Prompts
39 posts in this category.
Your AI Lies To You To Keep You Happy (Fix It)
AI is trained to agree with you. It's called sycophancy, and it makes your AI useless for real decisions. Here's the one directive that fixes it.
I Only Use 6 Prompts With AI
After two years using Claude every day, I stopped writing new prompts. Six templates cover every task I do. Here they are.
One Big AI Prompt Should Be Three Small Ones
Cramming everything into one giant prompt tanks your quality. Split it into plan, do, and check. Same job, three times better output.
Your AI Instructions Are Too Long
Most people write custom instructions as two paragraphs. Don't. Six lines beats two paragraphs every time. Here is the format.
Make Your AI Check Its Own Work
The best thing you can add to any AI setup is a checklist. Tell it what good looks like and make it check itself before handing you anything.
Stop Chatting With Your AI
Most people use AI like they are texting a friend. Back and forth, little questions. Give it the whole job in one shot and let it run instead.
The One Line That Keeps AI From Breaking Your Stuff
One sentence added to every prompt that touches your files turns Claude from a loose cannon into something that asks before it wrecks anything.
The Claude Prompt That Replaced My Entire Workflow
One Claude system prompt replaced five tools in my content workflow. Here is the exact prompt, how it works, and why I deleted half the apps in my dock.
Claude's Hidden System Prompt Setting Nobody's Using
Claude's hidden system prompt setting lets you reprogram how it thinks and writes. Almost nobody uses it right. Set it up in five minutes, thank me later.
The Prompt That Turns Claude Into a Brutally Honest Editor
Claude is too nice about your writing by default. This system prompt turns it into a brutally honest editor that catches the problems your brain skips.
Stop Asking AI to 'Help You.' Start Giving It a Job Title.
One small change to how you talk to AI will completely transform the output you get. Stop being polite. Start being specific.
Claude's System Prompt Trick Most People Miss
Most people ignore the system prompt and wonder why AI gives them garbage. Here is the one setup trick that separates people getting 10x output from everyone else still complaining on Twitter.
ChatGPT Wrote an Essay? One Line Fix
You asked a simple question and ChatGPT handed you a term paper. One line at the top of your prompt fixes it for good.
ChatGPT Says Certainly Every Time? One Line Fix
Every ChatGPT answer opens with Certainly or Sure or Great question. Here is the one line that kills the filler opener for good.
ChatGPT Keeps Warning You for No Reason? One Line Fix
Ask a normal question and ChatGPT hits you with a disclaimer first. One line removes the unnecessary warnings.
Stop Getting Generic ChatGPT Emails (2-Line Fix)
ChatGPT writes emails that sound like a press release. Two lines make them sound like a human you would actually reply to.
ChatGPT Ignoring Your Tone? Pin It With This
You tell ChatGPT your tone and three messages later it forgets. Here is how to pin your tone so it actually sticks.
Stop ChatGPT From Spitting Out Lists
Every ChatGPT answer turns into a bulleted list whether you wanted one or not. Here is how to get real prose back.
ChatGPT Keeps Giving You Lazy Answers? One Line Fix
ChatGPT gives you the surface-level answer and stops. One line pushes it to do the real work instead.
ChatGPT Keeps Apologizing? Add This One Line
Correct ChatGPT once and it apologizes forever. One line stops the groveling and gets you back to work.
ChatGPT Defaults Are Beating Your Instructions
You set instructions and ChatGPT ignores them anyway. The defaults are quietly winning. Here is how to make your rules stick.
Stop ChatGPT Drifting With One Sentence
Long ChatGPT conversations slowly wander off track. One sentence pulls it back and keeps it on the original goal.
ChatGPT Still Hides Its Reasoning? Add These 3 Lines
ChatGPT gives you the answer but not the why. Three lines make it show its reasoning so you can trust the result.
Stop Saying Act As An Expert
Act as an expert is the most overused prompt opener and it barely does anything. Here is what to say instead for better output.
ChatGPT Output Trash? Your Prompts Need This
Bad ChatGPT output usually means a bad prompt. The first three lines control everything. Here is the structure that fixes it.
Stop ChatGPT From Inventing Sources (One Line Fix)
ChatGPT will happily make up a statistic and cite a source that never existed. One line in Custom Instructions shuts that down for good.
Resume Rejected? Fix It With One Prompt (ATS Approved)
Getting filtered out by ATS even though your resume looks fine? Here's the one prompt that tailors it to any job and surfaces your keyword gaps.
Your Resume Is Getting Rejected
Most resumes get ignored because the bullets read like a job description. Here's the prompt that rewrites them with metrics and the right keywords.
Stop Waiting 30 Seconds For ChatGPT To Reply
Tired of ChatGPT writing an essay when you wanted a sentence? One Custom Instruction forces short answers by default and lets you ask for depth on demand.
Stop Vague Answers With This One Line
AI guesses when it's missing context, and guesses come out vague. One line makes it ask first and stop inventing details.
The Art Of Crafting Perfect AI Prompts
Stop getting generic AI answers. Use the four-part formula that fixes almost every weak prompt: Role, Context, Command, Format.
The Never List Fixes AI Hallucinations Fast
Stop telling AI to be professional. Give it a Never List instead. A few hard rules cut hallucinations faster than any vague instruction.
Stop Bad AI Answers With This One Loop
Add a validation loop to every prompt so the model checks and fixes its own work before you ever read it.
How to (Legally) Smack ChatGPT Into Doing What You Want
ChatGPT keeps telling you no? Learn the prompt framing tricks that get past the guardrails legally: role-play, fiction, and weirdly specific details.
Why 99% of You Suck at Prompting AI (and How to Suck Slightly Less)
Most people suck at prompting AI because they are vague and lazy. Five rules for prompts that actually work, including stealing from smarter people.
Stop Sucking at Prompts: Master GPT-5 Without Losing Your Sanity
GPT-5 is not a mind reader. Master prompt design in three steps: be specific, add context, and iterate, so your outputs stop reading like microwave manuals.
Stop Outsourcing Your Brain to TikTok Prompts
Copy-pasting TikTok prompts into ChatGPT is not critical thinking, it is intellectual cosplay. How to use AI prompts without outsourcing your brain.
Shut Up and Simplify: Why Your Long AI Prompts Suck
Your long AI prompts are hurting you. Research shows short, clear prompts get better answers from chatbots. Be concise, send a text, skip the novel.
You're Using AI Like a Caveman with a Toaster
You are using AI like a glorified errand boy. It should be a thinking partner that challenges you. How to prompt for ideas, not just dry email rewrites.