One of the most useful things to understand about AI is that most of its use cases are an “optimization equation.” In other words, you’re always trying to optimize for something—whether you’re doing product research, building an app, or developing your business strategy. Always tell AI what you’re optimizing for.
To illustrate with a couple of examples:
- Say you’re using AI to research which frying pan to buy. Like with any AI problem, think of this as an optimization equation. Tell AI what you’re optimizing for with the search. Do you want a pan that’s convenient and easy to clean? Do you want the most wallet-friendly option? The “buy-it-for-life” pan that will last decades and not months? Give AI the variables that matter before it researches the best option. Better yet: have it interview you so it has even more context to determine the optimal one—this way you can identify criteria you didn’t even realize mattered.
- Or maybe you’re developing your business strategy. What are you optimizing for? I was doing this the other day (so it’s fresh in my mind). I told AI what I was optimizing for: serving others through my work, while operating a sustainable long-term business (I find these two work hand-in-hand). I asked it to help me iterate on my plan with this in mind. What improvements could I make to it? What blind spots do I have? It helped me identify a few. (Including one project I can drop to have more time to write and research.)
With anything you’re using AI for, you’re trying to optimize for something—and there are always variables that matter more than others. There are usually also constraints which will limit what you can do (like time, money, or tokens).
A simple prompt that integrates all this:
Think of this problem as a “constrained optimization equation”—and interview me to determine the variables that matter most.
Think of everything you use AI for as an optimization equation and you’ll be a lot happier with the results.
