A friend of mine tried Copilot once and decided it wasn’t for her. She asked it to write a message for her book club, a “here’s what I thought” note about the novel they were reading. What came back was three perfect paragraphs of what she called “book report language.” Nothing was wrong. Nothing was hers.
She closed the tab.
I asked what she’d typed. “Write me a message about the book.”
That’s the whole story. The instruction was thin, so the response was generic. Copilot has no way to know you want casual when you say nothing. It fills the gap with what usually works: formal, complete, textbook.
She tried again a few weeks later. This time she gave it more: who it was for, what tone she wanted, a bit of personality. Still not perfect on the first try. Still fixable. She edited it in three minutes and sent it. Her book club thought her writing had improved.
Here’s what changed: the tool did the exact same thing both times. What changed was how much instruction she gave it.
**What this teaches you**
Copilot doesn’t try to nail it on the first try. It generates a plausible first draft from what you gave it. Thin instruction equals generic output. This isn’t a flaw. It’s how the tool works. The real work happens in the back-and-forth.
If the first draft doesn’t fit, you stay in the same chat and tell it what to change. It remembers everything you’ve said. By the second or third version, it’s working from all your corrections, not just the last one. Most people get what they want in two or three rounds.
**Try this**
Pick something you tried before that came out wrong, or start fresh:
1. Open Copilot (copilot.microsoft.com or your Copilot-enabled browser) and type your request with context: who it’s for, what you want it to say, what tone you’re going for.
2. Read the draft. It probably won’t be exactly right. That’s normal.
3. Stay in the same chat. Tell it what you want changed. Be specific: “Can you make it shorter?” “It’s too formal. Can you write it like I actually talk?” “Can you end on the part about the garden instead?”
4. Read the second version. Do it again if needed.
5. Most of the time, two rounds gets you close enough that you’re only editing a sentence or two yourself.
The key: Copilot remembers everything in the same chat. Each correction builds on the last one. By round three, it’s smarter about what you actually want.
**What to watch for**
Most people stop too soon. If something is 80% right and you’re not sure how to fix it, just describe what’s wrong: “It’s almost there but something feels off about the opening.” You don’t need to know the answer. Naming the problem is enough.
One real limit: if you’re asking for something specific: a fact, a date, a quote, you still have to check the answer. Copilot sounds confident even when it shouldn’t be. It’s genuinely good at sounding right. You’re good at knowing what’s actually true. Stay skeptical on facts.
And sometimes iteration just doesn’t work. If you’ve done five rounds and it’s still missing the mark, you might be asking for something the tool can’t do, or you might just need to write it yourself. Not every task is a good fit for back-and-forth. You’ll learn which ones are as you go.
**The closer**
My friend now uses Copilot for every book club message. The first draft is still never exactly right. She’s made peace with that. The second one usually is. She told me she’s started looking forward to the writing part.
Once you get comfortable with iteration, the next skill in this series gets easier. You’ll understand when to push back and when to accept. You’ll know how much context to give. The tool works better every time you use it, not because it changes, but because you do.
Making Sense of AI is a six-part series walking first-time users through the basics, one skill at a time.