Get all your news in one place.
100’s of premium titles.
One app.
Start reading
Tom’s Guide
Tom’s Guide
Technology
Amanda Caswell

I stopped asking AI to brainstorm — this is the only prompt I use to turn ideas into action

Texting.

I have a big idea problem. I have a figurative Mary Poppins-sized purse full of ideas and think all of them are worthy of "Shark Tank." But at the same time, I often lean on AI to shape new ideas and branch out from ideas I already have.

As someone who turns to ChatGPT or Gemini to shape my ideas, I've noticed that I'm often hit with a wall of options. Some of them are good, but I spend so much time filtering through the fluff that I almost feel like I've started from scratch.

In other words, I'm not stuck for a lack of ideas, I'm stuck because I lack decisions about those ideas. That's the problem with leaning on AI for brainstorming. It's built to expand the "solution space," but as humans, we suffer from decision paralysis. When an AI gives you 20 ideas, it hasn't solved your problem — it’s just multiplied your workload.

To fix this, I stopped using AI as a brainstormer and started using it as a strategic advisor. Here is the prompt that changed my daily workflow.

Going from ideas to action

(Image credit: Getty Images)

Like most people, I have a lot on my mind. So, instead of asking for a list that may or may not be useful, I use a prompt that forces the AI to narrow, prioritize and justify a single path forward.

The prompt: "Act as a strategic advisor. Based on my goal below, recommend ONE best option and explain why it is superior to alternatives. Then, list two backup options and specify exactly when I should choose them instead. My goal is [Insert your goal here]"

This shift moves the AI from an "idea generator" to a "decision engine." By forcing the model to pick a winner, you get:

  • Less fluff: No more scrolling through 15 vague suggestions.
  • Strategic context: You learn why an idea is good, not just that it exists.
  • Momentum: It’s easier to edit a decision than to create one from a vacuum.

Real world examples

1. Making the most of a busy weekend

(Image credit: Shutterstock)

When I have ideas about what I want to do over the weekend such as workout, clean out the garage, run errands, go grocery shopping, I'll use this prompt to narrow down my list with the goal of getting more done. So I'll prompt something like: I have three things I could do on Saturday: clean the kitchen, or work out and grocery shop for the week. I want the one that will make Sunday tomorrow easiest.

Within the prompt, the chatbot throws in some ideas that I hadn't thought of such as, "if it's a nice day, wash the car." Rather than a random cluster of ideas, this prompt helps give my ideas direction, while sparking new ones.

2. Deciding on purchases

(Image credit: Shutterstock)

If I have a list of ideas of what I need to buy, such as groceries for the week or to upgrade our living room, I don't ask for the best options. What I want are recommendations and backup ideas.

Using AI like a blank slate is never a good idea because what you'll get back is a bunch of slop. To use AI most effectively, you need to go in with a list of your own thoughts.

In this case, ChatGPT gives me ideas based on my budget and anything else I inputed.

3. Choosing a health habit you’ll actually stick with

(Image credit: Shutterstock)

I really like working out, but my eating habits are lackluster. Because of my "big ideas" I often forget about taking care of myself. For example, I'll stay "in the zone" and suddenly realize it's 3 p.m. and I haven't eaten lunch only to reach for a jar of pickles and handful of mixed nuts. See what I mean?

If I’m stuck on how to get healthier, I don’t ask for “a bunch of healthy ideas.” I ask for the single most realistic habit. I'll share a goal that is far more specific such as "I want to feel better and have more energy, but I only have 20 minutes a day."

Sometimes I'll even add an extra layer when the stakes are higher such as: “Evaluate these options based on long-term impact, effort required and likelihood of success.”

This forces the AI to weigh trade-offs (what pays off vs what just sounds good) instead of handing you the most “creative” answer.

Bottom line

AI is only as good as what you give it. So if you turn to AI and ask for a list of ideas, most of what you really want won't be there. But by using this prompt, you're giving the chatbot a good starting point, which makes all the difference.

You'll find that you will prompt less and there will be less back and forth because you'll get the preferred list of truly helpful ideas in the first place.
Give this a try next time you have a ton of ideas in your head. You might just discover that your brainstorming session with ChatGPT or preferred chatbot is much more productive.


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

Sign up to read this article
Read news from 100’s of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.