Hello and welcome again to Elevated, the podcast helping you build a better kitchen and bath design business through innovation and modernization. I'm your host, Brandy Lawson, and if you want to master AI, this is a key episode for you. In 2022, IBM reported that 35 percent of businesses were using AI globally. More recently, the U. S. Census Bureau's data reflected adoption of AI in the U. S. overall. It's relatively low, with only 5 percent of businesses currently using it. In the industry breakdown of AI usage, construction came in at 1%. Even though the U. S. is still only in single digit adoption, it is likely that number will increase exponentially in the next year or two. But why are the numbers so low anyhow? Obviously, there can be a lot of barriers to embracing innovation. But one of the chief objections I've heard to using the currently available AI tools is, I didn't get anything useful when I tried it. Ah yes, well there is that old adage, garbage in, garbage out. AI is no exception to the reality that you need high quality input to achieve high quality output. The learning curve with AI is to understand how to create prompts that get the desired result. And to do that requires something that hasn't really been absolutely necessary before. We have to reveal and understand our own thinking. Now, don't run away! Granted, the prospect of making your thinking transparent can seem daunting. But, you know, I've got a framework to get you started. And like most things in life and business, this is a skill you can build. Prompt writing, or prompt engineering, is really just breaking down the steps needed to frame out any problem or task. I think the biggest issue is that without understanding or practice We tend to skip directly to the task description without providing the adequate background information and contextualization. The biggest secret here? AI can be your Jerry Maguire. It can help you help it. Let's break down the four steps to successful AI prompt writing. First, tell AI the role it needs to play. By default, ChatGPT and other AI interfaces assume the role of assistant. which might be fine if you need an assistant, but if you're trying to get help with research, need code written, want an article that will get ranked by search engines, or crafting emails to clients about a price increase, being more specific about the role AI is playing is critical to getting the results that you want. Most AI services now have different kinds of GPTs or personas pre programmed for you to choose from. Pick the one that represents the role you need AI to have for the output you need. If one doesn't exist, you can still inform AI with the specifics of the role you're needing to have it improve the output it generates. Okay, number two. Give AI adequate context to play its role. We each have decades of experience and expertise we bring to our thinking and decision making. The more of this information that you can share with AI, the better output it can give you. Feeding in brand voice documents, similar examples of what you want, your values, the company values, articles, or other contextual data can vastly improve outputs. It can be a bit enlightening to think about all of the influences to our thinking process. Consider all the various information sources you might call on in your experience and expertise to perform the task you want from AI and then feed that information in. Number three, tell AI the task you want to perform. This is typically the most obvious step for users, but even an expertly crafted ask isn't going to get you anywhere without those first two steps. If you are a good delegator, you may have this one nailed. If you aren't a great delegator, you may need to think through the various steps in achieving the outcome you want and define your task accordingly. You may even need to break out the steps into separate requests. You can even ask AI to help you more clearly define your task. Okay, number four. Ask AI what else it needs to perform the task. This is the key that unlocks the next level of prompt writing skill. Use AI to tell you how to get what you want from AI. And this sometimes is where the bulk of the work for the human comes in, as AI is a great tool, but it does require high quality input from a human. When you tell AI, ask for anything you need before you start this task, It will kick back a list of additional information it needs or questions to answer. Providing this additional data always results in a better output. Using these four steps, you can build your skill and the usefulness of AI to your business. It takes some practice and iterations, but pretty soon, you'll be creating a prompt library and updating your processes with which personas to use. In the next episode, we'll further discuss upgrading our skills and habits to fully leverage AI and possibly even improve other areas of business and life. Like what you heard? Never miss an episode by subscribing. Head over to listentoelevated. com to subscribe or share with a friend. Everyone deserves to have less stress and more impact.