I use the 'unicorn prompt' with every chatbot — it instantly fixes the worst AI problem

For a long time, I thought I was bad at using AI. You'd never know it now considering I test and review AI for a living. But not too long ago, I’d open ChatGPT, Gemini or Claude, type what felt like a clear request, and still get an answer that was off and unhelpful. Even with memory enabled, the responses felt too long, generic and sometimes completely wrong. Not hallucinations, per se, just not good.

Then it hit me: the problem isn’t that chatbots are dumb. It’s that they’re guessing. After all, they don't think like humans and although some understand context, they still deliver responses based on patterns.

That gap — between what you ask and what the chatbot assumes you meant — is where most AI responses fall apart. ChatGPT or your favorite alternative, fills in the blanks, makes a few guesses and delivers a response that seems helpful until you try to actually use it.

So I started using one prompt that forces any chatbot to slow down, clarify the goal and stop guessing.

I call it the “unicorn” prompt, because it works across basically every AI tool I’ve ever used or tested. And once you start using it, it’s hard to go back.

The 'unicorn' prompt

Here’s the exact prompt I use in every chatbot:

Pretend you’re my assistant and you actually want me to succeed. Ask up to 3 questions if anything’s unclear. Then give me: the answer, the plan and the pitfalls. Keep it short and tailored to: [insert goal]. If you have to make assumptions, list them first.

This prompt works best anytime you’re thinking “I don’t even know what to ask” or “I need something I can actually do.” Here are great real-life situations:

Here are 15 ways to use the “unicorn prompt” with real-world examples:

• Write an awkward text without sounding weird
  Goal: Write a text to a friend I haven’t replied to in 2 weeks without making it awkward.
• Send a friendly-but-firm email
  Goal: Write an email saying I can’t take on more work right now, but I’m open to revisiting next month.
• Respond to a passive-aggressive message calmly
  Goal: Reply to this message politely without being a doormat: [paste message]
• Turn a messy thought into a clear paragraph
  Goal: Rewrite this into a clean, confident paragraph in my voice: [paste draft]
• Plan your week when your brain is fried
  Goal: Plan my week with 3 priorities, 5 must-dos, and realistic time blocks. I have [X] hours available.
• Make a to-do list you can actually finish
  Goal: Turn this messy list into a realistic plan with what to do today vs later: [paste list]
• Stop procrastinating and just start
  Goal: Give me the first 3 tiny steps to start this task: [task]
• Decide between two options without overthinking
  Goal: Help me choose between Option A and Option B based on my priorities: [list options]
• Plan a trip without opening 40 tabs
  Goal: Build a simple 2-day itinerary for [city] with kid-friendly stops and breaks.
• Plan dinner when you’re tired and everyone is picky
  Goal: Give me 5 easy dinner ideas using what I already have: [list ingredients]
• Cut your monthly spending without sacrificing
  Goal: Find 5 realistic ways to cut $200 from my monthly budget without making my life harder.
• Write a “teacher message” that doesn’t sound unhinged
  Goal: Write a message to my child’s teacher about [issue] that’s respectful but clear.
• Learn something fast without spiraling
  Goal: Explain [topic] like I’m smart but overwhelmed. Keep it short and practical.
• Fix a tech problem without guessing
  Goal: Troubleshoot why my [device/app] keeps doing [problem]. Ask questions first.
• Get better AI results across any chatbot
  Goal: Help me get the best answer from any chatbot for this task: [task]

Why it works so well

Most chatbots have the same bad habit: they confidently give answers — even if they're wrong.

So if your prompt is missing a key detail, the AI will often fill in the blanks on its own — and that’s how you end up with advice that sounds helpful, but is completely wrong for your particular situation.

The unicorn prompt fixes that in three ways:

• It forces clarification. Instead of guessing, the chatbot asks questions first. That alone improves the quality of the response more than any “magic words” ever will.
• It forces structure. You’re not getting a wall of text. You’re getting a clear answer that better avoids mistakes.
• It keeps things short. This is a big one. Most people don’t need a chatbot to write them a novel. They need something they can skim and act on.

The takeaway

This prompt works for almost anything, but here are the moments it saves me the most time:

• Writing awkward messages (texts, emails, follow-ups)
• Planning my week when everything feels chaotic
• Learning something fast without spiraling into 10 tabs
• Getting unstuck when my brain is fried and I just need steps

What I really like about this prompt is that it works well when you’re switching between tools. ChatGPT, Gemini and Claude all have different strengths, but this prompt gets them to behave like the same kind of assistant.

You can even add an extra line that makes the response even better:

“If you have to make assumptions, list them first.”

Give this universal prompt a try next time you're stuck or switching from one chatbot to the other. It's the secret to getting better answers nearly every time.

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

• Google Gemini is basically running my side hustle for me — here’s how
• I didn’t realize Claude could do this — 10 features hiding in plain sight
• ChatGPT earbuds may be coming in 2026 — but can they really compete with AirPods?