Prompt Zero
Go forth.
Prompt better.
Get your thinking out of your head before AI has a chance to reshape it.
Okay, so, AI is fast. Suspiciously fast. So fast that you'll start typing a half-baked idea, watch it spit out something polished and confident, and forget you ever had a different vision in the first place. BadaBING, badaboom, your original thought? Gone. Replaced by something that sounds smart but isn't yours.
Prompt Zero is the brain dump you do before you open the chat window. Seven questions. A timer. A blank page. That's it. No AI in the room yet. Just you, deciding what you actually think, so when you finally do prompt the robot, you're driving instead of getting driven.
A receipt, since you asked
I get a week's worth of work done in 30 minutes instead of half a day.
That's not a marketing number. That's me. Same brain, same tools, same chatbot. The only variable is whether I did Prompt Zero before opening the chat window. Half a day of back-and-forth ("no, not like that," "closer, but," "okay try again") collapses into one clean handoff because I figured out what I actually wanted before I asked. Compounding weekly, this is the difference between drowning and surfing.
Why Prompt Zero is awesome
It saves you from your own first instinct. Your first prompt is almost always wrong. Not because you're dumb. Because you haven't decided what you want yet. Prompt Zero forces the deciding to happen before the typing.
It catches the stuff in your head you forgot was in your head. Every task has institutional knowledge, unwritten rules, and weird little constraints that are obvious to you and invisible to everyone else (including the AI). Question 5 alone will save you three rounds of "no, not like that."
It names the hard part out loud. Most prompts collapse on the one piece that actually required judgment. Prompt Zero makes you point at that piece before you delegate. Big difference.
It is, somehow, also therapy. Okay not really. But kind of. You will be surprised how often the answer to "what am I actually trying to accomplish?" is "huh. Not what I was about to ask for." That's the whole product right there.
The seven questions
Look. If you don't want to use my little app, that's fine. Truly. (A little hurtful, but fine.) Here are the questions. Grab them. Print them. Tape them to your monitor. Tattoo them on your forearm. The whole point is the thinking, not the software.
- 1
What am I actually trying to accomplish?
Not the task. The outcome. "Write a blog post" is a task. "Convince mid-level managers that their AI strategy has a blind spot they haven't considered" is an outcome. Say it in one sentence. If you can't get it to one sentence, you don't know what you want yet. That's fine. Keep talking it through until you do.
- 2
Why does this matter?
What happens if this goes well? What happens if you don't do it at all? This forces you to separate the things that actually need to be good from the things that just need to exist. Not everything is high-stakes. Knowing which category you're in changes how much specification work the task actually requires.
- 3
What does "done" look like?
Describe the finished thing. Not the process. The output. If someone handed it to you completed, what would make you say "yes, that's it"? Be specific. Length, format, tone, level of detail, who it's for, what they should feel or do or know after they encounter it. If you can't describe what done looks like, you're not ready to delegate this to anyone — human or AI.
- 4
What does "wrong" look like?
This is the one people skip. It's the most important. What would make you look at the output and say "no, that's not what I meant," even if it's polished and technically correct? What's the subtle failure mode? Think about the last time AI (or a person) delivered something that checked every box but still missed the point. What did they miss? That's the constraint you need to encode. Write it down now, while you can see it, before the AI's confident framing makes you forget you ever had a different vision.
- 5
What do I already know that I haven't written down?
The institutional knowledge. The context. The unwritten rules. The thing that's obvious to you but wouldn't be obvious to someone encountering this task for the first time. This is the stuff that lives in your head and evaporates the second you let someone else start working without it. Say it out loud or write it down. All of it.
- 6
What are the pieces?
Break it down. What are the components, subtasks, chunks? What comes first? What depends on what? What could be done independently? You're building the decomposition that makes a specification work. But you're doing it in your own head first, where you can see the whole picture and catch the dependencies that a task list would miss.
- 7
What's the hard part?
Every task has one piece that's genuinely difficult and several pieces that are just effort. Name the hard part. Where are the judgment calls? Where could this go sideways? Where are you least certain? This is where your specification needs the most detail. And it's the part most people gloss over because it's uncomfortable to sit with uncertainty.
Bonus freebie
The 95% Rule:
Stop guessing. Start interviewing. 95% or bust.
The 95% Rule is one sentence you paste into your prompt. That's it. That's the rule. Copy it, paste it at the top of whatever you're about to ask the AI, and watch the whole conversation change.
Interview me until you have 95% confidence about what I actually want, not what you think I should want.
Why it works. The default behavior of every chatbot on Earth is to assume it knows what you want and start producing. The 95% Rule flips it. Instead of generating, it asks. Instead of guessing, it interrogates. You go from "AI gave me a thing I have to fix" to "AI made me sharper before it produced anything." Free upgrade. Use it on every serious prompt.
Where to drop it
Paste the 95% Rule at the very top of your prompt, before you paste in the brain dump from the seven questions. Like this:
[95% Rule sentence] Here's my brain dump from Prompt Zero: 1. What I'm actually trying to accomplish: ... 2. Why this matters: ... 3. What "done" looks like: ... 4. What "wrong" looks like: ... 5. What I already know that I haven't written down: ... 6. The pieces: ... 7. The hard part: ... Now, before you generate anything, follow the rule above.
The 95% Rule on top sets the behavior. The seven-question brain dump underneath gives the AI the raw material. Together they turn a chatbot into something that actually thinks with you instead of at you.
Okay but why use the app then?
Fair question. Honestly? Because a piece of paper doesn't beep at you. The app has a timer, saves your sessions, and lets you go back and see what past-you was actually thinking before present-you got smart about it. It's the questions plus a little structure plus a little accountability. Same medicine, easier to swallow.
But if all you ever do is read this page, copy the seven questions into a note app, and use them once before your next big prompt, I've still done my job. Go forth. Prompt better.