This simple, step-by-step prompt system unlocks ChatGPT’s potential for better, more consistent results. No technical skills required. You’ll be ready for reliable answers in under two minutes.
Jump in and explore the step-by-step prompt system now; I’ll break down the science behind its consistent results at the end.
Hey, I’m Karo Zieminski 🤗
AI Product Manager and builder.
I write Product with Attitude, an AI newsletter for thousands of subscribers developing critical AI literacy the only way it sticks: through practice.
We don’t just use AI. We build workflows, automations, and products with it, while studying how AI itself is built, positioned, and woven into our work.
If you’re new here, welcome! Here’s what you might have missed:
The Only AI Prompting Guide That Works On Reasoning Models (And Our Cognition)
AttitudeVault: my searchable prompt and Skills library, including community-shared prompts from Product with Attitude readers.
What’s Inside
Why a 35-criteria rubric beats “rewrite until it feels right”
The 7 rubric categories and what each scores
The Prompt Builder prompt (free, copy-paste ready)
The Prompt Evaluator prompt (paid, the scoring engine)
A worked example: a low-scoring prompt rewritten to high-scoring
How to chain the two into a single agent loop
Why Trial-and-Error Prompting Is an Expensive Habit in 2026
A vague prompt run a thousand times burns a thousand cycles of credits to find the version that should have existed on attempt one.
A 35-criteria rubric is not academic. It’s a checklist that turns a hunch into a score. The score tells you which knob to turn, in what direction, by how much.
The shift: prompt engineering becomes prompt evaluation. The skill is no longer crafting the perfect sentence. The skill is scoring the sentence you already have.
The 7 Categories of the 35-Criteria Prompt Rubric
The Builder-Evaluator Loop: a 35-criteria Prompt Rubric
Two prompts. One writes, one scores. The scorer hands the writer a rubric, the writer rewrites, the scorer scores again. The loop stops when the score crosses a threshold I set.
Your setup:
ChatGPT Plus
Prompt Builder
Prompt Evaluator
That’s it.
This simple trio works for everyone, from building advanced AI agents to writing a best man speech.
The Prompt Builder
Copy-paste into any model. Drafts the first version of a prompt against the rubric.