Here's a scene that plays out thousands of times a day.
Someone opens ChatGPT for the first time, types something like "help me write an email" — and gets back a stiff, generic draft that sounds nothing like them. They shrug, close the tab, and tell their coworker: "I tried it. It's okay, I guess."
The tool didn't fail them. Their prompt did.
And it's not their fault — nobody tells you this upfront. But once you see it, you can't unsee it.
The mistake: being vague
When you give AI a vague prompt, you get a vague answer. Every time.
"Help me write an email" could mean a hundred different things. So AI makes a guess — usually a safe, bland, corporate-sounding one — because it has no idea who you're writing to, what you need them to do, or what tone you want.
It's like walking up to a stranger and saying "make me something to eat." They might hand you a granola bar. Technically food. Not what you wanted.
What a specific prompt looks like
Here's the same request, done right:
"Write a short, friendly email to a client named Sandra. I'm following up on a proposal I sent two weeks ago. I want to check in without sounding pushy. Keep it under five sentences."
That gives AI something to work with. You'll get a draft that's actually usable — one you might change a word or two in and send.
The difference isn't the tool. It's the instruction.
The four things that make a prompt specific
You don't need all four every time, but the more you include, the better the output:
1. Who you're talking to A message to your boss reads differently than one to a new client or a longtime friend. Tell AI who the audience is.
2. What you want them to do or feel After reading this, should they reply? Take action? Feel reassured? Give AI the outcome, not just the task.
3. The tone Friendly? Professional? Direct? Casual? AI will match whatever you name.
4. Any constraints Length, format, things to include or avoid. "Under 100 words" and "don't mention price yet" are both fair game.
A before and after
Before:
"Write me a social media post about my business."
After:
"Write a LinkedIn post for my small accounting firm. I want to reassure small business owners that tax season doesn't have to be stressful. Friendly and calm tone. Under 150 words."
The second one takes 20 extra seconds to type. The output is five times more useful.
The good news
You don't have to get it perfect on the first try. If the result isn't quite right, just tell it:
- "Make it shorter."
- "Sound less formal."
- "Try again, but lead with the most important point."
AI remembers the conversation. You're not starting over — you're refining.
Most people who think AI isn't useful for them have only ever tried vague prompts. Fix that one habit and the whole tool changes.
That's the whole lesson. Specific in, specific out.
If you want a simple framework for writing prompts that work every time — across emails, documents, research, and more — that's exactly what Module 1 of the Clearly, AI course covers. It takes about 20 minutes and it'll change how you use these tools for good. Plans start at $15/mo — see what's included.
Ready to go further?
The full Clearly, AI course goes deep on everything in this post — with hands-on exercises, real prompts, and new modules launching regularly.
See plans — from $15/mo