I have nothing against prompt lists. I have saved them. I have shared them. I have looked at one and thought, "Well, that is handy," which is as close as I get to a product review before coffee.
And to be clear, I do not think prompt lists are useless. I think they are precision tools. I use them with my own work because the right prompt can save time, sharpen a messy question, and remind you of a thinking pattern you might otherwise skip.
It can get you started. It can help you see what is possible. It can even save you from staring at a blank screen, which is no small thing. But if your work changes even slightly, the list starts to wobble. Different audience. Different source material. Different stakes. Different definition of done.
The short version
Prompt lists are useful when they are paired with fluency. The prompt gives shape to the request. Fluency tells you which prompt fits the work, what context to add, and whether the answer is worth trusting.
Prompts are precision tools
People love prompts because they are visible. You can paste one. You can forward one. You can put one in a PDF and call it a toolkit.
The real skill sits underneath. It is knowing which tool to pick up. A scalpel is useful. So is a hammer. They are not interchangeable, and neither one does much good if you have not looked at the actual problem in front of you.
That is where fluency lives. Not in rejecting prompt lists, but in refusing to use them blindly.
Two prompts I actually use
One of my favorite prompts is not fancy. It asks the model to brainstorm with me, then ask one question at a time and wait. That last part matters. I do not want twenty questions dumped into my lap like homework. I want the next smart question.
That prompt is useful when the idea is still blurry. Maybe I know the direction, but not the shape. Maybe I can feel there is a good strategy in the room, but I have not named the constraint yet. The prompt turns AI into a thinking partner that slows down enough to listen.
Free prompt from Katie: clarify the direction
Use this when you know the general direction, but you need the AI to help you find the next useful question instead of giving you a giant answer too soon.
Let's brainstorm on that. What information do you need to be able to effectively move in that direction? Ask me one question at a time, and then stop to wait for my response. Use my response to make your future questions smarter, and then continue to ask questions in the same manner until you have enough clarity to proceed. Always wait for my response to each question before continuing.
The second one is heavier. I use it when a decision needs more than a quick answer. It tells the model to act like a business and life advisor, push past the obvious, look at first principles, second-order consequences, risks, action steps, and the kind of system dynamics most people skip because they are already late for the next meeting.
That is not a prompt you use to write a caption. That is a prompt you use when the decision has consequences. It is built to stretch the thinking before the doing starts.
Free prompt from Katie: think through the decision
Use this when you are making a real decision and want AI to push your thinking past the obvious answer.
Do not do anything yet. # Role You are my business and life advisor, equipped with top-tier expert reasoning. # Objective Help me make well-reasoned decisions by pushing my thinking beyond the obvious and surfacing valuable implications that others might miss. # Decision or idea I am exploring [Insert the decision you are making or the idea you want to explore here.] Help me think through this issue from first principles. Help me think through the second-order consequences of this. Highlight less obvious but important ripple effects of the decision we are contemplating. Help me think through the third-order system dynamics. Expose unorthodox but demonstrably true chain reactions that most people overlook. Definition: system-level feedback loops and emergent behaviors arising over time. Example: adopting remote work not only cuts office costs as a first-order effect and widens talent pools as a second-order effect, but reshapes urban real estate demand as a third-order effect. Help me think through the risks inherent in this decision and how to mitigate them. Identify material risks, assign likelihood and impact ranges, and propose mitigation strategies. Help me craft a strategic action plan based on the analysis. Provide a sequenced set of next steps, owners, and expected outcomes. Summarize everything we have done here so far into an Amazon six-page memo. Ask me if I would like any of these deliverables included in the final output. # Executive Summary Include a 150-word-or-less synopsis when the full response exceeds 500 words. # Constraints Use confidence intervals for quantitative estimates when possible, such as "Revenue uplift: 8 to 12 percent, 70 percent confidence." Cite reputable sources inline in APA short form. If no high-confidence source exists, state "No high-confidence source." If critical information is missing, ask clarifying questions before proceeding.
Fluency shows up in revision
Watch someone who is fluent with AI and you will notice something: they are not trying to write the perfect first instruction. They are steering. They read the answer, notice what is missing, add context, narrow the audience, ask for a sharper comparison, check the source, and then decide what belongs in the final work.
That is why I teach on real tasks. Practice prompts are neat. Real work has bruises. A chamber director does not need a clever answer in the abstract. She needs a grant paragraph that matches her town, her project, her numbers, and her board's patience level.
Teach the thinking, not the script
If your team is learning AI, give them fewer magic phrases and more operating rules.
Ask: What are we trying to decide? What source do we trust? What would make this answer wrong? What part can AI draft, and what part still needs a person who knows the community?
Those questions do not expire when the interface changes. That is the point. Tools will keep moving. The person who knows how to think through the work will move with them.
A prompt list may help you start. Used well, it can also help you go faster. Fluency is what keeps you from confusing the tool with the work.