{"id":387133,"date":"2026-01-24T01:34:21","date_gmt":"2026-01-24T01:34:21","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/387133\/"},"modified":"2026-01-24T01:34:21","modified_gmt":"2026-01-24T01:34:21","slug":"i-use-the-unicorn-prompt-with-every-chatbot-it-instantly-fixes-the-worst-ai-problem","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/387133\/","title":{"rendered":"I use the &#8216;unicorn prompt&#8217; with every chatbot \u2014 it instantly fixes the worst AI problem"},"content":{"rendered":"<p id=\"1b7b544b-4d9d-4174-8ae9-ac6e2d832bd7\">For a long time, I thought I was bad at using AI. You&#8217;d never know it now considering I test and review AI for a living. But not too long ago, I\u2019d open <a data-analytics-id=\"inline-link\" href=\"https:\/\/www.tomsguide.com\/news\/chatgpt\" data-mrf-recirculation=\"inline-link\" data-before-rewrite-localise=\"https:\/\/www.tomsguide.com\/news\/chatgpt\" rel=\"nofollow noopener\" target=\"_blank\">ChatGPT<\/a>, Gemini or <a data-analytics-id=\"inline-link\" href=\"https:\/\/www.tomsguide.com\/ai\/what-is-claude-everything-you-need-to-know-about-anthropics-ai-powerhouse\" data-mrf-recirculation=\"inline-link\" data-before-rewrite-localise=\"https:\/\/www.tomsguide.com\/ai\/what-is-claude-everything-you-need-to-know-about-anthropics-ai-powerhouse\" rel=\"nofollow noopener\" target=\"_blank\">Claude<\/a>, 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. <\/p>\n<p>Then it hit me: the problem isn\u2019t that chatbots are dumb. It\u2019s that they\u2019re guessing. After all, they don&#8217;t think like humans and although some understand context, they still deliver responses based on patterns. <\/p>\n<p>That gap \u2014 between what you ask and what the chatbot assumes you meant \u2014 is where most AI responses fall apart. ChatGPT or your favorite <a data-analytics-id=\"inline-link\" href=\"https:\/\/www.tomsguide.com\/ai\/best-chatgpt-alternatives\" data-mrf-recirculation=\"inline-link\" data-before-rewrite-localise=\"https:\/\/www.tomsguide.com\/ai\/best-chatgpt-alternatives\" rel=\"nofollow noopener\" target=\"_blank\">alternative<\/a>, fills in the blanks, makes a few guesses and delivers a response that seems helpful until you try to actually use it.<\/p>\n<p>So I started using one prompt that forces any chatbot to slow down, clarify the goal and stop guessing.<\/p>\n<p><a id=\"elk-seasonal\" data-url=\"\" href=\"\" target=\"_blank\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\"\/><\/p>\n<p id=\"1b7b544b-4d9d-4174-8ae9-ac6e2d832bd7-2\">I call it the \u201cunicorn\u201d prompt, because it works across basically every AI tool I\u2019ve ever used or tested. And once you start using it, it\u2019s hard to go back.<\/p>\n<p>You may like<\/p>\n<p><a id=\"elk-d21fcb43-e8f2-4c28-9eba-c0aec5f9f294\" class=\"paywall\" aria-hidden=\"true\" data-url=\"\" href=\"\" target=\"_blank\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\"\/>The &#8216;unicorn&#8217; prompt <\/p>\n<p class=\"vanilla-image-block\" style=\"padding-top:56.25%;\">\n<p><img decoding=\"async\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/01\/yQk44xVVvEZb7xGqG9j5tU.jpg\" alt=\"Man working from home kitchen on his laptop\"   loading=\"lazy\" data-new-v2-image=\"true\" data-original-mos=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/01\/yQk44xVVvEZb7xGqG9j5tU.jpg\" data-pin-media=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/01\/yQk44xVVvEZb7xGqG9j5tU.jpg\" class=\"inline\"\/>\n<\/p>\n<p>(Image credit: Shutterstock)<\/p>\n<p id=\"88a6f64a-a5ba-464a-bd0a-02850a1b60b8\">Here\u2019s the exact prompt I use in every chatbot:<\/p>\n<p>Pretend you\u2019re my assistant and you actually want me to succeed. Ask up to 3 questions if anything\u2019s 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.<\/p>\n<p>This prompt works best anytime you\u2019re thinking \u201cI don\u2019t even know what to ask\u201d or \u201cI need something I can actually do.\u201d Here are great real-life situations:<\/p>\n<p>Here are 15 ways to use the \u201cunicorn prompt\u201d with real-world examples:<\/p>\n<p class=\"newsletter-form__strapline\">Get instant access to breaking news, the hottest reviews, great deals and helpful tips.<\/p>\n<p>Write an awkward text without sounding weird <br \/>Goal: Write a text to a friend I haven\u2019t replied to in 2 weeks without making it awkward.Send a friendly-but-firm email <br \/>Goal: Write an email saying I can\u2019t take on more work right now, but I\u2019m open to revisiting next month.Respond to a passive-aggressive message calmly <br \/>Goal: Reply to this message politely without being a doormat: [paste message]Turn a messy thought into a clear paragraph <br \/>Goal: Rewrite this into a clean, confident paragraph in my voice: [paste draft]Plan your week when your brain is fried <br \/>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 <br \/>Goal: Turn this messy list into a realistic plan with what to do today vs later: [paste list]Stop procrastinating and just start <br \/>Goal: Give me the first 3 tiny steps to start this task: [task]Decide between two options without overthinking <br \/>Goal: Help me choose between Option A and Option B based on my priorities: [list options]Plan a trip without opening 40 tabs <br \/>Goal: Build a simple 2-day itinerary for [city] with kid-friendly stops and breaks.Plan dinner when you\u2019re tired and everyone is picky <br \/>Goal: Give me 5 easy dinner ideas using what I already have: [list ingredients]Cut your monthly spending without sacrificing <br \/>Goal: Find 5 realistic ways to cut $200 from my monthly budget without making my life harder.Write a \u201cteacher message\u201d that doesn\u2019t sound unhinged <br \/>Goal: Write a message to my child\u2019s teacher about [issue] that\u2019s respectful but clear.Learn something fast without spiraling <br \/>Goal: Explain [topic] like I\u2019m smart but overwhelmed. Keep it short and practical.Fix a tech problem without guessing <br \/>Goal: Troubleshoot why my [device\/app] keeps doing [problem]. Ask questions first.Get better AI results across any chatbot <br \/>Goal: Help me get the best answer from any chatbot for this task: [task]<a id=\"elk-15f72030-71d7-4760-affb-09404e505e54\" class=\"paywall\" aria-hidden=\"true\" data-url=\"\" href=\"\" target=\"_blank\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\"\/>Why it works so well<\/p>\n<p class=\"vanilla-image-block\" style=\"padding-top:56.25%;\">\n<p><img decoding=\"async\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/01\/6Z4jz4zDuR7yhtbpnbgJJJ.jpg\" alt=\"A close up photo of someone's hands while typing on a laptop\"   loading=\"lazy\" data-new-v2-image=\"true\" data-original-mos=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/01\/6Z4jz4zDuR7yhtbpnbgJJJ.jpg\" data-pin-media=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2026\/01\/6Z4jz4zDuR7yhtbpnbgJJJ.jpg\" class=\"inline\"\/>\n<\/p>\n<p>(Image credit: Shutterstock)<\/p>\n<p id=\"c90a8cac-62ad-4528-a8d0-a3c3d2ddc1c5\">Most chatbots have the same bad habit: they confidently give answers \u2014 even if they&#8217;re <a data-analytics-id=\"inline-link\" href=\"https:\/\/www.tomsguide.com\/ai\/study-finds-chatgpt-5-is-wrong-about-1-in-4-times-heres-the-reason-why\" data-mrf-recirculation=\"inline-link\" data-before-rewrite-localise=\"https:\/\/www.tomsguide.com\/ai\/study-finds-chatgpt-5-is-wrong-about-1-in-4-times-heres-the-reason-why\" rel=\"nofollow noopener\" target=\"_blank\">wrong<\/a>.<\/p>\n<p>So if your prompt is missing a key detail, the AI will often fill in the blanks on its own \u2014 and that\u2019s how you end up with advice that sounds helpful, but is completely wrong for your particular situation.<\/p>\n<p>The unicorn prompt fixes that in three ways:<\/p>\n<p>You may like<\/p>\n<p>It forces clarification. Instead of guessing, the chatbot asks questions first. That alone improves the quality of the response more than any \u201cmagic words\u201d ever will.It forces structure. You\u2019re not getting a wall of text. You\u2019re getting a clear answer that better avoids mistakes.It keeps things short. This is a big one. Most people don\u2019t need a chatbot to write them a novel. They need something they can skim and act on.<a id=\"elk-560ec926-2e2e-400b-a897-93daa67e7d10\" class=\"paywall\" aria-hidden=\"true\" data-url=\"\" href=\"\" target=\"_blank\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\"\/>The takeaway<\/p>\n<p id=\"3a43353b-7fe7-41d3-90ee-ffafa5dbb1e7\">This prompt works for almost anything, but here are the moments it saves me the most time:<\/p>\n<p>Writing awkward messages\u00a0(texts, emails, follow-ups)Planning my week\u00a0when everything feels chaoticLearning something fast\u00a0without spiraling into 10 tabsGetting unstuck\u00a0when my brain is fried and I just need steps<\/p>\n<p id=\"4918d926-c0e8-406e-8895-d18dd1c71558\">What I really like about this prompt is that it works well when you\u2019re switching between tools. ChatGPT, Gemini and Claude all have different strengths, but this prompt gets them to behave like the same kind of assistant.<\/p>\n<p>You can even add an extra line that makes the response even better:<\/p>\n<p>\u201cIf you have to make assumptions, list them first.\u201d<\/p>\n<p>Give this universal prompt a try next time you&#8217;re stuck or switching from one chatbot to the other. It&#8217;s the secret to getting better answers nearly every time.<\/p>\n<p><a href=\"https:\/\/news.google.com\/publications\/CAAqKAgKIiJDQklTRXdnTWFnOEtEWFJ2YlhObmRXbGtaUzVqYjIwb0FBUAE\" rel=\"nofollow noopener\" id=\"7f740d38-efb1-4e86-a887-5aaf6166a1fb\" data-url=\"https:\/\/news.google.com\/publications\/CAAqKAgKIiJDQklTRXdnTWFnOEtEWFJ2YlhObmRXbGtaUzVqYjIwb0FBUAE\" target=\"_blank\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\"><\/p>\n<p class=\"vanilla-image-block\" style=\"padding-top:31.51%;\">\n<p><img decoding=\"async\" src=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/12\/1766753472_563_r3t8zZ5ve4GewFTeoCM3R6.jpg\" alt=\"Google News\"   loading=\"lazy\" data-new-v2-image=\"true\" data-original-mos=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/12\/1766753472_563_r3t8zZ5ve4GewFTeoCM3R6.jpg\" data-pin-media=\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/12\/1766753472_563_r3t8zZ5ve4GewFTeoCM3R6.jpg\" class=\"pull-right\"\/>\n<\/p>\n<p><\/a><\/p>\n<p id=\"d75bcea6-7756-4958-bf74-7299f77323c6\">Follow <a data-analytics-id=\"inline-link\" href=\"https:\/\/news.google.com\/publications\/CAAqKAgKIiJDQklTRXdnTWFnOEtEWFJ2YlhObmRXbGtaUzVqYjIwb0FBUAE\" target=\"_blank\" data-url=\"https:\/\/news.google.com\/publications\/CAAqKAgKIiJDQklTRXdnTWFnOEtEWFJ2YlhObmRXbGtaUzVqYjIwb0FBUAE\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\" data-mrf-recirculation=\"inline-link\" rel=\"nofollow noopener\">Tom&#8217;s Guide on Google News<\/a> and <a data-analytics-id=\"inline-link\" href=\"https:\/\/google.com\/preferences\/source?q=tomsguide.com\" target=\"_blank\" data-url=\"https:\/\/google.com\/preferences\/source?q=tomsguide.com\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\" data-mrf-recirculation=\"inline-link\" rel=\"nofollow noopener\">add us as a preferred source<\/a> to get our up-to-date news, analysis, and reviews in your feeds. <\/p>\n<p><a id=\"elk-more-from-tom-s-guide\" class=\"paywall\" aria-hidden=\"true\" data-url=\"\" href=\"\" target=\"_blank\" referrerpolicy=\"no-referrer-when-downgrade\" data-hl-processed=\"none\"\/>More from Tom&#8217;s Guide<\/p>\n","protected":false},"excerpt":{"rendered":"For a long time, I thought I was bad at using AI. You&#8217;d never know it now considering&hellip;\n","protected":false},"author":2,"featured_media":387134,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":{"0":"post-387133","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-technology","12":"tag-uk","13":"tag-united-kingdom","14":"tag-unitedkingdom"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/387133","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=387133"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/387133\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/387134"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=387133"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=387133"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=387133"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}