Still arguing with AI over a bad first draft? Try these 4 tips
13 minAudio
Do you still have a prompt formula saved somewhere, maybe an acronym from an Instagram reel that promised better answers from AI? You paste it in, swap a few words, hit send, and what comes back still misses the mark. Years of typing a few keywords into a search box have shaped how we talk to AI, and that habit might be costing you time and patience. In this How I AI episode, Neo and I look at why prompt formulas took off, what has changed since, and how to brief AI so you get better work back with far less back and forth. What you’ll learn: Why prompt formulas became so popular, and why they matter far less now What AI memory changes about the way you brief it The old search habit that quietly works against you A better way to give AI the background it needs How to get AI to question your idea, not just your draft Practical AI tools for productivity and focus Real-world AI workflows used by high performers How to use AI at work without burning out Smart shortcuts for managing time and mental load Connect with Neo Aplin on LinkedIn (https://www.linkedin.com/in/neoaplin/) and via inventium.ai (https://inventium.ai), where he leads Inventium's AI training and upskilling work with organisations and teams. Find out more about Inventium AI’s training programs at inventium.ai How I AI with Dr Amantha Imber and Neo Aplin explores how high performers are using AI at work to boost productivity, make better decisions and reduce overwhelm. Want more practical ways to put AI to work? You can now follow How I AI separately on Spotify or Apple Podcasts so you never miss an episode. My latest book The Energy Game is out now. You can order a copy here: https://amzn.to/48ID29M Connect with me on the socials: Linkedin (https://www.linkedin.com/in/amanthaimber) Instagram (https://www.instagram.com/amanthai) If you are looking for more tips to improve the way you work and live, I write a weekly newsletter where I share practical and simple to apply tips to improve your life. You can sign up for that at https://amantha.substack.com/ Visit https://www.amantha.com/podcast for full show notes from all episodes. Get in touch at amantha@inventium.com.au Credits: Host: Amantha Imber Sound Engineer: Martin Imber
Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.
Transcript
From the show. Tap a time to play from there.
Speaker 1Do you still have one of those prompt formulas saved somewhere? Maybe some acronym, an Instagram reel, swore would get you better answers from AI. And maybe you still paste it in, swap a few words, hit send, and what comes back still isn't what you wanted. Part of the trouble is that most of us still talk to AI the way Google trained us to. A few keywords shouted into a box. Today,
Speaker 1Neo and I look at why those formulas caught on and what has changed since, including how memory now fills in some of the gaps for you. And today, you're going to learn how to brief AI properly, what to ask it so it shows you better options, and how to get it to challenge you right down to whether you should be making the thing at all. By the end of today's show, you're going to have a simpler way of talking to AI that gets you better work
Speaker 1back with far less back and forth.
Speaker 2Welcome to How I AI with me, Dr. Amantha Imber and Neo Applin, head of Inventium AI.
Speaker 1Each episode, we share one practical way to use AI better at work and in life.
Speaker 2No fluff, no tech jargon, just things you can use straight away.
Speaker 1Prompt formulas used to be really, really big in AI in like 2023, 2024, maybe marginally in 2025, where, you know, there were all these fancy acronyms that we had to remember that the Instagram influencers were telling us in reels to apparently get better output from AI.
Speaker 2So, I mean, why did we have, like, why was there such a focus on prompt formulas, Neo?
Speaker 3They were cool. Everyone had one and I wanted to collect them. No, I didn't want to collect them all. I found it very difficult to remember. Did you? It was a prep, edit or goal. I can't remember all those different things that they had for these acronyms. Yeah, the reason was first off, these were pretty early models. They were pretty good. Like if you look back to AI a couple of years back, they were pretty good, but they were not as good as what we have today. And so people were trying to find a way to get the model to actually work with them in a way which was a little bit more reliable and actually
Speaker 3would actually be better. And so each of the companies and different people had different ways to be able to tell AI what we wanted. But it was a flawed perspective in a couple of ways. One was what we were trying to do was send it one command, a magical command, this big long prompt that had all the words in it and all the things. And then it would be like an abracadabra. It would then open up the thing and then suddenly you'd get a great response
Speaker 3from AI. And maybe that was the case for the day. And I don't think it was really... true, but I think a lot of people felt a lot of comfort in that I've got this magical thing called AI. I'm not really quite sure how to talk to it, but here I've got a formula. I'll just grab the formula, change a couple of things and then send it and then it will be great. And that's where the kind of reliance came from. And it does make sense. We're all getting used to it and people wanted to find their way through it.
Speaker 1So what has changed so much that really these prompt formulas are really don't matter in the way that they did previously. So what are the big changes that have happened?
Speaker 3The first is that these models have gotten better. So the AI companies, Anthropic and OpenAI and all the others, they've done a better job with these models. And the models are better at understanding what you really mean, not what you say. The problems that we as humans have are we're really lazy with our language. And so AI can But earlier, it was very literal. And so it would go, oh, you want this? And then you go, no, it's not really what I meant. It's what I said, sure, but it's not what I meant. Now, AI has a
Speaker 3much better understanding of what good looks like. Sometimes it has a better idea of what good looks like than what we do. And so then it can kind of read between the lines. And there is really the big benefit of it. So rather than us having to teach AI what good is, because they've elevated their models, they've something a lot smarter than they used to be, AI, and here's actually probably a problem, is AI thinks it probably knows better than you do in a lot of ways. And so we don't need to use magical phrases or
Speaker 3cut and paste major prompt libraries to be able to get a pretty good output out of it.
Speaker 1So Also, memory, I believe, is something that has changed as well that impacts on how we have a conversation with the AI in a way that gets us really good output.
Speaker 3Yeah, I should have mentioned that. That's the other part. So the memories in these models, AI does know a fair bit about you. It depends on the different tools you've got. There's different types of the memories there. But in a broad kind of framework, Think about AI having a little notebook about you. And it's about three pages-ish of notebook about you. And it depends on the different models as to how they do this. But generally, it's like who you are, what you do, what you're generally working on. And it does really like to know about
Speaker 3the things that you care about. So if you think like your children, your dogs, your pets, your hobbies and passions, it certainly likes to scribble those away. also how you try to talk to it. And then it starts to get an idea of the human that it's dealing with so it can more likely personalize things for you. And so it's then kind of guessing based on your role, your job, what you've done with it before, I got an idea of what you're trying to achieve here. So it'll help you do it again. So you don't have to be as explicit. But then again, I'd also argue
Speaker 3that can be a bit dangerous because Just because I did something once or I've worked in a particular area doesn't mean that I'm going to do that kind of thing again in the future. And so I find the memory is a bit of a two-edged sword. For most people, it's magnificent and you don't have to prompt as hard with those magical prompts because it already kind of understands what you're after. But if you're doing lots of new or different things, then how you worked yesterday doesn't help you today.
Speaker 1So given all these, given all these changes, how should we be prompting AI now?
Speaker 2What's the best way to have a conversation with it? All right.
Speaker 3I'm going to give you four tips. Tip number one, we've got to forget what we've learned from Google. Google's great. Don't get me wrong. Love Google. Google's awesome. But what we've learned from Google over all of these years is I will shoot it a, I call it a caveman phrase of keywords. So it might be a best washing machine 2026 or something like that. And then you'll get a pretty crap response. And so you might go best washing machine, family, grass stains, 2026 or something like that.
Speaker 3And so we did like yelling at our AI at Google and we've got like four or five words and then we'll get this response back. Now I do all the work here because I'm hitting another word. I've got to read another eight pages and all those kinds of things. And what I found watching people is they will effectively put a couple of words around their Google phrase and give that to AI. So it's the equivalent of what is the best washing machine I should get for my family in 2026? It's still pretty the same thing, you know, and people do shout their commands at AI, which is write me a report that does blah. And of course,
Speaker 3then you get a report and then you go, that's not a good report. That's a terrible report. And then you're arguing with your AI and you're spending a lot of time and energy of your emotional energy and also tokens as well to be able to get it. So instead, tip number two, tip number one is forget what we've learned from Google. Tip number two is treat it like a consultant. So you can imagine any of the kind of consultant you would love to be able to hire. They can be $ 3, 000 a day consultants if you want to. When you bring someone into your business as a consultant,
Speaker 3you won't just go, write me a report or give me the analysis. Instead, you'll be going, okay, so here's what we've done before. Here's what I'm going to do. Here's where I need to go. What are your thoughts on this? You're going to have a conversation. do the same thing with AI. And so use direct natural language. This is where you and I always recommend dictate to AI. You're more likely to deal with it like a human by giving it the background, the context, what you're trying to do, what you've done before, all of those kinds of things. And if you're dealing with it like that consultant,
Speaker 3you're more likely going to give it more background, more context, and help it to understand what you're truly after.
Speaker 1And I should clarify, by dictate, you don't mean be a dictator, but press the little microphone button that is in all the major AI platforms. It's so much easier to speak these things than type these things.
Speaker 2Sorry, Neo, continue.
Speaker 1What is tip number three?
Speaker 3Or just on the treat it like a consultant, I would also give a consultant documents. And so rather than just say, do this thing, give it the background, the context in a document. Say here, read section five, they'll give you a nice bit of background. We would do that with people, but we'd never do that with Google. And so we've got to start giving it much more background and context, and it does a much better job that way. Tip number three is be inquisitive. So if I've got a consultant, they've got a brain, they're really smart. That's why I'm paying them to come in to help
Speaker 3me with these things. And so I'll go, hey, what do other clients do? What do other industries do? Is that a better way to do that? Can I achieve this in a different way that'll land better for my customers or clients? So being inquisitive, because it can actually show you and teach you ways of doing these things. And you might find there's a better way to get these results you're trying to do and try to get out of AI.
Speaker 2What is the final tip, Neo? Tip number four.
Speaker 3Ultimately, challenge it. So if you're a customer of one of these consultants, Yeah, they'll come in, they'll tell you what different industries and different clients and different companies are doing. But you then have to go, yeah, that's great, but I'm not those companies or that's not my industry. And so it doesn't really apply to me. And so absolutely, when you have this conversation with the AI, say, here's my instructions, what I'm trying to do. Before you get to do the thing, you might actually go, hey, what a better way to do it. And it might come
Speaker 3up with something and you go, that may not land for me. There's something you need to look at and kind of really judge if you'd like, is that right? And if it's not right, challenge it and tell it why it's not right so it can then understand what's not right. And so this way, you're not just accepting it, you're more likely going to understand or get it also to understand what you're trying to achieve. Another part there is also get it to challenge you as well. So I get mine to challenge me not only just on how I can create the thing, but also should I
Speaker 3be even creating that thing in the first place? Are there even better ways to achieve that? And so get it to challenge you as well as you challenge it when it gives you the response back or the document or the output or the research or whatever it is, and you'll find that you actually get a much better result. But ultimately, out of those four tips, it's really deal with it like a human being insofar as... It doesn't know enough about you. You've got to brief it. It can do a good job. It could also misunderstand things. You can learn from it. It can learn from you.
Speaker 3But ultimately, you are the customer of this. And so it's got to make sure it lands with you. So check those things off.
Speaker 2Amazing. Thank you for sharing, Neo.
Speaker 1And hopefully our wonderful listeners have got some very practical tips to talk to AI, perhaps in a slightly different way today. Thank you so much for listening to today's episode of How I AI. If this show got you thinking about how you could use AI better, that is exactly what we help people do at Inventium AI. We run AI training programs for organizations and also for individuals. So if you want to upskill your entire organization or
Speaker 1maybe just yourself, you can find out more at inventium.ai. Hey, and once more favor before you go, if you've got a moment, like just five seconds, I'd love it if you could leave us.
Speaker 2A review and hit follow wherever you're listening.
Speaker 1It really helps the show reach more people and it helps us create even better episodes for you.
Speaker 2Thank you so much for listening and we'll see you next time on How I AI.
Speaker 1How I AI was hosted by me, Amanda Imber and Neo Applin. A big thank you to Martin Imber who does our sound editing and Jem Rubio for production support. And thank you to John Kilby who composed the theme music.
Think about how many useful conversations you have in a week. Now, how much of that advice do you actually remember? Chris Hutchins, host of All the Hacks podcast, started wearing an AI device that transcribes his...
**Join the AI Mastery program here: https://www.inventium.ai/ai-mastery ** You built an AI skill, tried it once, and it was brilliant. Then you ran it again and got something completely different, or handed it to a...
Saying no to a bad idea takes no effort. Saying no to a good one is where prioritising gets hard. Too much to do, everything feeling urgent, and no clear idea of what to let go of: this is the problem I hear about more...
**Join our AI Mastery program: https://www.inventium.ai/ai-mastery ** You’ve typed the same instructions into AI for the third week running, tweaked the wording slightly, and got a slightly different result again. It’s...
You've spent years collecting frequent flyer points. Then you finally go to book a flight, and somehow the seats you want are never available. Or the points required seem ridiculous. Or you give up and pay cash anyway....