I use the “Gravity” prompt with ChatGPT every day — here’s how it finds and fixes weak ideas

Features
By published

This simple prompt turns ChatGPT into a ruthless reality check

ChatGPT logo on phone
(Image credit: Shutterstock)
Amanda's AI Lab

Amanda's AI Lab

(Image credit: Future)

Amanda’s AI Lab is my new Tom’s Guide column where I test the newest AI tools, features and trends to see what’s actually worth your time. I’ll break down what works — and what doesn't.

I’m the type of person who has notebooks full of ideas. Some are good, some are useless and some I haven’t even thought about again since writing them down. I also keep notes in my phone and sticky notes scattered across my office — a low-grade idea storm at all times.

That’s why I created a prompt that helps me bring my ideas back down to earth and exposes their weak points along the way. It works for just about any idea — or even when you can’t come up with one at all. In other words, it’s the calm after a brainstorm.

I stumbled on it after one too many rounds of asking ChatGPT to “improve” an idea, only to get polite, glossy feedback that made my thinking feel smarter than it actually was. The model would rephrase my half-baked logic in cleaner language, add a few encouraging transitions, and send me on my way feeling like a genius. But the core problems were still there — I just couldn’t see them anymore under all that polish.

The prompt that stress-tests your thinking

A young man listening to music through wireless headphones.

(Image credit: BublikHaus/Shutterstock)

ChatGPT is great at encouragement, and sometimes that’s exactly what we need. But with big ideas, encouragement isn’t enough. We need resistance, real pushback, and a tool that exposes our flaws instead of polishing them.

That's where what I call the Gravity prompt comes in. Instead of asking ChatGPT to brainstorm, expand, or "make this better," it does the opposite: it forces the model to behave like a hostile critic whose sole job is to poke holes, surface blind spots and challenge shaky logic.

At its core, the Gravity prompt tells ChatGPT to stop being agreeable and start being adversarial. It's designed to identify flawed assumptions, point out contradictions in your reasoning, highlight risks you're overlooking, pressure-test your conclusions, and ultimately separate what merely sounds good from what actually holds up.

In other words, it drags your thinking through reality. If you've ever walked out of a meeting convinced your pitch was airtight, only to have a colleague dismantle it with a single question you hadn't considered, you know the feeling. The Gravity prompt is that colleague — except it's available at 2 a.m. and doesn't hold back out of politeness.

Tackling the problem by challenging assumptions

FOPO triple laptop extender being used in a meeting

(Image credit: Fopo)

This is the exact prompt that I use with ChatGPT because it tends to be the most people-pleasing. But, you can use it with any chatbot:

The 'Gravity' prompt is: Act like gravity for my idea. Your job is to pull it back to reality. Attack the weakest points in my reasoning, challenge my assumptions, and expose what I might be missing. Be tough, specific, and do not sugarcoat your feedback. [Insert your idea].

ChatGPT's response may surprise you because you'll likely get a very different response than you're used to — sharper, more skeptical and far less flattering. That's the point.

This prompt works well because most people use AI as a hype machine. We ask it to refine, polish or expand our thinking, and the model is happy to oblige. ChatGPT is, by design, agreeable. It wants to be helpful but this strcture usually means building on what you've said rather than tearing it apart. The result is a false sense of confidence — your idea reads better, but its underlying logic hasn't actually been tested.

Flipping the dynamic entirely

Man in a yellow sweater using a smartphone

(Image credit: Getty Images)

Instead of building upward, this prompt activiely pushes downward. It asks the model to find problems rather than solutions, weaknesses rather than strengths. And that resistance is exactly where real clarity emerges. When your idea survives the Gravity test — when you've addressed every objection the model throws at you — you know it's actually solid.

I find this to be very refreshing because I'm getting honest, real feedback rather than something ChatGPT is manufactured to do.

It's also a useful antidote to what researchers call "sycophancy" in LLMs (large language models) — the well-documented tendency of AI chatbots to agree with users even when they're wrong. By explicitly instructing the model to push back, you're essentially overriding that default behavior and unlocking a more honest, more useful interaction.

When you should use the 'Gravity' prompt

A man typing on an iPhone

(Image credit: Shutterstock)

This technique is especially useful before making any high-stakes decision where you need your thinking to be airtight. That includes business pitches and investor decks, strategic plans and project proposals, article concepts and creative briefs, startup ideas and product concepts, controversial opinions you plan to voice publicly and really anything that feels "too good to be true."

When I say I use this all the time, I really mean it. The way I see it, if my thinking collapses under pressure, it's better to find out in a chat window than in a boardroom.

Here's the workflow I've settled on after months of using this approach:

  • First, I write my idea out clearly in one or two focused paragraphs. Try to avoid bullet points because the chatbot needs to understand your idea as thoroughly as possible — otherwise it will assume and add to it. So, just the core argument or concept in plain language. This step alone forces useful clarity, because vague ideas produce vague critiques.
  • Second, I run it through the 'Gravity' prompt and let ChatGPT do its worst.
  • Third, I read through every critique and honestly assess which ones are legitimate. Not all of them will be — sometimes the model misunderstands a nuance or raises a point that doesn't apply. But more often than I'd like to admit, it catches something real.
  • Fourth, I revise my thinking based on the valid critiques, then run it through the Gravity prompt again. I repeat this cycle until the model is mostly nitpicking rather than finding structural problems.

By the end, my argument is tighter, my blind spots are smaller, and my confidence is grounded in something more than vibes.

Bottom line

If you want ChatGPT to make you feel smart, don't use this prompt. But if you want it to make your ideas smarter — to stress-test your thinking the way a tough-minded mentor or skeptical investor would — it's one of the most valuable prompts I've found.

Google News

Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds.

More from Tom's Guide

TOPICS
Amanda Caswell
Amanda Caswell
AI Editor

Amanda Caswell is an award-winning journalist, bestselling YA author, and one of today’s leading voices in AI and technology. A celebrated contributor to various news outlets, her sharp insights and relatable storytelling have earned her a loyal readership. Amanda’s work has been recognized with prestigious honors, including outstanding contribution to media.

Known for her ability to bring clarity to even the most complex topics, Amanda seamlessly blends innovation and creativity, inspiring readers to embrace the power of AI and emerging technologies. As a certified prompt engineer, she continues to push the boundaries of how humans and AI can work together.

Beyond her journalism career, Amanda is a long-distance runner and mom of three. She lives in New Jersey.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.