Strategy A Lay Person’s Guide to Using AI Elizabeth Holloway Strategy 8 mins read August 4, 2025 Blog Strategy A Lay Person’s Guide to Using AI Table of Contents What you need to understand about generative AI So, how do you get generative AI to do what you want it to? When in doubt, ask AI What about all those pesky “AIisms”? What’s the takeaway? Share This Article Facebook Twitter LinkedIn Email We’ve all seen it before, generic and obviously AI generated content that starts with “in a fast-paced digital landscape,” and is full of all those words AI loves to overuse and abuse. It’s led to constant callouts and gotcha moments in comment sections all over the web. But the biggest reason so much AI content sounds the same is because most people are still struggling with how to effectively use and prompt generative AI. So, I’m here today to give you the non-tech-bro lowdown on how to get AI to actually do what you want it to—no technical know-how required. What you need to understand about generative AI We at Third Wunder have been doing a lot of experimenting with generative AI, trying to see how we can adapt and integrate this new technology into our workflows. This has involved a lot of trial and error and not a small amount of frustration. But the biggest takeaway from all of it is this: AI is both very smart and very dumb. Let me explain. AI is able to compute what would take you or I several lifetimes to get through in a matter of seconds. But at the same time, it doesn’t have our instincts or ability to make cognitive leaps. What that means is AI does not do nuance and it takes everything literally. So you need to be painfully specific and detailed in how you ask it to do things. Sort of like the children’s book character, Amelia Bedelia (pictured above), if you don’t give AI the right context or leave it to its own devices, you’re not going to be happy with its output. So, how do you get generative AI to do what you want it to? By now, you’ve probably heard a lot about prompt engineering. When generative AI first hit the scene, a lot of hay was made out of the idea that prompt engineering was going to become its own discipline. This, like many things in tech, soon fell to the wayside as newer, more sophisticated models have come out. That hasn’t stopped people from talking about it. One of the more persistent schools of thought from the early days of AI is the notion that you have to create the perfect prompt all in one go, almost as if you only get one chance to get it right. That couldn’t be further from the truth. In fact, the more you ask AI to do in one go, the less likely you are to get something you’re satisfied with. Which is why the most effective way to prompt AI is in the form of a conversation. Think of it like briefing a freelancer. You want to be clear about the type of work you are asking for, as well as giving the AI pertinent information like your goals, intended results, and target audience. If it’s content to be created, give it the necessary parameters like length, tone, and style, as well as examples of similar work. The more context the better. After that it’s all about refining. Having a structured initial prompt is good, but the real work is in analyzing the AI’s output and asking for refinements. It’s a lot easier to articulate what exactly you’re looking for after identifying everything you don’t like about the draft in front of you. What prompting AI looks like in practice As I’ve mentioned, prompting is more of an iterative process where you are in dialogue with the agent you’re using. A lot of my own conversations go something like this: I usually start off with something along the lines of “I’ve been tasked with creating [content type] for [platform]. This piece is on [subject] from [angle/perspective] and is targeted at [audience segment]. Can you help me create an outline? By asking the agent to write an outline or brief, it gives me a chance to see the direction and editorial choices the AI makes and it’s easier at this stage to fine tune it, if the AI is missing key points or you want to go in a different direction with the piece. Once I’m happy with the outline, I get the agent to start drafting the piece itself. Once you’ve got a working draft, the conversation becomes more like a feedback or review session, where you can identify what you don’t like and ask the agent to make changes. Telling it things like “can you add more meat?” or “make it sound more human and less boardroom,” go a long way towards getting output you’re satisfied with. When in doubt, ask AI Another approach is to ask AI to help you create a prompt. If anyone is an expert on what AI can and cannot do, it’s AI. That is to say, if you’re not successful in getting the kind of output you need, the best solution is to ask AI why your prompt isn’t working. This works for two reasons. One, the AI model you’re using will identify any limitations or obstacles it’s bumping up against (like your ask exceeding its memory limit). And two, this frees you up to more easily articulate your big-picture needs without getting bogged down with all the minute details. This is also an excellent exercise if you’re not entirely clear on what it is you need. It’s sort of like playing 20 questions, where at the end you have a clear set of directives for what needs doing and how to get it done. What about all those pesky “AIisms”? While getting better at prompting will improve the quality of AI output, it’s still going to have a lot of those telltale signs that it was written by an AI. It’s a bit trickier to fix that. Most commonly, people will do a copyedit of the work and change all those “enhance”, “elevate”, “unlock”, and other overused words. A strategy that we’ve found quite effective in training the agents we use at Third Wunder is to create a document of exclusions. By training our agents on this document, we cut down on the amount of time needed to proof work completed by AI. It’s not 100% foolproof, though. The insistent overuse of em-dashes being one of the tendencies that is particularly sticky, but it does make life a little easier (and our agents more reliable). What’s the takeaway? All it really takes to get good at AI is effective communication, not unlike most things in life. The upside is that AI never gets offended or frustrated with countless rounds of feedback and revisions. And speaking from personal experience, the more you work with AI, the easier it gets to figure out how to ask for what you want. Share This Article Facebook Twitter LinkedIn Email
UX vs Web Design: The Overlooked Difference That Changes Everything Elizabeth Holloway Design 8 mins read July 28, 2025
8 Design Principles That Shape Every Great Visual Experience Elizabeth Holloway Design 5 mins read July 21, 2025
Rethinking AI in Philanthropy: Enhancing Decision-Making and Values Alignment Mohamed Hamad Strategy 4 mins read July 14, 2025
Strategic Storytelling: The New Superpower for B2B Brands in a Noisy World Mohamed Hamad Branding 5 mins read July 7, 2025