What NOT To Do With ChatGPT: 7 Costly Mistakes Accountants Make

Okay, so what are we going to cover today? Let's start. So we're going to look at really what not to do with ChatGPT. What are the seven big mistakes. And so yes, I will go through seven mistakes, but what I will also do is then show you how to avoid those mistakes. I'll make sure that you are using ChatGPT the right way and I've got some exciting stuff to show you. So I'm going to show you how to fix the seven mistakes and I'm also going to share with you some prompts because I keep getting told over and over again that people love the standard prompts that I create. I'm going to aim to show definitely one, probably two, one of which I use myself. And I love it. It's a really good prompt, really powerful. I think you'll have, I think you'll have some fun with that particular prompt. So, okay, let's look at what are the mistakes people make with ChatGPT and how can we then fix them? So mistakes. The first one I think people make is they treat it, they treat ChatGPT like Google and this probably isn't you, but a lot of beginners just use it like they would with a search engine. And the problem with that is if you use it like you would use Google, you're going to get real surface level answers. They're not going to be great answers. What I always recommend, and this is, I heard this when I first got into ChatGPT in early 2000. Sorry, 2023. In 2023, someone once said, treat it like your new hire or a junior team member. And I think that's really good advice. I just treat it like another person. So when you are, when you're delegating work, when you're asking your assistant, your junior team member, whatever to do something, then you'll give a reasonable amount of information to get the answer back that you are looking for, which is a very different into, very different to what you might put into traditionally a search engine like Google. So I always think of it as having a conversation with somebody else. In fact, in the AI academy, about a few weeks ago, I posted an interesting chat, chat about or comment about what do people call their chatgpt? And it was one of the most, for a while, it was one of the most, the longest running that it's interesting, everybody sort of caught on with that and started coming up with using a prompt that I put in there, a little prompt, a fun prompt that you can use to come up with what would be a good name for your chatgpt. Mine came up with Nia. Nia. Well, at least it came up with some suggestions, and that was the one I chose. So. So chatgpt is called Nia. To me, I think of it as NIA giving me advice and having a conversation with Nia. So that's my first tip, is think of it as having a conversation with a human, and that will then get you thinking different about how you communicate. And the second mistake, which is very much linked to that one, is using one sentence prompts. One sentence prompts are not going to be very useful to you for most of the serious stuff that you want to do. Yes, it's fine for a bit of fun. For example, if you said, write a blog about tax planning, you will probably get a fairly poor result. I often use the phrase that you've heard, garbage in equals garbage out. If you don't give it a great prompt, you're going to get something poor coming out. So what that means is that when we craft our prompts, we want to add some structure, we want to add some specification. We want to specify, for example, well, who is the audience? Who are we aiming this response at? Is it going to be something we're going to use with a client, for example, or is it just for our consumption? And so that might get us to think about, what about the tone, what about the format? So this is about creating structure, creating some specificity, and this is what we learn in prompt engineering. And I'll talk a bit more about some of the great, some of the ways that we can construct great prompts. And I will show you some prompts later on. And I know some people will be listening on the podcast right now. So when we get to that bit, if you want to see the prompts, then hop across to my YouTube channel and you'll see them in the video. Okay, that's number one and two. Number three, the third mistake is to ask ChatGPT stuff without telling it who you are, who you are. You need to create the more information you give it. And we talk a lot about context. The more context you give, the better the results you'll get. And that includes, well, who are you? And one of the things that you'll find is that when it understands you a bit more and what you are looking for, what you want, then you'll start getting better results. So tell ChatGpt who you are. What is it you're looking to do? Who do you help? And one of the ways that we can do this is in a great feature that came out early on with ChatGPT, which was custom instructions. And so you really need to be using custom instructions. You find it in the settings where you can customize ChatGPT. And the two primary boxes are to tell a bit about you, and the other one is how do you want it to respond? And that particular one I find really important, because if you want to use ChatGPT to create written responses that you might use, that might be, for example, that you want to use it to help you write a blog post, social media posts, write an article, a report for clients, then one of the things that people often complain about is they say to me, Mark, when I get chatgpt to write something like a blog post or an article, it sounds like it's written by AI. And yes, it will. It's got better, by the way, over the years, it's improved. And certainly Claude is very good when it comes to more human like sponsors. And also the latest models of ChatGPT. ChatGPT 4.1 is a big improvement on 4.0, so it's definitely getting better at creating more human like responses. But we can go further than that by making sure we tell ChatGPT about our writing style. How do, how do you write? How do you structure your sentences? What's your tone of voice? Do you like short sentences? Do you want long sentences? Is there any particular word choice that you use? Diction. And we can put this in the customer. And the great thing about custom instructions is you put it in there once and that will apply to all of your chats going forward. So make sure, if nothing else, that you put in your writing style into custom instructions. But also in the other main box, you can put some information about you, for example, if you tell it, who you help, who you serve. If, for example, you're an accounting firm and you serve people in the medical industry, then that means going forward, when you want to write, let's say an article, a blog post, a social media post, it will know that information. And therefore, if in the event you forget to tell it, who is your target audience, it will automatically build that in anyway. So use custom Instructions to tell ChatGPT a bit about you, about your writing style. There are a couple of other boxes in there as well. You can tell it your name if you want. And I did that. And it started now in a lot of the responses, it says to me, hi, Mark, that's a great question. And then it would go on, which I find a little bit irritating. It Never used to do that. So sometimes in my prompts I tell it just to get straight to the point. Okay, that's number three. The fourth thing, and this is a really, really big one, and that is wasting time writing prompts from scratch. Because I said to you earlier, mistake is one sentence prompts aren't very good. We have to create longer prompts, we have to make sure we are very specific. We give it the structure, the writing style, the writing tone and so on. But of course, the downside of that is it takes more time. Just like if we think back to number one, when you are delegating to a task to a junior team member, we all know that the more information that we give to that person, the more detail we give in terms of the what we are looking for them to do, the more likely we'll get the right response coming back. And it's just the same with ChatGPT. We do need to create that detail. But of course the downside is that does mean taking some time. It takes time writing prompts. So let's not waste that time writing from scratch. What we want to do is because your time's precious, you are busy. So let's make sure that we think about what are the standard things that we do regularly, what are the standard tasks, the things we want to do with ChatGPT. And let's simplify the process, let's automate the process, let's create what I call some prompt templates, let's create some pre built prompts that we can use over and over again. And so I'm going to, at this point, I think we'll talk about one of those prompts to give you an example, and then we'll get on to mistakes 5, 6 and 7. So let's imagine that, let's imagine that you're an accounting firm owner and one of the things that you might want to do for your own firm, but perhaps more likely for your clients, is perhaps you want to come up with some ideas for your clients of how they could create some key predictive indicators. KPIs. Every business should have KPIs. And so let's, if we haven't, if we're not sure what KPIs to use, why don't we use CHAT GPT to do that? Or different large language models. So everything I say today pretty much applies if you prefer Claude, if you prefer Google's Gemini, whichever is your preferred. I usually talk about ChatGPT, it's the most common one. And so let's Imagine for your business, you want to, you want some ideas on some KPIs, things that you should measure. And if you are the owner of an accounting firm, this is something you might do frequently because you might want to do this for clients. It could be that you do this for every client, either as part of a business advisory service or just simply to add more value, perhaps once a year, or perhaps as part of your onboarding process. There's lots of ways that we could do this where we advise on KPIs. And so if you're doing this for clients, you don't want to rewrite the prompt from scratch every single time you want to have a standard prompt that you can use. And so firstly, well, where do you keep that prompt? And my advice is you keep it inside a prompt library. Let me show you what I mean by that. A prompt library is essentially a database of prompts. And here is the one that I use. So some people, there are other things that, things that you could use. Some people use notion for there to store their prompts. Some people use Trello, we used to use Trello. Some people use databases like Airtable. But having been teaching prompt engineering for two and a half years now, having been using ChatGPT for two and a half years and using prompts regularly, I did use Trello. And there were a few things I found a bit frustrating that took me a bit of time. So I decided to create my own prompt library because I know the power of this in terms of the time it can save. And so this is, you may, you may be looking at this for the first time. This is something that we are rolling out right now to our members of the Value Python academy and the AI Academy. It's a prompt library. It's a way of managing your prompts. And so if you want to do a task, we're going to look at KPI, we're going to look at creating KPIs. I have one called KPI Creator. It happens to be second on the list. But we're. I could have searched for this in a range of different ways. I could search on the type of prompt. It's a business advisory prompt in this particular case. There are prompts here for marketing, for copywriting, for content creation, SOPs, ideation, and so on. So we could filter down and find the prompts. We could type in. I could type in KPI if I knew what the prompt was called and it's come up. Or I could just filter my favorites. I happen to favorite some that I'M going to show today at least one or two of these. And so we find the prompt we want and I want to create some KPIs and so we click on it and when we go to the prompt, then we can see what the prompt does in the instructions at the top. Most important is the prompt itself. And my prompts are always very long. Why are they long? It's because what I've learned over the last few years about prompt engineering is the more detail you give, the more specificity, the more guardrails, the more you give examples and templates, the more predictable the answer, the better the answer that you will get. And so this is why we take our prompts, the things we do regularly, and we turn them into prompt templates that we can just reuse. Think of these as mini systems. So we have here a mini system to come up with KPIs for any business. And so all we have to do to use it is really simple. We just find it in our prompt library, which we can do through the filters or the search. We open it up, we don't need to read it, we just have to click Copy as markdown to clipboard, which I've done. And that's going to copy the prompt, the markdown version to my clipboard. And then I can come out of this and go across to ChatGPT and I can do Control V and paste this in. And this, by the way, is a prompt that nobody has seen yet because I wrote this one specially for today's session. It's a brand new prompt. If you are in the value pricing academy, you will not have seen this before. It's a pretty cool one. And I'll talk you through some of the things in the prompt in a second and how they overcome some of those mistakes we've talked about. But the first thing I'm going to do is go to the end because what I always do in my prompts to save time, to make it easier, all the prompts are designed so you don't have to do anything with them, apart from add a few variables, which I always put at the end, which means that all you have to do is go to the end and put in a few details. So let me do exactly that. I just need. I can see, I can see. A great question caught my eye. I'm going to come to questions in a bit. So all we do is put in a few details into here. And the one thing I just didn't do earlier was actually write down a couple of these in advance so I can copy and paste. So I am just grabbing a fictional website that I can use and rather than me typing these in. So if I just. If you bear with me a second, I'm going to use a. We'll do KPIs for. Let's do an engineering business. So all I need to do is grab a website of a business. This happens to be a UK engineering business called SaxonEngineering. And the industry sector, well, that's fairly obvious. It's engineering. Okay. So we can. That's all we need to put in. If I just go back to the start. So there's a few things that I'm. I won't go through everything here, but I want to pick up on a few things. So it starts off with the role. What role do we want chat to be? To play. To chat to be. To play. And it says you are a performance analyst with expertise in identifying and evaluating key performance indicators for businesses. And we do that because we know that when we give ChatGPT or any large language model a role to play, we tend to get a better answer, the sort of answer that in this case we would expect from a performance analyst. So I always have every prompt I do has a role that I give chatgpt. Then we have the task. And the task is to analyze the industry sector and identify the most appropriate KPIs for client name, client website, and present them in a table format followed by detailed explanations for KPI. So that's the task. It's very clear there. But you'll notice that it's got the variables embedded in it, which means that. And you'll find them in many places in the prompt. So rather than having to go through the prompt every time and put in a new client name, it knows that's a variable we only have to put it in once at the very end. That's the power of variables. It makes it so easier, not easier to use your prompts then. So we have a task and then what I do is very often in prompts, I then break it down into action steps to be really clear. The more clarity you give to the large language model, then the better and more predictable the response. So I want it to identify the key KPIs first and then I want it to create a table and I'm specifying exactly what I want to be in the table. So we can see there's a list here. I want it to have the name of the KPI, how it's calculated, what it measures, why it's important and tips on how to measure it. And then to make it really clear is I then include an example in there of or template, if you like, of the layout I am looking for. And when we're constructing prompts, I found that giving it templates, giving it examples are two of the most powerful things that you can do if you want to get some consistency in the type of output. Particularly important. If, for example, you are, let's say you've got a prompt that creates standard reports for clients, perhaps it's end of year financial review, it could be a report based on tax planning. Then you want to make sure that in your prompt you've been very specific about how you want it to lay out the report. What headings do you want? What do you want to be in the report? Because then you will have some consistency as to what you're going to get. And so all of this here is just giving it the specific response I'm looking for. I want a table first, looking with the six headings. And then I want some detailed KPI descriptions below that. And then just to create some additional clarity, I'm just telling it instructions for use. Replace the variables in curly brackets with the relevant information for each client or industry. I don't often put that in. Usually it knows that they're variables, but specificity is always powerful. Fill out the KPI table with the most appropriate metrics for the client's business and expand the detailed KPI descriptions to give extra clarity, context and actual tips. And then I've got some constraints and goals. In this case, I'm telling it to ensure the KPIs are relevant and also to avoid including irrelevant, obscure KPIs that do not provide meaningful insights. And then we have the variables. So that's the prompt. Let's run it, let's see what happens. And I know I've talked for a bit now, but if we think about how long this is going to take, it took probably 10, 20 seconds to locate it in the prompt library, perhaps 10 seconds to hit that copy to clipboard and paste. The longest bit will probably be putting in the variables, which is simply a client name copying and pasting a website and then an industry. So so far probably takes a minute. And then I hit this button here and ChatGPT usually takes a matter of seconds. In other words, in less than two minutes, in less than two minutes, you can generate a really powerful report of ideas of KPIs for any business, your business. If you're working with clients, their business as well. So if we look at this we've got below is a tailored KPI dashboard for Saxon Engineering based on the needs and benchmarks of the engineering sector. These KPIs help track productivity, profitability and operational efficiency, all critical to engineering firms. So what's it suggesting? Well, project gross margin. It's suggesting and it's telling us how we'd measure that and what it measures, why it's important to show whether projects are priced and delivered profitably. Tips on measurement use job costing tools to allocate labour and materials. We've got engineering utilization rate, we've got on time, delivery rate, rework rate, quote to win ratio. That's an important one for any business that does quotes, revenue per engineer, change order frequency, client satisfaction score, bid accuracy and cash conversion cycle. So we have this wonderful little table with a whole bunch of really powerful KPIs specific for engineering firm owners that we could, if you were, if you're the owner of an accounting firm wanting to add some value or doing advisory work, you would then print this out and then go through this with a client to see which ones they are measuring, which ones they're not and the ones they're not. Do they agree they should be measured and if so, you could then offer to help them measure those things. And then below that we've got more of a detailed KPI descriptions for them. So take engineering utilization rate. It says what it measures the proportion of time engineers spend on billable tasks versus total bill of available hours. Why it's important. High utilization means you're making the most of your engineering team. Low rates suggest overstaffing or inefficient workflows and tips on how to measure require team members to log time daily, categorize time as billable versus non billable, to calculate accurate utilization and so on. For all of those KPIs, we've got more detail as well to help you with measuring them and so on. So within two minutes you've got something really powerful and hopefully now you can start see the importance of why one sentence prompts are not going to give you this. You would not get this from a one sentence prompt. You would not get this from a. You would not get this from a searching on Google in the traditional way, this kind of analysis. So we have to just make sure that we know how to craft our prompts. Okay, let's move on to mistake number five. And mistake number five is ignoring ChatGPT's creative strengths. In other words, some people use it for very limited Uses perhaps just admin tasks. But there is so much that we can do with large language models. I use it every single day. In fact, my team uses it every single day. And I have it on all the time. In fact, not only that, one of my members of the academy in one of our conversations had not thought of the idea of having it open on multiple browsers at multiple times. I typically have it open at least three times, different places. I have two different computers. And I'll have it open on Chrome. I'll have it open perhaps on my desktop version. I might have it open on Safari. And that's because I am regularly using it and multitasking with it. I might be getting it to do one thing on one computer and something else on another computer, because some things take a little bit of time if I'm doing deep research, if I'm creating images. And so I'm often using it for different things. So we should not be ignoring its creative strengths because it can do so much than just basic answering questions or admin tasks. I think its real power is ideation and brainstorming. If you ever want ideas for stuff like KPIs, if you don't know which ones to use, then it's great for doing that. So I recommend that what you do is get into the habit of using it more and exploring all the different ways it can help you in your business. Things like ideation and brainstorming, things like analyzing financial data, things like creating your marketing material. And now we've got, in the last few months, they brought out the brand new AI image generation, which is so much better than the old Dall E3, which was pretty average. There's some great stuff we can do with images once we figured out what are the right prompts to do. So get to use all of its various strengths. Mistake number six, we're on now. Mistake number six is not reviewing or refining the output. So if you are using it to create content, to send to customers, to send to clients, then please do not send the output straight to a client or to a customer. There's a phrase that's being increasingly used, which is human in the loop. And what that means is that we should be treating AI as a tool to accelerate and not replace us. And so we want to make sure that we are using as a tool. And that means you need to provide, you need to add your own professional judgment. If, for example, you were to create a report for a client, make sure you read it first and use your professional judgment. I was using it just a couple of days ago to create a complete workflow action plan and so on for valuing IP in a business. And it did a really good job. But a couple of things it gave me in the advice, I was thinking based on my knowledge of tax and tax and valuing IP, I was thinking I'm not 100% sure that's right. And so I would then go back and ask a more detailed question about that little bit of the advice. And I would specifically ask it to use its search facility and cite the sources. And what I found in two instances the other day was that twice it wasn't necessarily wrong the advice, but there was a better route and once I'd steered in the right direction, it then said, yes, actually you're right, Mark, this would be a better way of doing it. So please do not just blindly rely on ChatGPT. Make sure you review the outputs, refine the outputs. That's really important. AI is not going to replace us just yet. It's a tool to be used, a very powerful tool. But nevertheless, there's some things it can't do. It can't replace us just yet, which is good news. Okay, and number seven, number seven is this. And it's breaching client confidentiality. So we have to be really, really careful about how we use it. We have to be aware of what are the privacy rules, the security rules, Privacy and security. And in particular, I'm guessing many people here are owners of accounting firms, client confidentiality. So you need to be aware of the rules and you need to be aware of what you can do and what you can't do, what you can put into ChatGPT and what you have to be careful about with personal information. And so I strongly recommend that you have an AI policy and you should definitely get clients permission, otherwise you can very, very easily, and I guess many accounting firms are unwittingly falling on the wrong side of the regulation. So let's just be careful about AI. It's an extremely powerful tool. We just have to make sure that we are using it in the right way. So let's look at. I'm going to look at one more prompt to illustrate some of the things that we talked about. And it's one of my favourites. It's a really powerful prompt I've used a few times now and the prompt is this. Have you ever had to, have you ever received a legal agreement to sign? And I don't know about you, but when I look at legal agreements, I find them so hard to read. My eyes start to go get really heavy as I'm reading a legal agreement. But I also know that we should read things and not just blindly sign them. And they could be things like non disclosure agreements, it could be a rental contract, it could be a business contract deal. There are so many different legal agreements that you might come across in your, both your personal life and your business life. And so what do you do when you get an agreement? Do you read it word for word and analyze every word? Which I don't, I have to confess because they just bore me completely. And I also find the way they're worded, I find it so confusing, I really struggle to follow sometimes what the clauses are talking about. So one of the things that ChatGPT is really good at is helping us understand legal agreements. And this is something that is for me a huge, huge time saver. So let me show you what it is. Let me go to the prompt library. And that's interesting. My second monitor just turned off. It's done that before. Which also means I think that I've lost the, I've lost it on the screen. I'm just pulling it back. It's coming, it's coming. We'll get it back, don't worry. So you can sort of see it at the moment on the screen. I believe I just need to change something. Just bear me a second. Okay, I think that's better. I think you can see it well enough. It's not quite as big as I want, but never mind. So we're in the prompt library right now. Let me just close the sidebar. That shouldn't have opened up. I don't need that. So I'm going to go to legal review and execution. And so this, if I copy it to Clipboard, which is the first step, I go across to ChatGPT. I'm going to create a brand new chat. I'm going to put it into here. And then what I need to do is there's one variable, it's really simple. There's two things I need to do. One is the advising party. And so, and this could be you, or it could be you are advising a client, perhaps a client said to you that they are thinking of, in their business is thinking of renting some new premises and they've got this complicated legal agreement and so they want you to perhaps as the accountant, look at it. And so you just put in who is the advising party? Because what Chat GPT is going to do with this prompt is advise one of the parties. Okay, so this is the tenant in a legal agreement. And the other thing I have to do is feed it the legal agreement. So just need to grab that. It was on my desktop, nice and easy to find. And because my second screen has just closed down, which is always annoying, I just have to find it from my browser. So let me just do that. I have somewhere here I have a commercial lease agreement which I am just dragging into ChatGPT. So you should see that. Now this is a lease agreement. It's a really long agreement with loads of clauses. I think it's about a 12 page or if not longer document standard lease agreement. So what this prompt will do is if we go to the top, we have it that we have the role and that is you are a legal expert specializing in contract law with a focus on ensuring that all legal documents are thorough, clear and properly executed. So we have this role first. We wanted to play the role of a legal expert because we know that we'll get a better response as a result of that. Then in the task, the task is to conduct a comprehensive review of the attached legal document, ensuring that all amendments, addenda and appendices are included and correctly referenced, verifying signatures and execution and documenting any verbal agreements. Important note, you are acting for advising party. You must conduct your review as advice for advising parties. So in this case, I just put at the end the tenant. It could be that you put in your client's name. It could be whatever. It might well be whoever you are advising. And that would be you, if it's from a personal point of view, you perhaps had something to sign as a document and you just want to make sure that you're okay to sign it. So you just might put me or whatever it says as you in the agreement, just for clarity. So then we have action steps because one of the things that's good with, with prompts is you can get to create better result if something's a more complex task. Break it down into the actions. Chat GPT will follow the actions. So I want it to firstly summarize it in simple plain English so it's easy to understand to a layperson like me who doesn't understand these agreements. And then I wanted to list any potentially onerous clauses that may adversely affect the advising party. So I'm not, I don't care about onerous clauses for the other party. I'm just looking, I'm just advising in this case, the tenant and items that are vague that the advising party should seek clarification on from the other party. And unfair clauses. Consider each item of the agreement elements and I'll come on to that in a second. For each, where appropriate, suggest a fairer or clearer clause section the advising party could propose by way of amendment. And then it says conclude with other advice considering each item of the further advice. So we're being, this is not a one sentence prompt. As you can see. We're being really clear here. You can see that advising party is used several times in this prompt. And what we don't want to have to do when we use these prompt templates is go and fill that in in every single place. That's why we use variables. It saves us huge amounts of time. And then what we can do is in this case, I've got the agreement elements. So I'm being very specific here as to exactly what I want ChatGPT to look at in the contract. I want it to make sure it understands the parties that are involved. I want it to review the purpose and the scope. I want it to examine key terms and definitions, check the obligations and responsibilities. I want to assess the payment terms, if that's applicable, identify potential risks and liabilities, check out, check for termination clauses. We should always look at the termination clause in an agreement so we know how we can get out of it. We want to review confidentiality and non disclosure. We want to examine dispute resolution mechanisms, evaluate any non compete or non solicitation clauses, assess intellectual property rights, look for automatic renewal or evergreen clauses, review governing law clauses, consider any penalties or damages clauses, check for compliance with relevant laws, seek clarification on ambiguous language. So these are all things that if you're reviewing a legal document, you should consider all of these things. And so we want to make sure that in our prompt we are being really specific. We are telling ChatGPT we want to look at all of these different areas. And then we've also got a section on further advice, what we want it to do. We want it to review amendments and appendices, seek expert opinion, verify signatures, document verbal agreements and so on. And then we have the variables. So it's a long prompt. Why? Because we're going to get a much, much better answer. So let's see what it does. Let's hit this button here. It's going to analyze this commercial lease agreement. It might take a few seconds because it has to read it. Yep, reading documents. Okay, that was fast. It's a really long document, but it read it pretty fast. I would have probably spent an hour reading it and still wouldn't have understood it. So now it's telling us, it's read that and it's telling us a plain English summary. This lease allows the tenant to occupy and use a property for warehouse and power generation. It started on December 1, 2013 and was set to end in 2020. However, the tenant has the right to renew it and so on. So we have a nice. I can understand that. So that we've got a nice little summary of it. Then what it's doing is going through critical issues and suggested changes. So we've got potentially onerous clauses. I think this is a US based one. So I don't understand all of this. But real estate taxes, the tenant must pay all property taxes, assessments. It then suggests a suggestion, asks for a cap or cost sharing. So it's picking up on all sorts of things we should look for that could be potentially onerous with suggestions on what to do. For example late rent fee, a 5% penalty after just 10 days, request a grace period extension to 15 days or reduce the fee. So these are all great ideas that we could then use. If we're still negotiating, then it's got vague or ambiguous provisions. So areas where we might want to seek some clarification. So landlord controls, insurance, trust fund and approval of architect. So the clarify by saying the tenant should have equal say in selecting the architect and managing proceeds. We have unfair or imbalance clauses and we've got a number of those options to purchase the assignment, the landlords, title warranties and governing laws. And we could perhaps then the suggestions then for what we can negotiate. Then we've got our further advice and checklist, review of the things that we should consider doing, seeking further advice and so on and then we've got a summary. So I think you'll agree that's a pretty good, a good review of this particular legal agreement which is very long and it just saves me so much time because I can't be bothered to read these things. In fact, I've just been sent one today. It's only a non disclosure agreement I've been sent. They're usually fairly straight, straightforward. I've never come across one with yet with onerous clauses. But I'm going to run it through this and get ChatGPT to review it as my lawyer and tell me if there's anything that I should think about before I sign this NDA. Okay, I'm hoping now that you've. You can now see the power of creating better prompts and also of having a prompt library. So we're going to come on to questions in A second. But how can you get access to this prompt library? If you're interested, if you'd like to get the prompt library, the software and the prompts that are in it, then you can either become a Value Pricing Academy member. That's one option, but that's not the only option. The other one is to just make sure you are part of the AI Academy. If you are interested in Learning more about AI, learning more about ChatGPT, learning more about prompts, then join me and many other professionals in the AI Academy. It's a very small monthly investment. I'm going to ask my team, Sarah to put in the chat the link to the AI Academy so you can go and check it out when you come here. You'll see it's a small monthly investment. Just so you know, and this is really important. By the end of this month we are putting the price up. It's going up. It's currently a special, It's a specially founder member offer. We only launched it a couple of months back. It's a founder member offer and that means that if you join now, you lock the price in. The current price will never change, but it is going up later on this month. So what do you get access to when you join? Well, you will get access to firstly a classroom full of my training on Chat GPT. There are many training courses. I have a new one that I'm going to be doing just in the next week or two on how to create SOPs for your business with all the prompts, step by step, how to systemize your business or any business. That's the new course coming very soon because members requested that. But existing ones are things like my prompt engineering course. I have a complete course on privacy and security which includes a suggested AI policy and how to ask permission from clients. I have the my AI image generation course if you want to learn how to use that, if you want to write custom GPTs, if you like the idea of AI agents, then I teach how to build custom GPTs. My most recent one is mastering chat GPT projects, which is my favorite feature inside chat GPT. And I teach you how to build projects and I teach you that it includes the prompts you need to build project files and project instructions really fast. And there are new courses coming every single month. So if you want to learn more about AI, then you want to join the AI Academy now, while the price is the founder member offer and then in the community you can ask questions. You'll also see when I'm running live events like you can see right now where it says live. But you can also ask questions here. I will answer your questions. It's a great community. There are some wonderful people in here. Some people I know watching now, like Rick is here. I did see earlier, Randall's here. I know Randall is always sharing great stuff that he comes across. He's a very active member of the Academy and many, many more people. And last but not least, I have just posted. Here's the post here. Let me just click on it. The prompt library. I am today rolling out that software to AI Academy members together with the prompts that are in it. And if you want to access that software, then when you join the AI Academy, go to this particular post that I've just done. Watch the video where I just tell you a little bit more about what to expect, what the software does, how to use the software, so on short little video. And you'll notice if you join right now, it does say that the link to request access the software is being posted at 1:00pm Eastern Standard Time today. In other words, in about an hour's time, we will post here the link. So if you are joining the AI Academy then, or if you're in the AI Academy, you will find the link. The link here. Okay, that's that. Right? I'm going to answer questions now. Let's move across because I am struggling a bit with my screen going down to one of my screens turning off. Anyway, I should be able to fix that. Let me go open it up. And I just heard that somebody just joined the Academy. So welcome to you. Right, let's go to questions. We have 12 minutes for questions and I'm looking for those Qqs. Where was the first question? I think the first question was. I think the first question was actually not a question. I think it was to illustrate two Qqs. What's the result for the B1 G1 poll? But Lisa, we don't know. We don't see who people vote for. Which one? I don't think. Unless Sarah knows. I don't know. Good question. I don't know the answer, but I know. Lisa, you often demonstrate a question with two QQ's. So thank you for that. Right. Where is the question? Randall? Randall, can we bookmark the ones we use the most? Okay, so that's a question about the prompt library. Absolutely you can. And I just need to open it back up again. Where was it? Here we are. Yes. So if you go to the prompt library, then one of the things that you can do is you'll see the little hearts on the right hand side. You can favorite unfavorite. So the way I've been using it, I personally, I'm just going to turn those back off again. You can favorite things and unfavorite things. So if I just get rid of my favorites filter, I can see all of them. If you decide that you really like this hook generator and want to use this regularly, then just hit the heart, the favorites and then at any time you can just filter to favorites and here we go. Here's the hook generator. So yes, Randall, it's really easy. And when you, I know you're in the AI academy already. When you, when you have got your access to it, that little video, I said go and watch that video. It tells you to watch the start here. There's a full set of videos I've done showing exactly how to use the prompt library, how to use all the features. So let's now go to what's the next question I have got. Let me just move that out of the way. Here we go. Next question was Lisa, if you put the client's name and details in, would I not be violating the Data Protection Regulations? ChatGPT is not secure, is it? Lisa? That's a really, really good question. Thank you for asking that particular one. And yes, you have to be very careful. It's why I talked about it with mistake number seven. You have to know what you can put in and what you can't put in. Now one of the things you can put in is things that in the public domain, that's websites. So you can definitely use a website. You can if you want to. That one I showed you of KPIs then. That's why a lot of my prompts, I've got a lot of my business advisory prompts ask you as part of the variable to put in the website. The website is in the public domain and so that is okay to use. But some things that aren't okay to use will be things like putting in. If you're uploading an Excel spreadsheet of financial data, you have to be really, really careful about that information. And for those of you who are in the AI academy, if you haven't already do work through the privacy and security course, because I go through what you can and can't do in that. Next question. How we doing for time? We've got nine minutes. If you're hearing that Ka Ching sound, that's people joining the AI academy. So thank you so much. I would normally say thank You. I would usually read your name out, but I've lost a screen. My screen's gone. Joe says for something like this, would you use 4.0 or 03? Joe, that's a really, really good question. A really smart question. So for those that aren't too sure with OpenAI, with ChatGPT, they've broken their models down into basically two types. They have their GPT series, they call it which wasn't. Which is 4.0 recently 4.1 and they did release 4.5 briefly, which I think I still have access to. And that's their. That's their standard model. And then they have their o series like O3 for example. That's their Advanced reasoning model. And then I have deep research. And so you do need to know the strengths and weaknesses of the different models because you would use them for different use cases. Most of the time you'll use GPTs. The GPT 4.0 or 4.1 is good for most things. Advanced reasoning, like O3 is the sort of thing you would use for coding, which I guess for accounting professionals is less important, but anything else where there's more of a thought process required. So a good example would be financial data analysis. O3 would often be better, but my advice would be that if you aren't sure, test out the prompt in both and see which one you like the best. That's the best way to find out which one you're starting to like best. You'll start to see that the sorts of prompts that work better with the GPT series versus Advanced Reasoning. There are some general rules for which ones you use, but I still sometimes find that. Sometimes I find that the surprisingly, the GPT one gives me a better response because it's more easier to absorb. Sometimes the Advanced reasoning is just going too advanced. I don't need it. But for some things it's really, really good. So just test it is my advice there. I will probably do a session at some point in the future if enough people want it on the different models available and look at different use cases. So if people want that, I will do that session. We do have six minutes left. Let me see if I can get through all the questions. Randall says, what do you think of ChatGPT5? It's supposed to have stronger logic and reasoning, plus it picks the best tool for the job automatically. Randall I don't know because I didn't know it was out. I'm not even sure it is out unless you talk about 4.5 and I don't have it anyway, partly because unfortunately being in Europe we tend to get things a bit later. There was a couple of announcements just last week from OpenAI of some new features. Now they are only for the Pro account, but it specifically said that if you're in the UK or Europe you can't have them yet. So unfortunately sometimes I have to wait. If you've got it Randall let me know and I will find out when I'll get it. But I always get things a bit later. Will this live meeting be available for later reviewing? Yes it will. All my live streams are livestream to my YouTube channel and they stay there and also some of my live streams. My team then edit them and re upload them as a video without the general chitchat at the start and the questions. But certainly the live stream will be there for you to catch up anytime you want. I think somebody must have asked for the link for the AI Academy, so Sarah did put that in. I'll just put it below as well. Richard, does uploading that draft legal agreement have confidentiality issues as it has names etc. In the document? Richard, again, great question and similar advice to what I said to Lisa is do make sure that you know exactly what you can and you can't do. Also, it depends to an extent on your AI policy. It depends upon what country you're in. It depends on what professional institute you're in because they all have slightly different views on what you can do. But most important is think about getting client permission. And in my course I give some suggested wording that you can build into your engagement letters. And I would definitely do that. You should. You should definitely make sure that's in your engagement letters about your use of AI. And that's critical because putting ChatGPT aside for a minute is pretty much I would guess that you have a tech stack in your firm, including the likes of QBO for example. Well, I think pretty much every single piece of tech now has AI built into it. So even if you're not using ChatGPT, you have to have an AI policy and you have to be getting your client's permission to make sure you are doing that. Please. But if you are doing that, then it comes down to it just come down to clients permission and also it also comes down to what information are you uploading. So the illegal agreement, for example, if it's got the client name in client's address or whatever, you could redact it. If it's a Word document you could just delete it and that would Be perfectly fine. That would be the safest thing to do. So, Richard, thank you for that question. That was a great one. It is an important issue. I'm glad that more people are now raising that issue of privacy and security because it's something I think people skip over and you shouldn't. That's why I did a course on it. Thank you, Randall. He says for $47 a month it's worth it even if you're already in the vpa, which again, Randall, is. So thank you for that, Randall. And remember, it's only $47. For just a little bit longer it will go up. So make sure you lock in the price. Don't miss out on the founder member offer. Have you picked which of those in the poll you are going to do? Oh, Randall, is that the course? Yes, I ran a poll, what, four weeks ago, Randall, asking people what they want me to what they want to learn next. So I've done that a few times now in the AI Academy. I've done run a poll because I want to make sure I'm teaching you the things that you want to know. And I gave four choices of what you would like me to teach. And I think, Randall, last time I looked, I need to double check. I think the last time I looked, Randall, it was actually, I think it was a three of them. It was a tie, wasn't it? I need to check if there's a tiebreaker. But regardless, anyway, I've made a decision on which one I'm doing next. I've planned it and I'm starting to film it this week. It will be ready next week because so many people wanted me to teach them how to use AI ChatGPT and standard prompts to create their SOPs. In fact, I wrote one today which I think is really cool. It's a really long prompt, but it's a great one that helps you to analyze the systems in your business and tells you which one to work on first. And there's a reasoning process that goes through. It's quite cool. And for those of you who are wanting to move up the value curve in your firms and offer business advice to your clients, then I think this whole area of creating SOPs is so valuable not just for your firm, but for any business and accounting firm owners can add huge value and charge good fees for helping clients put systems in place. So that's the new course, Randall, coming your way to the AI Academy. I think it'll be next week I upload it and then I'll be Working on one of the other ones that was in that poll, I guess. How are we doing for time? We've got one more minute. Which question shall I answer next? Brian, are VPA members automatically AI Academy members? No, you're not, Brian. AI Academy is separate. It's a separate business. It does different things. So yes, we cover a lot of AI stuff in the Value Pricing Academy, but if you do want the benefit of everything kept in one place and some of those courses are. May contain some things that are brand new that aren't in the Value Pricing Academy, it's up to you. It's up to you, Brian. But I know that a lot of Value Pricing Academy members are also joining the AI Academy now as well, whilst it's still a really low monthly investment. So that was Brian and I think that's. Yeah, that was Brian's question as well. That's what I thought. Randall, you were, you were. Yeah, I didn't think. Sam Altman said this summer. I don't know when it's coming out. I look forward to it. I believe. Lisa, my VAT is rusty. No, It's a flat 47. It's a. Oh, I don't know. I don't know. I do know that the vat's handled by school. We use school as a platform and I can't remember. We can find that answer out if you email Lisa, if you email Sarah on support. I'll find out the answer for you supportally pricing academy.com and I'll find out the answer. Randall says building your prompt library has 10 votes at the moment. Does that mean it's gone ahead? Right. If that's the case, I will be doing that as well soon. Okay. Hi there, Heinrich, Good to see you. Just seeing your comment. Right. We are out of time. I said we have a hard finish at 5:00.00. If you found something valuable in this session, please let me know by giving it a thumbs up. I would really appreciate that. And also as I play out with some music, also please let me know in the comments what is, what's the best thing you've learned today. I'd love to know. I'd love to get your feedback. Also, if there's anything else that you specifically would like me to teach, let me know. I haven't yet planned the subject of my next live stream, but if there's something you particularly want me to cover, then I love getting feedback. Let me know in the comments and I will see you all soon. Bye for now. Yeah, planned the subject of my next live stream, but if there's something you particularly want me to cover, then I love getting feedback. Let me know in the comments and I will see you all soon. Bye for now.