AI Productivity Unleashed with ChatGPT: Boost Efficiency and Dominate Your Day

1. Class Introduction: AI Productivity Unleashed: Hi, there. I'm James. I've spent the last 20 years launching and growing online businesses, and more recently, I led an E commerce team for a European technology start up, which operated in 14 different countries, spanning Europe and South Africa. I've also launched and sold two e commerce businesses, one of which was a seven figure business. And now I'm passionate about helping professionals like you unlock the power of AI to transform the way you do business. This class is all about boosting your productivity using AI. We're going to be looking at the two main language models. Those are Chachi BT and Gemini, and you'll learn how to streamline your workflow using these powerful tools. We'll cover everything from mastering AI prompts to task management, automating content creation, and much more. You'll master essential skills like crafting the perfect prompt, automating repetitive tasks, and improving the creative output of AI. Whether it's content generation, business analysis or time management, I'll show you how to use AI to elevate your daily work flow. You'll also learn how to improve your efficiency, using a tool like Phrase Express. I'm also going to introduce you to some of my favorite AI tools that are going to help you boost your content creation game and generate quality ideas and outputs faster than ever before. This class is perfect for remote workers, business professionals, even online business owners. Anybody who just really wants to leverage AI to be more efficient in their workday. You don't need any prior AI experience, just a willingness to learn and an open mind. By the end of this class, you'll know how to save time, create better content, automate repetitive tasks, and streamline your workflow using AI. For the class project, we're going to get creative and use chat GPT to blend two unrelated topics into a single piece of content. This fun project will allow you to experiment with your new found AI skills. You'll choose two topics, generate a unique prompt and share the results with the class. It's a fantastic way to practice everything that you'll learn in the course. I'm so excited to help you transform your productivity potential with AI. So let's get started and take your productivity to the next level. I'll see you inside the class. Goodbye. 2. Choose Your AI: A Comparative Guide to ChatGPT vs. Gemini: Hi, and welcome back to this lesson. We're looking at the differences of hat GBT versus Gemini. There are some key differences, and we're going to be looking at those. So let's have a look at each of them. The primary focus for hat GBT is generative AI. So it excels in creative writing and content generation. Code generation as well, it's incredibly adept at coding and disseminating and understanding code. And also generating engaging and human like text formats, whereas Gemini is a bit more designed for research and information gathering, leveraging its access to real time data and Google search capabilities to provide comprehensive and accurate responses. So this is one of the key differences with Gemini and ChatBT is that Gemini does have access to real time data, so it taps into Google's extensive database and search capabilities. Whereas HTPT on the free version has limited access in the free version to web browsing capabilities, and this is a topic we're going to discuss next. So web access, previously, ChaGPT relied on data sources trained up to April 2023. That was the cutoff. This is the official cutoff. However, there is unofficial rumors that April 2024 is when the last model was trained on, but it now has browsing capabilities. However, this is only available on the paid version of ChatBT, which is the pro version, as well as if you're using the API. So if you are making API calls to the Open AI platform, you could have access them to browsing capabilities. Gemini aims to provide factual and accurate information, so it does tap into Google's database and extensive data resources, as well as having real time data access, which is quite important. Accuracy, it must be noted that both of these models do make mistakes, so it's always good to fact check and not to necessarily take the responses as gospel truth and just make sure to be aware of that. Accuracy for Chat EBT, it relies on external sources as well as the knowledge database that it has. This can mean if there's a gap between the cutoff date, and the current date, there would be a gap in the information there. So if you're not on a pro plan that is able to access and browse the Internet, there could be a knowledge gap there. But again, the pro version has browsing functionality. Gemini generally performs better as it can have direct access and integrate in real time with Google's data sources. So it does have that slight edge there on the free plan, at least. Integrations, custom GPTs there's an entire marketplace, and this is where you're able to access GPTs that others have created, so they can perform very specific functions. So if you wanted video creation or if you wanted to do it an SEO audit of your website, there are custom GPTs out there that make this available, and they're created by some incredible people, agencies, experts, you name it. There are custom GPTs available, and that's only available on the pro plan of Cha GPT. For Gemini, you have inherent access to all of the Google Workspace apps. So that is Google Sheets, Google Docs, Gmail, all of that, as well as Google Drive. So you are directly integrated with that. However, there are no plug ins at this stage, but it might be introduced in the future. When looking at the price, both are equally matched. Of course, there is a free plan for both of them. And if we look at Chat GBT, the pro plan has the advantage of allowing you web browsing functionality. It performs a lot better, especially in peak times and when there is high load, you're able to still get your responses. Whereas on the free version, you would be throttled and only able to get your responses once the servers free up and have the capacity to do so. The other major benefit is that of custom GBTs. You're able to access all of those on the GBT marketplace. So those are some really significant enhancements and features that you get access to with the P plan. On the paid plan of Gemini Advanced, you're able to have enhanced features, capabilities like deeper data analysis, more complex query handling, and sophisticated content generation. There's also priority support, increased usage limits, so more availability. You can also have higher or unlimited usage caps for queries, API calls, and data processing. So there's a number of key enhancements and benefits on the paid plans for each of these models, so have a look at them and see what feels better to you, what is better suited to your workflows in terms of productivity, both work equally well. I'm a staunch ChachiBT van, and that is my tool of choice. So I use that daily. I love being able to create my own custom GBTs that are trained on my own knowledge and using all of the info and data points that I supply it. So that is a major advantage. I also like having better availability and better performance to know that when I'm putting a query in, it's not going to be limited or throttled. And there is no doubt it completely pays for itself. Just the enhancements in productivity that you get from this is incredible. And with that, we've come to the end of this lesson. In the lessons to follow, we're going to be working on your skill set and how you can improve your prompts and just get more from Cha chibi t or Gemini. But that's it for this lesson. I will see you in the next one. Goodbye. 3. Prompt Essentials - Crafting Prompts: The art of prompting a prompt is how you talk to the AI. It's the instruction that tells it what to do. AI is highly intelligent, but it's not a mind reader. Think of prompts as directions for a virtual assistant. Good prompts equal better, consistent results. Bad prompts equal vague, generic or are totally off from what you expected. By the end of this lesson, you'll know how to craft effective prompts that work every time. You'll learn how to identify bad prompts, write clear specific prompts, and use building blocks for a repeatable framework. Let's get into it. The task. Start with a clear action of what you want, keep it simple and action based. Use action verbs. These are things like asking it to write or explain or summarize or list or reword or translate. Specific using clear direct language. This helps the AI to stay on track, and it avoids it inferring what you might be wanting, which could actually be incorrect. Then one pro tip is to guide the AI on what you do want instead of what you don't want. So by this, I mean, it can sometimes fixate on negative things and include elements of it in the response. So try using positive phrasing instead of saying don't give me a long summary, instead say, give me a concise summary. The role assigning a role is a key part of good prompting. What is a role, though? A role assigns a persona to the responses. So it's able to shape the tone. It's able to give contextual perspective, and it's able to give responses in the appropriate voice. An example of this is terminology that may be used for a specific industry or topic. And this is especially important when you're creating content for your target audience. Think of roles as narrowing down the expertise so that you're able to add the clarity and perspective that is needed for those expertise. It also means that the responses are given back in the appropriate voice using the correct terminology for that industry or expert. Some example roles are things like a customer support agent, where you would say, you are a customer support agent, apologize for a delay, or you are a doctor, list three future health risks based on this history, or even other roles like a teacher or a business or life coach things like that. There is no fixed list of all the available roles. It is up to you to just look at what is going to be the best expertise that you can tap into for a particular purpose or prompt. And we dive into roles and personas in more detail in an upcoming lesson. Building block number three, giving examples. AI absolutely loves patterns and examples. It just shows it how you want it to respond. To do this effectively, show don't tell. So by that, provide one to two examples for complex task to help demonstrate the pattern you wanted to follow. How many examples? Well, one to two is enough. Provide one to two examples for complex tasks. This helps to demonstrate the pattern you wanted to follow. And there's no magic number of how many examples. But generally speaking, one to two is enough for it to get a good idea of what you're wanting. Of course, if you have a more complex task or there's multiple steps involved, then it might be a good idea to include more examples, especially if the context and the request changes through the prompt. So if you have a multi step process and each step is needing a different example, that's where you would add in a few others. Examples are even more important when it comes to complex tasks because they clarify the expectations and they give the AI a very clear guide as to how it needs to respond to you. If we have a look at an example prom, this would be as a copywriter, write ten short, catchy Instagram captions for a fitness brand. Keep the tone motivational but friendly. And example one, this is the tag line we would use. No shortcuts, just sweat, strength and progress. Example two, you don't have to be extreme, just consistent. Now, write eight more captions like this. And from that, the AI can understand the format and the tone that you're wanting. It's then able to do the remaining captions with greater success. Building block number four, the output format. This is where you want to specify the structure and the desired response format. Examples would be write in three bullet points or summarize in one short paragraph or list steps in a numbered order. Next is to set the length. Examples are make it 100 words in length or keep it to three sentences or limit the reading time to 2 minutes. Specifying the output format is also going to save you a lot of time with editing. This means that you can use the responses straightaway and you don't have to spend any more time getting it to how you want it. Building block number five, extra info. This is where you are giving all of the contextual information, all of the relevant data that the AI needs to be able to give you the best possible result. It's important to establish and specify the audience. So who's the intended audience. This will also determine the level of detail and the terminology used and the tone used in the responses. You can imagine, a very technical topic would need a lot of detailed and technical terminology in the response versus something that's a bit more casual and conversational. Tone. This is where you specify what sort of tone you want. Is it going to be professional and instructional or is it going to be casual? Should it be fun? Specifying this in the prompt is an important step to getting it to respond in the correct tone. Then timing, this is where you say, when will this be used and by that I mean, is it going to be a piece of text for a Christmas campaign? If so, it needs to be festive. Maybe you're drafting an email to a colleague working on a project and a deadline is looming, so you want to emphasize the urgency of that, and that needs to come across in the response. So it just helps the AI adjust the tone, the urgency, and the relevance to fit the moment. It's always a good idea to put this extra info and contextual information at the start of the prom. This way, the AI has all of the contexts that it needs and all of the data to be able to follow the steps according to that data. If you think of a machine, it's a very linear process in how it operates. So it's going to take all of that first information and then execute based on that initial information. If you put it at the end, it just makes it more of a challenge for it to incorporate that into your response. This is due to the AI giving more prominence and weight to information that appears earlier in the prompt. Next, we're going to be looking at what a bad prompt looks like and how to improve it. If the prompt is unclear, the result will be, too. So it's a lot like that saying a garbage in garbage out, and this is where you need to give it clear concise details to be able to give you the best response. Let's look at some bad prompts and identify what is wrong with them. The first one, tell me about marketing. Vague, too broad. There's no direction or goal, and just very inefficient. Make this sound better. What's wrong with it? It's missing context, and better is a very subjective term. One person's better might be very different to another's. So it's important to be specific in what better actually is. Then the next one writes a blog post for me. This is inefficient because we're going to have to provide the AI with more information, and there's going to be a lot more back and forth. Whereas if we had provided that information to begin with, we wouldn't have to do multiple passes at. Also doesn't have any topic. There's no link specified, and of course, there isn't any tone seen there. Then a pro tip is to instruct the chatbot to ask you questions to gain more info and understanding. So by that, you can then finish off your prompt by saying, ask me for any details or information to help you better respond. Something as simple as that would work really well. Next, we're going to look at fixing bad prompts. We'll see them before and after. Here we have a few bad prompts, and the first one is tell me about marketing. This is very vague. So a better prompt will be write five beginner marketing tips for small ecommerce stores and use a casual tone. The topic and the context is beginner marketing tips, and we've identified the audience as being small ecommerce stores. So it's going to be speaking their language, and we're also specifying what tone we want and that it should be a casual tone. Make this sound better. That is also very vague. A better prompt would be to say rewrite this paragraph in a persuasive tone for business owners. Again, we are saying what it needs to do. We're giving it some tone directions, and we're giving it some cues as to the audience, which is the business owners. Next prompt is write a blog post. Very vague. This is going to result in a lot of follow ups needed and just extra work, whereas a better prompt is going to say, write a 300 word blog post about time management in a friendly tone. So from there, you can see, we're not going all out and putting in a detailed prompt, but we are providing very specific elements and all of these building blocks into the prompts to get the best possible response and the most efficient one as well. And one thing I've noticed is that most prompts can be easily fixed just by being more specific by specifying the output and providing an example. These three elements alone can fix all of your prompts or at the very least, make them significantly better. So I urge you to try this, and even just these three elements is going to hugely improve your prompting abilities. The key takeaways for the lesson is that good prompts are clear, specific and structured for the best AI responses. Remember to use the building blocks that we learned about here in this lesson. Those are state the task, assign a role, provide one or two examples, let it know what format you want it in. Is it a list? Is it a paragraph? Is it a table, and also to provide the extra information. So the context surrounding the request or any relevant information you feel that the AI would need to be able to respond better. Of course, you are going to sometimes get undesired results, and that's where you iterate. So don't be afraid to refine your prompts, give the AI feedback, give it updates to make, and it will learn from those responses. And most of the chatbots, especially Gemini and Chat CIBT have persistent memory so they're able to understand and learn from the interactions that you have with it, to be able to respond better. More you're prompting, the more practice you're getting and the more it's able to know exactly what you want. And using these building blocks, you're able to get consistently better results. So strong prompts mean you're getting your results faster and the results are better. That wraps it up for this lesson. I hope you're able to see that these elements and building blocks are crucial for getting better results and prompting your way to success. In an upcoming lesson, we're going to look at assigning roles, which is quite an important topic, and you'll be able to see just how to do that more effectively and what options there are for being effective with assigning a role to your AI. I'll see you in the next lesson. Goodbye. 4. Prompt Essentials - Roles and Personas: Going to be talking about roles and personas in this lesson. AI chat bats, like Chachipiti are generous by default. By that, I mean, when you ask questions, you're getting the default version of Chachipit. Their knowledge spans all subject matter, but when you ask a question, you'll get a generic cookie cutter response. It's when you use AI personas that the magic starts to happen. To illustrate the power of personas, here is an article 0N Zi Net. It shows how GBT 4.5 took the Turing test. Now, this test involves a human judge chatting to both a human and a computer. The judge then has to distinguish the computer from the human based on their responses. There were two prompts used. One was a minimalist prompt. The other had additional instructions on what kind of persona to adopt. Responding to the interrogator, specifically a young person who is introverted, knowledgeable about Internet culture, and uses slang. GBT 4.5 had a win rate of 73%, meaning it fooled the human judge into thinking it was a human 73% of the time. So this just shows the power of personas and how you can really leverage the subtle nuances and tone and language of that specific persona. The touring test, it's not a direct test of intelligence, but more of a test of human likeness. And here on the screen, we can see an example of the prompt that was used during this test for the AI to adopt the persona needed to be successful. AI personas can shift the tone, depth, and delivery style based on who they're pretending to be or who they're speaking to, I E, the audience. When you ask the same question, but using an AI persona, the AI won't just respond differently. It also thinks differently. Consider this. Let's say you ask a question of how does a combustion engine work? You'll get a very different answer coming from a mechanical engineer versus a primary school teacher versus a Formula one race car engineer. The teacher might respond with It makes tiny explosions to move the car like magic. A mechanical engineer would say something like it converts fuel into energy through a four stroke cycle. And lastly, a race car engineer would ask, well, it depends. Are we optimizing for toque, RPM, or thermal efficiency? So in summary, when you want to tap into more specialized expertise and thinking, use those specialized personas in your prompts. Because if you're getting very technical responses, but the intended audience is not technically inclined, it's all going to be lost on them. Understanding role prompting. So this is where you want to give a clear direction. Roll prompting is assigning a specific persona to the AI, which means you want to get the perspective and the expertise of that specific persona. Personas are not necessarily needed when you need simple and generic responses. But when you're looking for very specific and very tailored expertise, that's when you need to activate the specialized knowledge, and using roles focuses the AIs approach to this. Also having a consistent voice rolls maintain a consistent tone and perspective throughout complex conversation. So what that means is that it will keep the level of detail. I'll keep the tone, and it'll also use the same thinking and angle based on the given persona. Personas you choose have an impact on the output style. Assigning a role or persona shapes how the AI respond. So it's able to match the audience, it's able to set the appropriate tone, and it's able to adjust the level of detail and the depth of content that it gives back to you. Let's look at example here. Without a role, we're saying, write a review of this new pizza place. And of course, as you can imagine, you would get a result that is probably quite generic, bland, and it just lacks specific expertise and perspective. As if you used a role with that same prompt, so you are a Michelin guide reviewer, write a review of this pizza. As you can imagine, the language would be a lot more refined. There would be technical culinary references and details that only a professional reviewer would be able to know. So this is where you would get a far more detailed, structured and appropriate response. What are some roles to try? Well, there's no fixed list that you can work from. But generally speaking, if you consider domain experts, so people that are considered the top of their field, those are the personas and the roles that you want to use in your proms. So let's go through a few examples here. One would be a copywriter. You could say act as a copywriter or you are a copywriter, but it's always a good idea to tap into a specific role. So looking at an industry, saying you are a copywriter for a B to B sales company, or you are a copywriter for a software company. These industry specific additions that you add there can really make the difference. Some other roles to try, so a content strategist, a social media manager, a web designer, SEO specialist, email marketer, data analyst, customer service agent, or a project manager. These are just a handful of some of the roles that you can tap into and ask the AI to respond as. An example, prompt using one of these would be you are a startup advisor, suggest three quick improvements for a landing page targeting SAS founder. Some interesting results, you could even try using celebrities or famous figures or any well known personality when you are prompting. Some examples could be Shakespeare or some old English style responses or David at Attenborough or some wildlife documentaries type stuff. Or Elon Musk from the perspective of a revolutionary industrialist or technologist or Stephen King, if you're looking for some compelling writing, Gary Wnechuk if you're wanting to tap into a more social media guru type of style or Neil deGrasse Tyson, if you're looking for very technical astrophysicist type of content, you also have Beyonce if you want a more lyric and musical based response, and, of course, Anthony Robbins, if you're wanting to motivate and inspire. These are just a handful of the celebrities and famous figures that you could tap into each one of them having their own unique style that they can bring into your responses and provide a unique voice, tone, and perspective. An example, prompt would be in the style of Stephen King, write a short story about and then you would insert your topic and set in, and there you would set your location. The benefits of role prompting in professional communication are that you can tap into the expertise of certain role. For example, a customer service role would allow you to create an empathetic solution orientated responses. So it would take on that persona of being a helpful customer service agent. If we look at taking on a marketing persona, that's where it would transform negative situations, so the challenges that your customers are having and turn them into positive opportunities with upbeat messaging. And this would in turn help to convert your landing pages or your sales pages better effect. And then also taking on a leadership role, you're able to activate an authoritative role that is clear on communication, and that could inspire action. You're also able to improve the responses you receive by using roles in your prompting. Examples could be maths equations where sometimes AI does struggle to go through all of the complex thinking. So by using a role, you're able to avoid that. The examples here are a math equation, what is 100 times 100, divided by 400 times by 56. Not having a role assigned may lead to calculation errors or it may not follow a logical and mathematical workflow to get to the answer that you're looking for. But where you use a role such as a mathematician to solve that same equation, it would then break down the task and work step by step to achieve the result. And this would lead to more accurate results because it's taken a methodical and logical step by step approach. The difference being, is that you're not asking the standard vanilla out of the box version of the AI, the role prompting, it's going to activate the specific expertise and the patterns and the methodical approaches that those roles would ordinarily take in their everyday work. And you get to tap into that by stating that role or persona in your prompts. Here are a few tips for effective role prompting. Be specific. So this is where you are stating in clear language what you are looking for and the role that needs to be assigned. So like we touched on that copywriter role earlier, an example here is you are a copywriter at a SAS company, and here we're putting in the audience and saying targeting founders. Test variation. So what you think could be the same role or persona, if you vary them slightly, you might get different results. So trying different roles like a coach, mentor or expert, they all fall under the same umbrella, but using each of them separately might yield different and better results. And then, of course, you want to pair the roles with instructions that are relevant to that role. So combine the role with clear tasks, and that would also lead to better outcome. In conclusion, by using roles, you are tapping into expertise of that given persona or role, which has very specialized knowledge, and these responses are going to be tailored to your needs as well as the intended audience. There's going to be better communication, and by that, the tone is going to be appropriate and the style being used is going to be better suited for all of the tasks and situations that you are using role prompting for. And lastly, this is a foundation technique. It's an essential skill for effective AI interaction. So practice your role prompting, try different things and see how you can get the most out of your AIs responses. It's an important step to take, and it's worth getting right because the results that you get are not only going to save time, but they're going to be more effective and better suited to your use cases, as well as those of the intended audience. Wraps up this one. I'll see you in the next lesson. 5. Prompt Essentials - B.R.A.I.N Framework: In this lesson, we're going to be learning about the brain framework. This is a framework that I've used with great success, and I wanted to share it with you. It's very simple in its application, and it has all of the elements you need for those consistent results that you're looking for. So what is the brain framework? Well, it's a set of building blocks that you can use to get to the perfect response. So Brain stands for different words. The first one is background. This is where you are setting the stage and you're providing all of the essential and contextual information that the AI needs to be able to process the request correctly. In addition to providing all of the relevant details and context putting this first, you are doing what's called front loading. This is where you're providing all of the information up front. LLMs, such as Chat ChIP T, they use what's called an attention mechanism, and this is where it weighs the importance of information appearing early on in the prompt. So this is why we're putting it in the front. It's also good because we're framing the entire prompt by giving it the information, so it knows which path to go down and it has all of the information that it needs to process the also want to have a clear problem statement in there. So this is just stating what you are trying to achieve, what you're struggling with, and how you want the AI to solve that problem. Next is R for role assignment. This is where you are assigning a role and a persona, and this is going to influence the AI's approach. So you're giving the AI the perspective that it needs, and it's able to tap into those expertise and just get a whole nother level of expertise versus just the default standard Chachi BT and the responses that that version would give you. Think of it as activating an expert role inside of the chat bot. Next is the action. This is where you state what you want the AI to do, and you're wanting to use clear action verbs. These are things like explain, summarize, compare. Inputs are next. This is where you're providing the necessary information, things like references, as well as one to three examples. Of course, the more examples, the better, but as a minimum, aim for about one to three. And this really just helps augment the background information that you've given. So the background information is the context it needs, and the inputs are the references and examples and any other data points that are relevant to the prompt and the desired outcome. Then next is N for narrowing. This is where we are narrowing down and constraining the focus for the response. So we're adding in parameters, such as the number of words that we want in the response. We're looking at audience identification. We're saying it's for a specific audience, and maybe we're also talking about the complexity level, the level of detail that we want from the response based on the level that the audience is at. Maybe they are at a lower education level or at a higher education level. It all just depends on the topic that is being discussed. This is a brief overview in the next slide. We're going to look at each of these a bit more closely. Background. Background is where you're going to be providing the essential context that helps the AI understand your request properly. This is where you're including relevant details and all of the background information that can help the AI get to the response that you want. Adding in relevant context. So anything that you think might be needed and just to give it more context. Think about if you were speaking to a friend or a colleague and you needed their help with something want to give them the information that they need. So why do you need this done? What are some of the things that you're looking to get out of this request? What would be a measure of success once it's completed? All of the relevant details surrounding the request and surrounding the information and the data that you are providing, anything to just help the AI know which direction to take and what sort of thinking to use when it's providing the response. Then a clear problem statement. This is where you're stating what the problem is and the solution and the outcome that you're hoping to achieve. And by giving the background, this is creating a solid foundation for more accurate and useful responses. Without the background, you might not get the responses you want. Or there's going to be just more effort and time needed going back and forth, interacting and engaging with the chat bod, just getting it to understand what you need. And there's no doubt that providing well defined background information and context is going to lead to better outputs. Role assignment, we touched on this in earlier lesson. This is where you're assigning a role to influence the AI's approach. The role you assign will guide its tone, its expertise level, and the perspective that it takes. It even changes how the AI thinks about your request. And as I mentioned, there is no strict or defined list of roles that you can tap into. But just think of who you would hire or who you would go to if you were looking to get somebody to help you with something. So you need an expert in a particular field. What would that role be? What would their title be? And that's essentially who you would designate as the expert in your proms. Some example proms here are things like a doctor or a teacher, programmer, financial advisor. There's also creative roles. You could tap into a poet, a storyteller, an artist, a filmmaker. More analytical roles, a data scientist, a researcher, detective, historian. And then if you need more of a programming role, tapping into software engineers, data analysts, database administrators, or web developers is going to get the best results for you. Next, we have A for action. Want to define what the AI needs to do by specifying clear outcomes and using action verbs. So you would define the task. You would use verbs such as explain this concept to me or compare these results for me, summarize this email for me, analyze this data for me. All of these are examples of clear and unambiguous actions that the AI needs to take. Then you want to clarify the outcome and also specify the structure and what is the purpose and desired result that you are hoping to achieve. For example, Are you asking for an entire blog article from start to finish or are you just asking for the outline of a blog article to be able to use further? Then another important element in the action is to specify the format. How do you want the response, and in what format should it be? By that, I mean, ask for things bullet lists, numbered lists, tables. You can even ask for actual file formats. So requesting it in CSV comma separated values format, or even a Word document. These work as well. But it should be noted that not all chatbots are able to do this. ChachiPT is one that is able to handle these file formats. Inputs, this is where you are providing the necessary materials and data for the task. So everything that it needs to be able to achieve this. Think of it as giving a assistant, all of the tools, all of the information for them to be able to complete the task for you. Without some of them, they might have to fill the gaps themselves, and that information or that approach might not be correct. So giving them everything upfront with all the references and the tools and the data points is the best action to take. Then references and examples of how you want the response are an excellent way to show what you're looking for. Aim for one to three references or examples. The more the merrier because AI is incredibly good at detecting patterns in the references and examples you provide. It's then able to convert those into the format that you're looking. More context leads to better outputs. Then lastly, N stands for narrowing. This is where you are setting the constraints around the request. That could be something like a length constraint where you specify the word count or the response size in how many paragraphs you want and how long the bullet list should be, things like that. You're also specifying the format requirements. What is the structure of the output? Is there a specific style that you want? Are you looking for a unique layout? These are all opportunities to put all of this important information to help get a better response. Then audience focus. This is very important, letting the AI know who is this intended for? Who's going to be using this information? What is their level of education? What is their experience? So are they a beginner? Are they intermediate or are they at an expert level? This would all determine the kind of terminology and the level of detail that is included in the responses. Again, here we're looking at the complexity level, and setting the education level or the technical depth means that your response is going to be much more tailored for your audience. These are all levels and parameters that you can specify in the narrowing part of your prompt. Narrowing focuses the AI's response, and it pulls out all of that irrelevant information, and it just gives the AI laser focused targeting, which is going to yield better results. This all together. So what would a prompt look like with all of these elements in place? First up is B for the background. We would say, I'm a marketing manager preparing a presentation on the latest social media trends. Next is R for role, and we're asking the AI as a social media expert. So we're asking them to activate that expertise. Next up is action. We're asking it to summarize the top three social media trends for businesses, and we're asking it for a specific year to make sure that it's current and fresh. And we're asking it to include relevant statistics. This is always good to get some nice juicy stats to be able to use in our content. Then I for inputs, we would attach a dataset, so this could be a CSV file, which has all of the social media trends that would be attached there as an input. It's the data that we are providing and the reference material. Next up is N for narrowing. So here we're asking to keep each trend to two to three sentences to keep it short and punchy. And of course, we could take it a step further here and add things like the tone what sort of tone we want? Is it professional? Is it casual? Is it conversational? We can also specify the education level of our reader, give it more information on our audience. All of these things are possible and would get you closer to the best possible response. And that is the brain framework. You can think of it as instructing the AI brain to give you what you want. That wraps it up. I hope the lesson was helpful, and I will see you in the next one. Goodbye. 6. Basic Prompting Tips & Techniques: This lesson, I'm going to help you improve your interactions with Chat CIPT to get the best possible responses. By the end of this lesson, you should be able to get smarter, faster and more accurate responses from the AI. Let's get into it. AI is incredibly smart, but it's not perfect, so it is going to get stuck sometimes. Let's have a look at some techniques to get around this. If the chatbot gets stuck or fixates on a pattern and keeps repeating mistakes, best thing is to just start fresh and start a new chat. AI models can get trapped in loops based on previous inputs as well as the context that they're including in their responses. So the best thing is just to start a new chat completely. This should fix the issue. When you encounter coding issues and you're finding that you solve one problem only for a new one to be created and you get into this loop, best thing is to ask the chatbot to create a summary and put into key bullet points, everything that has been discussed, the full context, copy that out, start a new chat, and begin again with a clean slate. This helps to clear everything out and you can start fresh, and much of the time, this will solve the issue. Next, just editing your original response is a really quick and effective technique. So if the chatbot is providing incorrect information, instead of debating or arguing, just edit your original message and re run it. This removes all of the bad context, and it's going to improve the response and get you closer to what you want. Simple structures for your prompts. If you're finding that you're still getting problems, breaking down complex tasks into numbered instructions is a good way to give the exact requirement that you're after. An example of that would be step one, list the key points. Step two, expand on each point. Step three, add an introduction. Step four, summarize with a conclusion. That has everything that you need, and it's going to force the AI to work step by step. Another thing to try. I know we've discussed about providing the background and the context first, but you can also state the goal first, as well. This can sometimes give you better results. So state the outcome, state what you want to achieve very early on. This can sometimes give much better results. And last one here using templates. So when you find something that works and you're happy with the results, save that, keep it stored safely and create a library of all of the prompts that work for you. You can store them in an Excel spreadsheet, an air table, a Google Doc, a notion document. You could even use a text expander or auto text to have a library where if you hit a specific hot key, it will then bring up all of your prompts that you can search through and select the best one needed. Any of these methods would work. The important thing is just to keep a collection of the prompts and templates and references and examples that are working well for you. Handling refusals effectively. Sometimes the happer will not follow through with your request, and then that's when you need to identify what is the reason for that. So identify the refusal type. And you would ask, is this a policy restriction or a system limitation. From that, you can understand, is there something that it is just not going to create for me? Or do I need to rephrase or rework the request? Be able to get around this. So a good technique is to rephrase the request. And in that rephrase, you would be more explicit and detailed and provide additional supporting context to really give the AI what it wants. If you hit a roadblock, why not try reassuring it of its capabilities and reminded that you've done this before, so you can do it again. Something as simple as saying try again, we'll get it to start the process over again, and I've had good success with just asking it to have another go at it. So give that a try. Getting the AI to follow instructions. Sometimes you just need to give the AI a nudge and a bit of guidance to take it down the right path. One technique is to frame things positively. So you are describing what you want instead of what you don't want. So describing what you want, not what to avoid. We touched on an example in an earlier lesson where if you ask the AI to not include any pink elephants. It might fixate on the word elephant, and you could get a green one instead or elements of an elephant somewhere in the response or the image. This is especially true when you're asking it to generate images. Then testing for accuracy, you would ask the AI to ensure this is factually accurate. It's important to remember that the training for these large language models are on datasets and training knowledge up to a specific point. So anything after that point, the AI would not have information about. And to fill the knowledge gaps, it might start to make up information. So this is where you need to verify the factual correctness of these. Another technique is asking it to do an online search, so a web search or search online, and there it can gather all of the data that's currently online to be able to give you an accurate response. Then this one I really love challenge assumptions. So you would ask the AI to request critical thinking and to even disagree with you and take purely objective approach to its response. This is a great way to ensure that the AI is not just trying to make you happy and agree with you and give you everything you want. It's really giving you the information that you need. So it's being impartial, it's being objective. And in the process, it might even stimulate some different angles and approaches to ideas and topics that you might be discussing with the AI. Improving results and fixing mistakes. So when you're getting incorrect or odd or just responses that you don't want, the best thing is don't argue with the AI, update the prompt and hit generate. This is something that is quite frequently needed. In generating AI images and especially when using ChatBT. And it gets to a point where all of the previous context and requests are just influencing its ability to handle things correctly. So best thing is just update the prompt and regenerate. Or if you're really still encountering problems, start an entirely new chat. And that is the next one. If you get persistent problems, then begin a new chat completely. Then another way to deal with this is to use one AI to fact check another, so you are cross checking so you would copy Cha CiPT's response and copy it into Claude or Gemini or perplexity and ask, is this accurate? And how can it be improved? Do you'd be surprised at some of the results you get when one model is fact checking another's? It's quite an interesting process. Why not give it a go? Now, moving on to optimizing AI for business and productivity. Self improving prompts. This is where you are asking the AI to rewrite your prompts for clarity. This is a great way to take what you have written as a prompt and ask the AI to better structure it and give it more details and more clarity for the best possible response. This is probably one of the top tips that I can give you, and it's it's so effective because the AI will rewrite your prompts in the language that it would best understand. So it's a really effective thing to try. Then for business use cases and frameworks, as we touched on in previous lessons, it's really good to assign expert roles and give it the business context and the data to get the best possible structured outputs. And remember, you can also ask for outputs, not just in text format. You can also get it in structured format. So that'll be things like CSV files or tabular data, things like that. Then using the AIs memory to your advantage, you can have the full context of the chat. So that is all of the responses as well as your prompts. This is super valuable to keep the chat going and to keep that context. So just because you've ended a session doesn't mean that you have to start a new chat over again. So keep a record of your chat, share them and save that URL somewhere. When you want to pick up again, you go straight back into that chat and you have all of the context, all of the prompts everything that you need is already in there, and you can just pick up from where you left off. Now, we're looking at performance issues and output issues and how to handle them. So in an upcoming lesson, we're going to be discussing how to humanize chat GPT responses, but a request as simple as asking for plain language and a natural tone and also to break down the request into clear steps. These can work wonders for your outputs. Switching models. This is where you would use different models for different purposes because each of them excel in different areas. For example, you have for example, Gemini and perplexity are really good for research. Claude is really good at natural language. Chachi Bit is great for brainstorming, structuring and refining data. Each of them have their strength. So make sure to use the best language model based on your requirements. And nowadays, a lot of them have very generous free plans, so you're able to swap out and switch over to another platform and use it with relative ease and without any additional cost. If you're concerned about Cloud AI and privacy issues, then consider running a local AI model such as Mistral or ama. These are really great to ensure that your internal data processing is up to the standards and the privacy levels that you need. What's more, it means you can fully customize the environment that these models are working. Next, let's look at some more prompting strategies. Here is another simple framework for you to use. It is the craft framework. So this is where you are providing the context, the role, the action, the format, and the target. Self evaluation, you're asking the AI to rate and improve on its answers. An example would be rate your response 1-10 on accuracy and clarity. And then also how could this answer be improved? And from that, you can iteratively improve the output and get to the best possible response. King an iterative approach. This is where instead of spending too much time crafting the perfect prompt, you just cast a wide net, you start broad and you say, give me a general response first, then we'll refine it together. These steps there are to give it the initial prompt, receive the response back, modify, improve, guide it a bit more. And then improve on that even further until you get that optimal response. So the approach you would take is basically give me a general response first, then we'll refine it together. And here are a couple of great resources, prompt base. This is a great website to find a huge collection of prompts for all different AI models, whether it be language models or image generation models. It's got something for everyone there, so it's worth checking out. Other great prompting resource is AIPRM. Both of these options are really great, and they have the web's largest collection of prompts, so worth checking out. And that wraps it up. These were some of the more basic prompting tips and techniques. In the upcoming lessons, we're going to be looking at some more advanced tips and techniques, so stick around for that, and I'll see you in the next lesson. 7. Intermediate Prompting Techniques: The previous lesson, we looked at some of the basic and foundational prompting techniques. In this lesson, we're going to explore seven distinct prompt types that serve different purposes and produced different results. Each prom type has a unique benefit and an optimal use case that can dramatically improve your results. We're going to examine how these prompt structures work, when to use them, and I provide practical examples to help you implement them in your own AI chats. This is going to help you to achieve more precise, creative, and useful prompts. So let's get into it. What are these seven prompt types? Well, they are listed here as we can see. They are step by step instructional, contextual and role based chain of thought reasoning, also abbreviated to COT, self critique and refinement. Creative ideation and expansion, compounded prompting, and lastly, multi modal or data driven prompt. Let's move on and look at each one of these step by step. First up is the step by step instructional prompt. This is where you are breaking down a series of tasks into logical steps that the AI needs to follow. Reason for this is it breaks the complex task down into logical chunks, and this means that results are a bit more predictable and you're going to be getting consistent results as well. An example of that would be, as we see on the screen now, step one, propose a book title on productivity. Step two, write a one paragraph summary of that book. Step three, list three key lessons from the book. There we have three very distinct tasks that it needs to follow and each one follows the next one. So once we have the results from the first step, it then iterates and improves for the following steps. The key benefits of this is that there is no ambiguity, so it reduces confusion. It keeps the outputs consistent and predictable and you have a clear and structured message that you are sending to the AI. When is the best time to use this type of prompt? When the task follows a clear sequence. So there's a logical set of steps that need to be followed, and you're able to combine those all into a single prompt, like with writing a fixed format or building something step by step. So you're just working through a series of steps. The next type of prompt is the contextual or role based scenario prompts. And this is, as you learned in previous lessons, where you're putting the AI into a specific role, such as a teacher or a consultant or a character, this gives the AI, the context and the depth and realism to be able to respond in the best way possible. You might remember when we give the AI a persona or a role, it not only responds differently, it also thinks differently. So it thinks based on that role and persona. This brings the contextual depth and relevance from those expertise, and responses are a lot more well structured. They're a lot more well thought out, and they will contain the level of detail that is relevant to that persona. Some examples of the contextual or role based prompting time is as follows, as a travel consultant specializing in ecotourism, create a five day sustainable itinerary for a couple visiting Costa Rica on a $3,000 budget, highlight eco friendly stays and activities and explain the environmental impact of each choice. Here we've given the role of a travel consultant, and we are giving all of the relevant background information and context. It has all of the details available. We're saying that it needs to be a five day trip, sustainable itinerary, so incredibly specific there we've given a budget as well, and we're also looking for activity as you can imagine, with all of those contextual details and all of the parameters that have been set, the AI knows exactly how to respond. The key benefits, as you can imagine, with all of this contextual information and detailed info that's provided, the AI is able to respond in a very thorough way. So it has all of that information. And it would even match the tone and voice of a consultant and give you all of the details that you would need. So this will also help you to boost creativity because you're going to be getting all of these options provided for stays and activities. And it would just allow you to come up with the perfect trip packed with all the activities that you want. It's time to use it. Well, anytime you want expert level responses or content with a particular strong point of view. That is the view coming from an expert or somebody very specialized in a particular field. In this case, it was the travel consultant. It's able to give you the relevant point of view from that expert. Next is the chain of thought reasoning, and this is a really powerful one because it encourages the AI to think step by step through its answers. This helps to improve the logical flow and it's able to show you all of the step by step thinking that it is doing. A lot of the language models and chatbots allow you to actually see the step by step thought process that the AI is going through. And here we can see an example of a chain of thought prom. The idea is to have a first this, then do that next, then finally do this. In the example here, analyze why the 80 20 rule is effective in project management. First, define what the 80 20 rule is. Next, provide a step by step example of it applied in a project scenario, and finally, present one counter argument about its limitations. Using this chain of thought prompting, it's better at problem solving and accuracy. You're asking the AI to slow down, take a step back and look at everything in a logical sequence. Instead of just trying to give you the quickest answer possible, it is going to think through all of the context through all of the steps, through all of the requirements that you've put in there and really bring its reasoning capabilities to ensure that it gets to the best possible answer for you. This is the benefit of breaking it down into steps. When is the best time to use this? Well, explaining a concept or analyzing a problem or just making sure the AI doesn't skip logical steps. And then one thing to note with the dedicated reasoning models such as 01 and oh three Mini and Gemini two point oh flash, they already have step by step reasoning built into the flow. So when you submit a prompt using one of these reasoning models, it's already built in there. So this kind of prompting is not as effective with those, and in fact, it's actually not needed because you will see that they take a chain of thought and step by step reasoning approach to your prompts by default. So it's just not needed for those models. The self critique and refinement prompting technique. This is a great one because the AI is self critiquing and self evaluating its own work. This produces a cleaner and more thoughtful response. It's especially good for writing tasks, such as articles or social media posts or presentations, as well as summarizing long form content or other types of summary needs. An example of the self critique prompting type, draft 150 words summary of the benefits of AI in business. Then critique the summary for clarity and persuasiveness. Based on your critique, rewrite the summary to be more clear and convincing. So we're asking it to not only critique its response, but also then to improve on it. So, in addition to the self critique, it's got a second step of rewriting the summary to be more clear and convincing. The key benefits, of course, this is going to lead to a very effective prompt. It's going to enhance clarity and you're going to be sure that you're going to get closer to the desired output that you want. It's pushing for self improvement on what it produces. The best use case it's great for editing, editing of written content, rewriting, of course, taking existing content, rewriting it in a different flavor or a different tone, things like that. Polishing and improving on first draft. If it has created a first draft for you, you can use a prompt like this to further improve. Though this technique might be less effective with reasoning models. It's worth trying it out and seeing the results for yourself and your particular use case. Then the next prompt type is the creative ideation and expansion prompting. This is really good for just generating a diverse range of ideas and brainstorming content. And it's particularly useful for brainstorming and marketing. If you're wanting to explore fresh ideas or just expand on existing short inputs, then this is the prompt to use. You'll be amazed at how it can just inspire more creativity and boost the thought process when you are using it. An example of creative ideation, list ten social media post ideas to promote a new electric bicycle. Then take the top two ideas and write a catchy tag line and a two sentence caption for each. This is just a simple way to squeeze out a bit more from the AI model and ensure that it is taking the cream of the crop the two best ideas that is relevant to the product and it's going to write the catchy tagline for that. Benefits of this is you're able to rapidly generate a lot of diverse ideas, and for marketing, this is essential. It's also great for content creation, and you're able to take small ideas and concepts and really just run with them and turn them into big ideas that can really help you in your campaigns. Best use case, of course, by the name, creative ideation, it's really great for content ideas. Ad campaigns, generating ad hooks for your social media ad campaigns or search engine ad campaigns or your print ad campaigns, that sort of thing. I can help with the ideation of that hook to be able to have effective ads. If you're looking for product names as well or listings or digital bundles of some sort or anything like that, it's really good just to take a SD idea that you have and just exploded into a whole series of brainstorming ideas as well as provide you with inspiration to get to the result that you want. A top tool is ChachiBT because it really does, at least in my experience, I find that it does excel at ideation and brainstorming. That is a top tool to use when you are doing this kind of compound prompts. These are when you are combining several tasks into a single one, the AI can deliver a complete and cohesive answer that is ticking all the boxes at once. It's providing you everything you need. This is obviously a huge timesaver because you're layering in all those tasks and it's making everything more coherent and useful. Example of that would be create a Linked in post about focus and productivity, start with the definition of focus, share a short personal story, illustrating its importance and end with a call to action inviting comments. There we are saving time by bundling these steps into a single prompt and we're able to get more content out of it and of makes it perfect for content with structure and purpose, such as social media posts where you would have these structured elements, such as the hook, the body, the conclusion, and maybe a personal anecdote, best use case. As we've been seeing, it's great for social posts, marketing emails or any format where you just want multiple elements like a story called action plus the definition, all contained in one output. Multimodal or data driven prompting. This is where you are getting other types of media formats, looking at charts or spreadsheets, images, audio files, video, that type of thing. You're able to use this data in whatever format you have it in to provide context rich responses. Most of the chatbots nowadays are able to use any kind of data in whatever format that you provide. Whether that is images or spreadsheets or charts and even audio. So whatever the format, it's able to work with it. An example of this multimodal prompt is using the attached sales dataset, summarize the key trends in employee performance last quarter, then generate to bar chart in textual description or code that compares the sales of each The key benefit of this is it handles data analysis and reporting with ease. So if you have charts and spreadsheets, you're able to use them as well. But not just that, it supports visuals and even code snippets. So you're able to put in any kind of image, whether that's an infographic or photos or anything like that, and it will then be able to use that as the input. So instead writing out a long text explanation of what it is. You're able to just add that to the chat and it knows exactly what it's working with to be able to give you the best possible answer. Best use case, of course, for analytics and data reporting, it is really good. But of course, summarizing from files and extracting data from files. If you have PDFs, you're able to drop in those PDFs and it can work with them no and it can work with all kinds of structured data as well. Whether that is something as simple as a spreadsheet or something even more structured like a JSON file or a web development or coding script, it can handle all of these media formats with ease. That wraps up everything. I'm sure you can see by mastering these prom types, it's going to lead to richer and more effective AI response. These slides, you're able to see which of the scenarios each of these prompting types are best suited for. I hope you can go out and try them just to see the difference that it could make. So why not apply these techniques and see how you're able to get clearer, more structured responses. That wraps it up. I'll see you in the next lesson. 8. Prompt Enhancing Shortcuts: Creating the perfect prompt shouldn't feel daunting, especially if you're looking to get creative and generate AI images. You don't have to be a prompt engineer to get great results. In this lesson, you'll learn how to use ChachibT as well as some other tools to structure and create effective prompts. You'll be able to use these inside of ChachiBT for content and images, as well as other AI image generators like Leonardo or Mid Journey. Let's have a look and see how you would do that. Using ha HIPT directly, you're able to build the perfect prompt. Instead of guessing or wondering what parameters I need to use, just ask Cha chipT to create the best possible prompt for your needs. Then how would that look? Well, let's work with an example here of generating an image prompt. The scenario is we want to create an AI generated image of a futuristic cyberpunk city. It's as simple as asking Cha IPT once we have all of the details that we want in the image, help me craft a detailed prompt for an AI image generator to create a cyberpunk city at night. Then we're adding some details that we want to appear neon lights, flying cars, and a futuristic skyline. And we're going to ask Cha CBT to help us just embellish and expand on this prompt and create something that is more comprehensive. And here we've been given a detailed prompt, and from here we can see it's really gone into details, and it's setting the scene, and we have elements appearing in the background, and there's a really impressive list of details. So as you can see, this has done a really good job, and what we would then do is use this to generate the image. We could even have a look at that now just to see what the result would be. So using the Dari picture action, I'm going to copy this prompt. And we will see what the result is for that. And the same thing can be done with text based content that you're wanting to create. So you would then ask in a situation, maybe you're creating a social media post, you would then ask, help me craft the best possible prompt to generate a high engagement linked post about productivity hacks for entrepreneurs. The prompt should ensure the content is concise, actionable and includes a call to action, use a suitable copywriting framework. And we'll run that in a moment. But here we can see this is quite a stunning visual that's been created, and we can see it's using all the details that we had from the enhanced prompt that we were given from ChachBT, which is quite a bit different to the one that we started with. And there we have the option of using ChachiBT directly to create our image prompts. Next, if we wanted to generate a text based bit of content, like I was mentioning a moment ago, we are looking to create a LinkedIn post that we could also use, and I'm just going to bring the prompt up here that I have ready. So this is requesting the prompt and we're asking it to give us some help and just add in all the details for us. So that's essentially what we're doing here. We're using SHAPT to fill in all the blanks and enhance the prompt for us. And here we go. We've got a very comprehensive prompt, and of course, we would refine this and adapt it for our needs. But you can see this is how you would achieve that. Moving on to the next option, that would be using a custom GPT. Then once you're in the GPT marketplace, you can search for prompt engineering or prompts, anything like that would bring up similar results. And from there, you can choose a custom GPT for your needs based on the platform that you're using or for the specific task that you're hoping to achieve. And that would then bring up a custom GPT that you can start to chat with, and it would help you create the perfect prompt that you can use either in Chat GBT with Dali or moving over to another platform like Mid Journey or Leonardo. And over here, you can see creating efficient prompts, master prompt engineering, and it's got all of these. And if you wanted to get specific, you would put in the tool that you were using to get tailored prompts for that platform. And that's taking a while to load up. But there you go. We've got some mid journey prompts, and of course, you could do the same if you were working in any other platform. The next option would be to use ready made prompts. And the favorite one of mine is prompt base. This is a marketplace where you can buy professional prompts. You can even sell them as well. And this saves a lot of time because they are professionally created, so you know you're going to get consistent results. But from here, you can see there are just so many categories available. And these offer both text based prompts as well as image prompts and a whole lot of other applications as well. This is a really good option, and as you can see, the prompts are very reasonably priced. For 299, you can be sure that you're getting consistent results. And lastly, there is another option, and that is to have a look at the image generation platforms for the actual proms. So if we hop over to Leonardo, this is an impressive AI image generating platform, and looking at the community generations, you're able to see exactly how these images were created. When you click on the image, you can see the prompt that was used, and from there, you can get a feel for how to structure these prompts. What sort of elements do you need to include in them for them to appear in the final output. And this just gives you a really good guideline to be able to get to those professional and those impressive outputs that you're seeing. It should also be noted that there are different models that are used for generation there's also elements and style references and things like that that can influence the output. It's not just working from the prompt alone. There are other elements layered on, and while you could use this prompt, it might not get the same result. What I'm showing you here is that you can use these prompts as a base to work from. There are, of course, a few other options like flow GPT and prompt hero AIPRM for ChatPT. These are all places where you're able to get prompts and use prompts generated by other people and professionally created for your own use. And that wraps it up for this lesson, and you're able to see that crafting the right prompt, you don't have to be a prompt engineer. It's as easy as asking ChachPT to help you build it for yourself. We learned how you can look on the GPT marketplace to get tailored GPTs purely built for effective prompts. And the best thing is just to try some of these prompts. And what I recommend is just to get your hands dirty and just try a few of these prompts, try different ways of saying the same thing or different ways of describing what you want to appear. And you'll be amazed at the results. And if you want to go a step further, using platforms like Leonardo or Mid journey, it's a great step just creating those professional looking images that you see online. But I hope you're able to see the possibilities of creating prompts or helping you to get to stunning AI image generations. That's it for the lesson. I'll see you in the next one. 9. Advanced Prompting Techniques - Superprompts and Pseudocode Prompting: We learned about the foundational basic prompting techniques as well as some more intermediate techniques. Next up in this lesson, we're going to be looking at three advanced prompting techniques. They are the super prompt, a compound prompt, and the pseudocode. These are all really powerful prompts, and I can't wait to share them with you. But before we dive in, I just wanted to touch on something. You might be thinking, Well, James, a lot of these prompts are looking very similar. You're not imagining things. There is a lot of overlap between all of these prompts. Each of them has a slightly different purpose, as well as a slightly different technique. So it's important for you to have a look at all of them that are available, and then you're able to pick and choose the elements that you feel are going to give you the best results. There is no fixed way to get the perfect response from an AI, but using the elements from these prompts, you're able to get it pretty close. The purpose of the super prompt is to achieve a precise and high quality output from a single task, and we're able to do this by giving the AI all of the information and context and examples and guidance upfront. Basically, we're giving the model a fully loaded, well structured prompt to get a rich output from it. Then the compound prompt, this is where we are combining multiple actions or questions into a single prompt. We're asking it to do multiple related tasks in a single goal. This is really good for automating workflows or tasks that have related steps to follow. With that out of the way, let's dive into them. The super prompts, with the super prompt, you're giving a comprehensive structure. So you're packing in all of the detailed instructions. You're giving the context and the background. You're giving it some examples, as well as constraints, and this is all being packed into a single prompt. So you're loading it with all the information that it needs from the start. This is really effective and it helps guide the AI toward a very specific outcome, and it reduces any ambiguity. So there's no room for misinterpretation, and it's also a reliable way to get exactly what you want. Specific outcomes, we are directing the model to a precise outcome. So superpmps make it clear what you want and they leave less room for misinterpretation. Or any ambiguity. Speed and completeness, as you can imagine, although it takes a little bit of extra time upfront to put in all the information, that time is saved by not having to iterate on the responses and have all of the back and forth with the AI. The likelihood is you're getting an accurate and detailed response from that first prompt. This is an effective and quick prompting technique. So you're getting a thorough output by giving it all of the instructions and all of the content upfront. So instead of iterating step by step, you get a solid first draft in one go. The use case, this is ideal for brainstorming, rich creative outputs. It's great when you want the AI to generate long form content such as emails or articles or marketing copy, and you don't want to do all that back and forth. So you're trying to get everything in a single shot. An example of this would be a basic prompt, would look something like this. Give me marketing copy for product X. Where as a super prompt you are a marketing expert, write a 300 word launch email for product X aimed at small business owners, start with a catchy intro about their pain point, time management, then introduce product X as a solution with two benefits backed by fax, with a friendly call to action to try a free demo. Use a confident upbeat tone and include one short customer testimonial. Then you would provide three examples of how you would like the output to be structured. As well as any additional data or context, things like PDFs or spreadsheets or graphics charts, anything that is going to be relevant that you can just really load the AI up with and ensure that it has all of the information it needs. Here, from this example, you can see we're using the role prompting technique. We're giving it a persona. We are clearly stating the task and the action it needs to perform. We're giving it constraints. We then giving it all the relevant information about the audience, and we're clearly stating that we need a catchy intro and we're targeting the pain point. Then we're introducing the product as a solution. And we're asking it for two benefits backed by fax, and then we're also including information about the tonality. A prompt like this is going to get you a very thorough, very detailed and very targeted response. It's a great one to use, and although a little bit of extra time upfront needed, it is well worth it to get that fully comprehensive response from the AI. Next up is the compound prompt. As I mentioned before, this combines multiple actions or questions into a single prompt. We're wanting it to do multiple but related tasks in a single go. It saves a lot of time because we're merging all of these steps into a single request. AI will consider all of the components together before it makes its response. Thing to note is there is a bit of balance required. So to avoid confusion from too many tasks, just make sure to keep them tightly related. Otherwise, it may send the AI off track a little bit. And this type of prompting is best used for related multi step tasks that benefit from an integrated and time saving response. Now, here we have a compound prompt example, act as a startup advisor for a software company. Given this idea and you would insert the idea for a app or a SAS product, analyze three pros and cons using market data and competitive benchmarks. Recommend one monetization model that fits a solo founder with limited capital and explain why it's the best fit. Outline the first three lean startup steps to validate this idea with minimal risk. Use a friendly, no fluff tone. And then I always like to make sure to let the AI model know if it has any questions or it needs more context. If you need more context, to give a better response, ask me follow up questions before answering. This is a really great way to make sure that all the gaps are filled and that the AI model is not making up all of the information and it has everything it needs. The pseudo code prompting type, this is one of my favorites because the results you get are incredibly accurate. It's a code inspired prompting language that helps AI like ChachiBT understand your instructions more clearly. Be these AI models are built on code platforms, understanding code is built into their DNA. So if you provide the prompts in a code like structure, you're going to be able to get very, very accurate results. So a code like structure provides clear instructions in a code like format, and this, of course, reduces any misinterpretation and ambiguity. Now, having mentioned code like structure, I don't want you to be put off a say, James, but I don't know programming or coding or development. It's not so much a structured, perfect syntax as you would find in programming languages. It's more about providing very specific logical requests. While we have a code like structure, it's merely a simple syntax, a simple language that we're providing to the AI to understand it more clearly. So it has clear organization, we're defining the data, the rules, and expected outputs all in one place. You're going to see from the example how simple it can be and how easy it is to read. Don't get put off. It is just a name that's given for this type of prompting technique. Then lastly, reusable components. You create the logic once and you're able to reuse it across different proms. Once it understands what you're looking for, you can then reuse that for an entire chat thread, and that makes it really efficient as well. This is best used for complex tasks requiring structured logic, defined outputs, and reliable execution. Now let's move on to an example. Here we have two examples, a plain language prompt. You can see what the prompt would look like in plain language if we were to spell it out for the AI model. And then on the right is the pseudocode prompt. As you can see, the total characters for each of them, 275 characters in the plain language prompt, of course, that's a lot more wordy and it's going to take longer to write out. That is far more efficient. So looking at the prom, from the list of e commerce items, extract the product name, the price and URL. Filter out any items where the price is less than $20. Format the output as a comma separated list where each item is represented as name, price, and URL, and then we are inserting the item list here. The pseudocode prompt version of that. Now, as I mentioned before, there is no language or no fixed syntax to use for this kind of pseudocode prompting. It's merely just a logical set of instructions that you're providing. Almost think of them as very basic Google sheets or Excel formulas that you're prompting with. So that same example, we're going to extract products. The input is items. We're saying that this is a list, and the output we want is in CSV format. We have a filter there and we want to filter out all of the items with a price greater than or equal to 20. So it's going to look down that column and start to filter those out. The fields we're working with are name, price, and URL, and we are going to provide the list of items. And here we're going to see a demo of what that looks like. This is an example of the list of products, and now we're going to run both of these prompts so that you can see the results that each of them will give us. And as you're going to see, the results are the same for each of them. I'm going to run each of these prompts independently and you'll be able to see the results from them. So let's take a look at that. And here I'm putting in the prompt. And also, we can see here is the spreadsheet. It has a very simple layout. We have some headers. They are product name Price URL, and from there, we are going to run this prompt. Here we can see it's giving us the results back. So yes, it has given the correct list of items. We see that they are filtered to those that are greater than $20. However, it is missing a few things. We're missing the headers, as well as it is not in CSV format. So we'd have to copy this and paste it into a blank spreadsheet, which is not ideal. I'd need to ask it just to add in the headers and also to create it in a CSV file format. Not a big issue, but it's just an additional step that's needed here. And there we go. We have the CSV format and everything looks good. Now, let's start a fresh chat, and we're going to try the same prompt again, but with the pseudocode prompt. And here is the pseudocode prompt, going to upload the exact same reference file and going to run that prompt. And as you can see here from the result, it has gotten everything that we're asking for. It even includes the headers there, so it saved us a step, and we also have it as a CSV preview window, so we're able to hit the download button and work with our CS they both more or less took the same amount of time to actually run the prompt. However, the pseudocode prompt was able to get to the result that we wanted in less time. I got it the first time and we were able to start working with our file and start using it straightaway. Whereas the first prompt where we had the natural language, the conversational language, it needed some work after, so we needed to iterate and there was a bit of back and forth to get to the same results. So this just shows the efficiency when using the pseudocode prompting technique. The main benefits of the pseudocode is clarity, removes confusion by using precise syntax. There's less guessing for the AI about what's expected and what it needs to do. Consistency, this is the beauty of it. You're going to be able to now get consistent results for each response. And when you're using the pseudocode prompts within a long message thread, that becomes very important. So it's following those specific rules, and you can expect the same output each time. Also define conditions and formats to help standardize these results as well. Efficiency, as we just touched on, it's going to require fewer words and oftentimes it's going to get better results as well. Complexity, it can handle some pretty advanced tasks more effectively than natural language, which is especially powerful for tasks that mimic programming, automation or structured data process. If you're working with data such as spreadsheets or tables or charts, that sort of thing, this is where it really shines. You might be asking, well, which prompt technique do I use? Which one should I be using? There's no one size fits all. Each of the prompting strategies have their use cases and their best applications. So when to use them, but there's nothing wrong with combining strategies. So to get optimal results, you combine the strategies because complex task can require a bit more complex prompting. So this is where you might choose the super prompt, but you could add in elements from another prompt. So you could have a super prompt combined with some step by step. Compound prompting tasks. Strategic selection. This is where you try to match the prompt type to the specific needs. And as you saw from this lesson as well as the previous lessons, where the best use cases for each of them, that's where you think about what prompt is going to give me the best result here and you use the most appropriate one. Look at each of the strengths for a particular prompting technique. As you practice, you'll be able to see which prompt types give you the best results. So I'd love for you to give these a try and see which one is going to work for your most common task. And just ask yourself, how can AI help me and which prompt is going to get the best results? So I encourage you the next time you have a difficult task or a workflow, think about which prompt and which technique you'd like to use and which one is going to be best suited for the task at hand. That wraps up this advanced prompting lesson. I will see you in the next one. 10. AI Document Summaries with Context: HGIBT really excels at taking large amounts of data and condensing and summarizing it into key points. I'm going to show you how to do this in this lesson, and we're going to take a PDF and summarize it. But then after that, we'll take it a step further, and I'll show you how to add contacts to the summary. So let's hop into HachiBT. Okay, I'm going to find the PDF, and this is just simply a PDF which is outlining the new features that Canva has released recently. I'm going to use a simple prompt. And that is to create a bullet summary of the key points. I'm going to run that. And there it's given us a nice summary with all of the key points, which is a lot easier to read, and it just is structured well. To take it a step further, if we wanted to create summaries in the context of our work or a specific project or a specific use case, we could do that via the custom instructions. To find those instructions, head down to the customized hat ChIPT option. And there you see a customized Chat IPT window, and you're able to add custom instructions. So to add some information that you'd like ChachiPT to know about you as much as you're comfortable with. That could be things like your personal details or of course, not any sensitive information, but personal details like your name, where you live, what your job is, what you're busy working on, that sort of thing. And you're also able to tell Chat GPT how you'd like it to respond. So would you like well structured responses with tables and bullet lists where possible? And that's what I've had it down there. You can also add things like the style and the tone and the friendliness of the responses. I'm going to enable this for new chats because we're going to run this again on that document summary task and save here. Now I'll need to start up a new chat. Let me actually see. Um, who am I? So here we can say, I am son with curiosity and creativity, so it doesn't know all of the details that I've just enabled for a new chat. But going into a new chat, asking the same question, it now has all the relevant contexts to be able to answer as we needed to. I'm going to attach the PDF again and give it the same summary, but at the end, I'll say in the context of my course that I'm developing. Okay, that's right. It's a bit tricky. I've got the microphone in front of the keyboard here, but we've managed it, and it's going to based on the course, it's giving us a different summary. And if I was to ask Cha CEPT what is the course I'm working on AI focused course. So it was able to take all the details that we gave it, the context that we are working with and respond according to them. This is just a great way to take documents and large amounts of data and give it the relevance that you need and put it into a summary that has all of the key points that are meaningful to you. I hope you find that useful, and that's it for this lesson. I'll see you in the next one. Goodbye. 11. YouTube Summaries using ChatGPT: Another great way to use Chat CIPT is to make YouTube summary. Sometimes you don't have the time to watch the full length video, or you just want to have the key points without all of the advertising or maybe there's some additional fluff that goes on and you just want to get into the meat of the video. ChachiPT can do that, and I'm going to show you how to get summaries of YouTube videos. To do that, you come over to your sidebar and down here to explore GPTs. From here, you're able to search on the GPT marketplace and using a keyword like YouTube, we can find all of the GBTs available. Now, it's a good idea to test some of these as not all of them work as expected, but one that I found to work pretty well is the YouTube video summarizer. As we can see here, the ratings are pretty solid, so it's a good one to go for. Once you're here, you would then just ask it to summarize a video. And once you have that YouTube video, you can add it in here. And then send that prompt. From there, it'll work on the back end, retrieve the video, and be able to start the action and create the summary for you. It should be noted that not all videos have transcription enabled on them, so you may find that some of the videos that you put and you ask for a summary of might not be possible. And this is just because the YouTube channel has restricted it on that video or the person doesn't want the transcript to be created. But for the most part, a lot of them do work, and here we're able to see it's given us a great breakdown and summary of the video, and this means we can just get the key points from a video. So that's one way to do it inside of Chat GPT. There's also a way to do it through plugins. On Chrome, if you have certain plugins, you're able to use what's called the YouTube transcript, and this is just a chrome extension that you install. And once it's installed, if you go to any YouTube video, you'll see a YouTube transcript button down in the bottom right there, and from there, you're able to see the transcript that is created. And once you expand the transcript, you're able to see it contained here below. From there, the entire transcript can be copied. At the bottom, there is a copy option. There you can bring it back into Chachi BT if you need to. Or use it however you need to. So those are two simple ways that you can use Chachi BT to summarize your YouTube videos. 12. Create Charts and Sales Reports with ChatGPT: Creating charts from your data is another handy feature that ChachiBT can help you with. This lesson, you're going to see how we're able to turn our data into interactive charts that we can then export or even save images to add to our own reports that we create. At the end of it, we're going to ask it to summarize all of its findings and create a report from us that we could send to somebody else. Let's have a look and see how to do that. I'm in Chachi Bettina, and I am going to use a simple prompt, such as this one. Asking it to create a comprehensive chart for the sales data in the attached document, I'm going to attach a CSV file and you'll be able to see in a moment with the preview window what we're going to be asking ChachiBT to look at. So here in the data preview window, we can have a look. This is just a simple table with some sales data information for a coffee brand called Mu tropic. We're looking at the products and quantities ordered, the price, and some other data as well. And here we go. I'm just going to minimize out of there. And Cha ChIPT has given us a breakdown of the daily sales trend in a chart format, as well as the total sales by product, as well. It's giving us the total sales by state. And what you can also do is interact with this chart. So here we have the data points, and we're able to see on the given date what is the value. We can have a static chart as well. We're also able to I'm just going to expand this here so we can see it a bit more clearly. You're also able to do some visual changes like the dataset color that can be changed to green or any color that you want. And you're then able to see that change reflected there. You're able to download these charts as well. So if you wanted to use it for other reports that you're generating, that's possible, as well. Taking a look at this, we've got all of the information we need, and it is beautifully laid out. From here, we could save these images individually. Or if we're happy, we could ask JAGBT to take these charts and create the report for us and also add a bit of contextual information and an executive summary to be able to understand the data a bit better. So let's go ahead and do that. Once we're happy with the response, then adding a new prompt, we're asking to create a sales report as a Word document. That's the format we want, using these charts and include contextual information as well as a summary of the report data so it can be understood more clearly. Using the information which it has, be able to tell us in plain language what exactly we're looking at and what is contained in the charts. And lastly, we've given it some additional context saying this will be sent to a sales manager for review, so it should have everything it needs. I'm going to run that prompt. And Chan CPT then should be creating the report and using the charts to fill up the pages of our report. And we're back and the report has been generated. Let's take a look at that. There we go. And from here we can see it's given us the sales report provides an overview of the sales performance analyzing trends. So it's included all of that, as well as the contextual information. It's quite basic in what it's providing, but it's given us a nice, well structured list of headings that we could work with and some information as well. So this to me is a really good example of just creating kind of a starter report. And of course, we could go in there and add on our own information and input our own insights, things like that, or even just put it back into Chat EBT and say expand further and give it more depth. So that is how you would create engaging reports, and you're able to create charts all inside of Chat EBT. They can be static. They can be interactive. You can change elements like the coloring of the bar charts, and that is sure to be a big time saver in your report creation needs. That's it for the lesson. See you in the next one. Bye. 13. Upscale Images & Convert to PNG with ChatGPT: The images that Chachi PT generates are created at one oh 24 by one oh 24 in pixel dimensions. Sometimes we want the images a bit larger than that. While there isn't a built in function to achieve this and upscale the images, we can do this with some clever prompting. I'm going to show you how to do that in a moment. Using the slash key, this selects the picture model from Dali, and then we can start to create our image. So a simple bowl of ramen for this example. I'll then create that image for us. And here we have our very tasty looking bowl of ramen. From here, I'm going to open the image and come into the editing mode. And the prompt that's needed to achieve this is upscale this image, and you would choose the amount that you want to upscale by. And then, importantly, to keep everything the same but sharpen and enhance the details. Now the next part using your Python Pillow library. The Python Pilar library is what ChachPT uses on the back end to do all of the image manipulation and image editing. We're asking it to use this when it does the upscale. Action. I'm also adding in some aspect ratio requests here, so we want to make it 169. We want it to be a PNG. We're asking it to not use any of its charting or data visualization libraries, just in case it tries to use one of those and gives us an undesired result. I'm going to run this prompt. And here we go. It's created the new image for us, and we can see that it's looking pretty good. And I'd just like to make sure that it's upscale as we want. I'll save this locally. And let's take a look at the dimensions here. I can see that it's still at the same size. We can see there it is 1024. That just means we're going to try again with the prompt, and hopefully the second time it will get it right for us. This is quite normal. Sometimes it won't always get it on the first attempt, and you just need to follow up with the second prompt, asking it to refine anything that you're not happy with or just resend the prompt altogether. It has upscale and enhanced, and it's given us a download link. I'm going to download the file. I can see that it has saved it as a PNG, which is already good news. And if we come in here and have a look at the upscale ramen, there we can see it has increased the pixel dimensions to 5376 by three oh 72, and the file size has jumped up to 20 meg. Having a look at that, we're then able to see here's our large image. And it does seem to have enhanced the details there. And that's just a great way for you to take the existing images that ChaGBTs created, adapt them, edit them, and ask HAGBT to upscale it, and try and sharpen and enhance the details so you can have a large image that has all of the details that you want. I hope that was helpful, and I'll see you in the next lesson. 14. Create Animated GIFs from MP4s with ChatGPT: Creating GIFs inside of CHAPT is as easy as giving it the overall theme that you want, any text you'd like appearing on the Jif and even things like the frame rate. But to take it a step further, we can create JIFs from MP four video files that we have. We can even specify the exact seconds and frames that we want to extract for our Jif. Let's have a look to see how you would do that. Inside of hachPT, I'm going to add a MP four movie file. And this is just a simple little movie here. There isn't any audio, but this is what it looks like. And we're wanting to extract some of the frames from it. So bring it into ChaiPT. I'm then going to use the prompt using movie Pi. This is the library that hachPT uses to do all of its video editing functions and asking it to create a Jif from seconds two to three. So we could either ask it to do for the entire video or specify which seconds from the video we like the GIF to be created from. Going to run that prompt. And here we go. It's created the JIF for us. Only thing left is to download it. And here we have the JIF file. If I open it, we can see that it's just taken out the range from second to second three. And with that, you're able to just extract the exact frames and the range that you want from MP four files. Can also use other functions from the movie Pi library, things like extracting audio. You can trim videos. In an upcoming lesson, you'll see all of the possibilities of using the movie Pie library and some of the things that you can do with video files inside of Chat GBT. That's it for the lesson. I'll see you in the next one. 15. ChatGPT Vision - Analysing a Social Media Post: The next key vision capability is contextual understanding. Cha chiPT can interpret the context of the images that you provide, and it can see the relationships between the elements and objects in an image. We're going to have a look at an example to see exactly how that plays out. And what I'm going to do is upload a screenshot of a LinkedIn post from a prolific copywriter. And the screenshot looks like this. This is from Dickey Bush. He's an exceptional copywriter, and this is a post on LinkedIn. And he was just giving advice on which books to read next. And from here, we want Chat GPT to break down the elements of this. So it's going to look at the different aspects from a psychological point of view, because we want to know what makes us click on a post or read further, and ChaiPT is going to help us understand the science and the psychology behind a successful post such as this one. And as we can see, it had 531 engagements, a lot of comments as well. So this is definitely a good example of a viral post, and we're going to break it down and understand exactly what makes it so powerful. The prompt I'm going to use is the following, and here it is. Analyze this Linked in post by examining the hook and structure. How does it grab attention, tone and writing style, what makes it resonate with the audience, engagement triggers, what elements, questions, storytelling format, drive likes and shares, and then some actionable takeaways. Cha CiPi T is going to look at the context that the post provides and just break down all of these elements and give us a structured analysis on the post. So let's see what it comes back with. Alright, so here, it's given us the hook and structure, saying that the post opens with a strong intriguing statement supporting context. The next line, they could have been blogpost is relatable for many readers and adds an air of authority. List format, it's saying why it's presented as a numbered list, makes it easy to skim. And including a bonus adds value and creates a sense of exclusivity. So as you can see, I won't go line by line through everything else, but we can see that it's really broken it down and just put it into plain language so that somebody could have a look at this and just understand the psychology of what makes this such a successful post and then try and replicate that with their own posts. Because that's the goal here is to emulate, take what we see as successful and powerful and use it for ourselves to bring some of that to our own posts. To take this a step further, we could then ask it to create a template or a framework from all of this so that we know exactly what we need to use and the elements that need to appear. And here, it's given us a template, a framework to work from, and we would essentially then just fill in the blanks with our own content. This wraps up the lesson. And I hope you can see from this one and the other lessons on the vision capabilities, just to see how powerful Chachi PT is, we learned about image recognition. It can identify objects, scenes, and elements in an image. We learned about optical character recognition that is OCR. This is where it extracts texts from printed or handwritten notes, image summarization, it can summarize parts of the image, image classification. Remember, we organized and classified and categorized all of those leaflets from the expo. It's incredibly powerful and quick at that. Data extraction. It can pull structured information from the images supplied. Even charts and graphics it's able to work with. Handwriting analysis, whether it's scribbles or tasks or meeting notes, it's able to digitize those writings so that we can start to interact with that content. And also visual search assistance, it is able to find and relate information from multiple uploaded images. Again, like we saw in the leaflets and the brochures, it was able to piece it all together and put it in a nice structured tabular format. This just shows Chat Chipt is just so much more than a text based chat bot. When it comes to images, you get a lot more functionality. It's a lot more efficient, and it's bound to streamline your workflows. That wraps up this lesson. I'll see you in the next. 16. ChatGPT Vision - Digitize Printed Documents: The next vision capability is image classification. This is where Chachi PT is able to classify, categorize and organize the data extracted from images, and it can also work with multiple images at the same time. This is what we're going to be doing in this lesson. And the scenario is having just come back from an exhibition, I have a whole lot of fliers and leaflets and business cards. That I'd like to digitize and organize and categorize just so it's a bit more neat, and I then have a list of contacts and companies that I can follow up with and potentially start to do business with. Let's see how that would work. All right. Inside of Cha C EPT, I'm going to upload these images, and I'll show you what they look like in a moment. Here they are over here. We can see it's a mixture of just leaflets that were handed out at the exhibition. Some of them are in a different language, but here you can see there is images, there's text, there's graphics. All of this is contained in here. There's business cards. So the typical collection of things that you'd bring back from an Expo, and I essentially want to digitize this and put it into a structured format. The prompt I'm going to use is attached our leaflets and fliers. Your task is to digitize these. And some of the important parameters I'm including is to explain what the business is. With business cards, it needs to extract the names and job titles with the flies and leaflets. We want to summarize each into two to three bullet points, and then categorization, we want to group the businesses by industry, so marketing, logistics, software, that sort of thing. And priority tagging, this is marking contacts as high potential partners or clients or people to work with in the future, and it's got a priority ranking there. Now, that would be especially useful if this was a custom GPT, and we had information about who we are or who I am as a business owner or a brand owner, it would have all of that contextual information and be able to relate that back to what would be a good fit for a partner from this list that it provides there. And then, lastly, the next steps, asking it to format everything for easy Importing into a CRM or spreadsheet. And let's run that and see what we get the prompt is run, and we have the results back. And from here, we can see that it's identified one business card. Of course, this would be a much more interesting list if there were multiple business cards, but it was just the one. But nonetheless, it's been able to categorize everything and it's put it into a nice table with columns there. Then looking at the leaflets, it's given us a brief explanation. It's also translated this leaflet. You might remember this one was in German. So it's gone ahead and done the translation, as well, which is really neat. And it's given us some other key information, and it's done the same thing with all of the others there and given us some really interesting breakdowns and key points. From there, if we wanted to create it into a CSV, we could ask it to do that. But I think for the purposes of this, let's just put it into a table. And here's created the table for us, and we can see that all of the details have been placed into this neat table, and we can actually see which ones are the high priority ones that we need to follow up on. So this would be a great starting point. And see if they might be a good fit to do business with. I hope that you can see how powerful the image classification capability is with Cha CBT. This would save so much time by going through these leaflets and business cards manually, and here we've been able to do that in a matter of seconds. That wraps up the lesson. I'll see you in the next one. 17. Real-World Applications: Gemini & ChatGPT in Action: Hi there, and welcome to this lesson on just introducing you to Gemini and Cha chi BT in action. Because in the next two lessons, we're going to be diving deep into Cha GPT and Gemini, we're going to have a couple of mini projects that you can follow along with. And we're just going to put both Cha GPT and Gemini through their paces. And in the process, you're going to be able to see just how powerful these two AI models are. So for Chat GPT, we're going to create our own audiobook summary of the book title Atomic habits, and this is going to use both Chat GPT and Speechifier to make our own audiobook summaries. Then we're going to perform some competitor analysis and analyze the strengths and weaknesses of a company called Space goods and see what opportunities exist there for another company to come in there and try and beat them. So that's going to be really cool. Then for Gemini, in the lesson after that, we are going to be extracting details from an info graphic. This is going to help to turbocharge our research, and we'll be able to use that information to get a kick start on a article that we would be creating. These are very exciting many projects, and I can't wait to show them to you. So let's dive right in, and I'll see you in the next lesson. Goodbye. 18. ChatGPT in Action: Real World Scenario: Hey, guys, and welcome to another lesson. I'm particularly excited about this one because I'm going to be bringing the power of AI to you, which is going to supercharge your productivity. We're going to be looking at two of the most popular models at the moment. These AI models are Chachi BT and Gemini. I'll show you just how efficient your workday can become with these two smart AI tools by your side. So let's take a look at them. First up, we have Chat EPT. This is a versatile AI assistant and is designed to help you with a wide range of tasks. It excels in understanding and generating human like text, providing quick and accurate responses and continuously learning from its interaction. So this is really good when you have a threaded conversation with Chat EPT. It's able to retain information and learn from the interaction that it's having with you. This improves the output, and it just makes it more efficient to work with. But let's take a closer look and dive into the interface. So this is the chat interface. What I love about it is it's very straightforward. I mean, you have the input field here. You're able to connect other applications, so one drive or add from Google Drive. You're able to upload files from your computer. And it will deal with all sorts of files like images, PNGs, JPEGs, as well as documents, PDFs, word documents, those sort of things. So it really has a wide range of documentation and media that it can accept. So this is where you would put in your prompt. Looking elsewhere on the interface in the left hand column. This is where all of your custom GPTs would be found. So a custom GPT is tailored GPT that fulfills a specific purpose. You can give it its own knowledge base and combination of skills. And as we're seeing here, this is the custom GPTs from the community, all sorts of tailored GPTs. These are the most popular ones. You've got ones created by GPT. By the Open AI Chat GPT guys. But here, I mean, there's custom GPTs made for writing, for productivity, for research and analysis, and these are worth having a look at because they could give much more different results than if you were just using the standard interface of Chat GPT, because they are enhanced with knowledge libraries and maybe specific methods and processes that the creators have used inside of them. So to give you an example of what a custom GPT would look like, I have created one for this course. And once you're in there, you can edit the GPT, and over here, you just give it some basic details. It's got some instructions as well. Conversation starters. And here is the knowledge library where you would add all of the relevant documents that are going to just enhance this GPT, so it is really tailored to your needs. So here I've uploaded all of my lessons. My courses bible, which has a lot of the tips and recommendations for creating courses and that sort of thing. It has its own set of GPT instructions, and then also some master SEO keywords for some of the descriptions on the platforms like Edom, that sort of thing. So you would configure it with all of those details, and then you would be able to create your own GPT. Super handy, I highly recommended. It's not as difficult as you might think, and it just allows you to have a much more powerful GPT that is trained on your own knowledge base and documentation. So other than that, you would have all of your past chats. So if you ever needed to refer back to any chats, you would have them all listed here. Which is quite neat, you have the option to upgrade. And it's worth mentioning that the standard free version of Chat GPT is still equally powerful. The plus version just gives you access to new features. So when new models are launched, you get priority and you're able to use them. It also has a bit more bandwidth. So if there are Times on the network where a lot of people are making requests. The plus members are going to have priority, and there won't be as many delays with responses. So that just improves productivity there. It also has Dali image generation, which is really handy. You're able to create graphics on the fly, real sort of life like imagery to accompany all of your documents and work that you carry out, and of course, the ability to create custom GPTs. That's all available to you in the pro plan. But if you're just looking for a everyday assistant that's going to help you with some basic tasks, it's easy to get away and cheap to get away with the free plan. And here you would just have some more settings. You can get your GBTs a bit quicker. You can customize them, and there's some general settings here as well. You can have all of these set to how you want. So with that, let's have a look and actually create something So what we're going to be doing, we're going to really put it to the test, and you'll be able to find all of the documentation and the work guides with the prompts and everything that I've included in this lesson. You'll find that in the resources section, so make sure to check that out. But what we're going to be doing is making, reading your new Superpower. So we'll create our own audio book. And that is a summary for us to learn more effectively. So it's going to summarize the popular books out there. These could be your favorite books. There could be books on productivity or books on concepts that maybe you are wanting to learn more about, and it's a bit challenging. So Chat BT is able to break it down and make it more understandable for you. So we're going to be creating that book summary, and then I'm going to show you how to create it into an audio file. We're going to be using a text to speech tool called Speechify, and that will then create the audio file for us. We can then download that audio file and play it on our smartphones or even read along on the document, on our desktops. So it really gives a lot of versatility, and I'm excited to show you how this all works. So let's get into it. All right. So here we are Chat GBT. So we're going to create a Chat GPT book summary and make our own audio books. The goal of this prompt is to create an audio book style summary of the most popular productivity and business books to listen to on an audio device or our smartphone. So here is the hat GBT prompt. Provide a chapter by chapter summary of the following book title, and then in there, we're going to insert the book title. The format and tone should be that of an audiobook, so we already want to tell it that it's going to be an audiobook. The summaries will be converted to audio files via a text to speech tool. So consider this and try to make it flow and make the summaries sound like an engaging audio book. Then there are parameters. The chapter summaries, make sure to include key points, strategies, concepts, quotes, insightful tips, and other relevant information. Each summary should be around 200 to 500 words. We want to make sure that it's a summary. We don't want it too lengthy, so that is a perfect size summary. The summary should contain the most important aspects of the chapter. So we want to extract all of the most important elements from that. Include a bullet list of the key takeaways from the chapter. So we also want to have them listed out, so it's able to just be a bit more digestible and easier to remember. And then lastly, using the 80 20 rule, extract the 20% of the key learnings for the bullet list above. So that's just to get just to squeeze out the most important aspects of the summary. So let's put this prompt into chat GPT. And watch it go to work. So I'm going to switch back to the normal GBT here. These are all the models that you have available to you. So GBT 40, that is the most current one. It's going to be improved in the future, but this is what we're working with at the moment. It's worth mentioning that a temporary chat is where you wouldn't need to have a history for it. It's just basically a disposable chat that you would use if you wanted that. So let's keep it on the GPT four model. And let's add the prompt. We're not adding any attachments because it's not needed, but the book title is atomic habits by James Clear. This is a really good book for how to be more productive and just create habits that have a lasting effect and help you to perform at your best. Let's run this query. So it's already started generating the summary. As we can see here, it's giving us the short punchy introduction, the summary, and we're getting all of the key takeaways. Chapter by chapter for all of the chapters in the book. So I'll let this run, and when we come back, we'll be able to see the final result. All right. We have all of the chapters all laid out and summarize. We're now going to copy all of that and paste it to a document. That was just an older summary Iran, but we're going to use the most recent one, the one that I've just shown you. And as we see here, all of the chapters laid out, everything is there. And I mean, if you'd prefer to read this, I mean, it's ready for you to use, but if you wanted to take it a step further and create an audio file of it to be able to have it as an audio book. This is where we use Speechii. So let us just print Over here. We will save it there. Next, we're going to take it into Speechify. This is an app that takes text and converts it to speech. It's also got the nifty feature of having celebrities as some of the voices. You're able to have Gwyneth Paltro or Snoop Dog, or Mr. Best read out your texts for you. It's also got some advanced features where you can actually train it on your own voice. You could have your own voice reading back to you. Um, that could be a little bit weird, but if you wanted to do it, it's possible to do that. So you are able to get a free trial with this. I'm going to be showing you how it works. There are other text to speech generators, if you'd like it to be completely free. Those are also available for you to use. So once inside Speech, we're met with this screen, and it's as simple as uploading the document we just printed out. So let's have a look here. Let's get the most recent one, which is that one. Uploaded it. My story. And already it's started reading it out to us. And we've got the voice of Gwyneth Paltro which is nice and soft and soothing and a great voice for audio books. And here's the option to create your own one, but we're happy with that. You're also able to change the speed. So if you'd like to get through an audio book even quicker, you're able to do that, or if you'd like to just slow it down, you can do that as well. And there are some other settings as well, things like highlighting, so it's going to follow her as she is speaking. This sets the stage for. Introduction. Good. So if you wanted to have just to be able to read from this screen, you'd already have a much more productive and enhanced reading experience. But we want to create an audio file. So I'm just going to let it play for a little bit just so you can hear how it sounds and the speed that's taken and how it would sound My story. Audio book. Welcome to Atomic Habits by James Clear. The journey begins with the author's personal story, illustrating how small habits can lead to significant changes. James Clear shares his experience of overcoming a severe injury, which ultimately sparked his interest in habits and personal development. He introduces the concept of atomic habits, emphasizing their potential to create powerful outcomes through incremental daily improvements. This sets the stage for exploring how tiny habits can compound over time to produce remarkable results. Key takeaways, Small habits when consistently practiced can lead to significant changes. Focus on 1% improvements to harness the power of compounding. True change requires a shift in identity, not just behavior. An identity, behavior. There it is. So once you are happy with all of that, you would then want to download it. So you would head to the download button over here and choose the download MP three. You could then download that to your hard drive or a Google Drive, and from there, you'd be able to load it up onto your smart device. Or the Speech of I has an app for both Google Android as well as iPhone, so you're able to use it on the app as well. And that is the process. Within a couple of minutes. We're able to have our own audiobook, and it only took a prompt, and we were able to create a realistic sounding audiobook that has all of the key points of any book title that we'd like to learn more about. So moving on, we're going to be now looking at how to analyze a brand or a competitor and see what strength and weaknesses we can uncover. So let's take a look. All right. Here is the prompt. The goal of this is to analyze the strengths and weaknesses of the brand and company called space goods. These guys produce a kind of adaptogen coffee, so it's enhanced with new tropics like mushrooms and that sort of thing. And we're going to have a look at the business and see the st weaknesses and opportunities. The prompt looks something like this, act as a business strategist, analyze the strengths and weaknesses. And opportunities of the coffee and new tropics brand, space goods. Your task is to provide a thorough analysis of their strengths and weaknesses and provide guidance on how a new brand could beat them. We're providing the website. That is another thing that Chat GPT is really good at is it can crawl web pages for you. And these are the things that we want to consider. But we've also said, but don't limit your response to them because otherwise, Chat GBT might focus just on those. So review all known aspects of their marketing strategy and their social media presence, including Facebook, Instagram TikTok, identify weak points in their marketing strategy. What else is missing lacking? Could their Amazon selling strategy be improved? Here's an example listing. Where do they produce their products? Is there somewhere cheaper? Do they ship worldwide, and do they have a fulfillent presence in all major markets? How is their pricing strategy? Could a new brand add more value, pay special attention to customer feedback online for their products? What are their most frequent concerns and issues? So this is what we are going to put into Cha GPT. And there we will let it run. You see, it's browsing the website. It's having a look online. Doing its thing, and here we go. It's given us the full breakdown. So the strengths, innovative product offering, high quality ingredients, brand identity and positioning, subscription model, customer engagement. So the weaknesses, limited physical presence, the reliance on online sales, limits customer interaction and instant purchase opportunities. Price points, the products are priced at a premium, which might be a barrier, dependence on specific channels, production costs, manufacturing in England and using high quality ingredients lead to higher production costs. Already, there's an opportunity and market penetration. So it's given us quite a good breakdown of the strengths and weaknesses, and now the opportunities for a new brand, it's giving some recommendations. So competitive pricing, if the new brand were to introduce similar high quality products, but at a lower price point, it could open up a whole new market if they diversified the marketing channels, enhance customer experience, product innovation, expanding the lines. This is something that the company would naturally do as well. Sustainability and ethics. This is a hot topic at the moment, and Using that and tapping into that could give the newcomer an advantage community building and customer feedback. So with that, it's given us a couple of really good points. I mean, from what I can see, the main one would be to review the pricing if you were able to get manufacturers to put the ingredients together and package it and warehouse it cheaper than than what we're seeing there. That could be a good opportunity. But other than that, you have everything here. You have all of the main points that that Church GPT was able to find. And of course, you could dive a lot deeper and ask it to expand on the price point recommendation that it had. So this is the starting points of your research. This is where you would dive a bit deeper. But it just shows you that you can use Church EPT for such a diverse range of tasks that it can be super powerful, and it should be your daily productivity assistant that is right there, just waiting for you to give it its next task. So that is it for Chat GPT. Next, we're going to dive into the world of Gemini. I'll see you in the next lesson. Bye. 19. Gemini in Action: Real World Scenario: Welcome back. We're looking at Gemini now, where much like Chat CBT, it's a powerful AI chat assistance designed to help you manage tasks. It excels in understanding natural language, providing quick and accurate answers, and it also improves with time. While it may occasionally struggle with very complex questions, it remains a highly effective AI assistant that enhances productivity and simplifies your daily routine. Let's look a little bit closer at it and have a look at the interface. Here is the interface. It's a very simple laid out chat interface, and much like Chat GPT, you're able to upload images. You're able to use voice typing as well if you wanted. It keeps all of your previous chats down in the left column as well. You have all of your settings, that's pretty much it. It doesn't have anything like custom GBTs. Although Gemini advanced is really powerful in that it integrates with all of your Google apps. Sheets and documents, you're able to have access to Gemini right within those. You don't need to come to the chat interface. It will appear in documents and cells, in sheets, that sort of thing. So that is one benefit of subscribing to the paid plan. But we're going to be using the free version. And what we're going to be doing is cutting our research time into minutes instead of a few hours. So we're going to be looking at a generative AI diagram, which has all of the top companies that are currently in existence. And we can ask Gemini to just strip out what's appearing in that info graphic because let's assume that we're doing an article on generative AI companies, and we want to include all of those that are appearing in this graphic. To give you an idea of the graphic that it's going to be working with. It is this one. You can see that it's nicely laid out. There's a lot of information here, a lot of logos. And of course, Gemini is going to do its best. There are some images and graphics. I can see that it would struggle with. And in that case, you would then need to just help it along, give it the actual name. But for the most part, it looks like the majority of these we're going to be able to extract. Let's take a look. Here is the prompt. We're going to be saving time, researching and infographic. The goal of this prompt is to create a list of all the generative AI software tools, and here is the prompt. You will be provided with an infographic, the file is attached, that contains logos of the top generative AI companies at the moment. Your task is to provide the AI software name, the URL, and a brief one line overview of the AI tool. This will be used for an article. I'm creating about generative AI and the best AI tools currently available. The parameters, so we're just giving it some additional instructions. The logos are neatly grouped based on medium produced and segmented by use case within each medium. Ensure you keep to this grouping. So we'll copy the prompt. We'll come into Gemini. We're going to upload the image over here. We're going to add the prompt, and we will run it. So what it will do, it will use the vision model as part of Gemini, which is going to recognize the text that is found within the image. So it will look at both the logo. If it recognizes that, as well as the text, if it can see what text is written there, it will then be able to use that to create the information that we're looking for. So here we have all of the options or all of the companies. Let's just go back to this one so we can compare. So co generation and documentation over here, replete Tabnin, D build. It has skipped a couple of those ones there. In this instance, you'd go back and ask it to maybe have a look at those or to help it along I would recommend doing a screen capture and just going row by row. But if you just wanted for it to pick out a handful of the best ones from this, this is how it could do it really easily. So we have the customer support, general writing and content editing, general writing, marketing and sales. So, as you can see, it's done its own categorization. It's kind of moved the tools under different categories. So write Sonkea, general writing, where Wright Sonic was under marketing and sales copy. So it's taken the liberty of doing its own categorization, which might work a bit better. But in that case, if it didn't do what you wanted, you would just ask it to be a bit more strict with the categorization. But otherwise, it's done a pretty damn good job. I mean, it's extracted out everything. It's recognized the logos or it's seen the text, and it's put this into a very, very comprehensive list of the generative AI tools available. So that would then you'll be able to use that in your article. If there was a couple that were missing and you absolutely needed to have them, you would just go into a bit more detail and ask it, pay more attention to those specific groups that you're looking at. But essentially, that is it, and it just shows you how versatile this tool is, Gemini. It's able to do anything just about, but something as simple as extracting all of the logos and the companies and the tools from an infographic. I mean, having to do that by hand manually would take a good couple of hours, just by plugging it into Gemini, we were able to bring that up in a matter of seconds. So huge time saver there for research. And that's just one of the many features that Gemini can offer. As you can see, huge productivity tool, and it's definitely something to consider. So I'd love for you to have a play around. Remember, these work guides are in the resources section of the lessons, so you're able to use the same proms and just see how it works for you. But I hope that this could show you the potential and the power that these AI chat assistants do have, and I hope you integrate them into your workflow and see the benefit that they offer. That's it for this lesson. I'll catch you in the next one. Bye. 20. Automate Your Workflow with GPT for Sheets and Docs: Hey, guys, and welcome to another lesson. We're going to be looking at a plug in for Google Workspace. This is the GPT for sheets plug in. And this brings the capabilities of GPT two sheets. Now, as you can imagine, that opens you up to a whole world of opportunities to work with bulk data. It allows you to manipulate the data, as well as generate text. But not just that. You're able to classify information, write, edit, translate, extract, summarize, All of the powerful functionality that Chad GPT can provide. It's able to do this in bulk now with your Google sheets. So let's take a look and see what it's all about. To find GPT for sheets, you would just need to go to the Google workspace marketplace and install it onto your sheets. Any sheet that you have, you are able to see the option in the extensions menu. And going down to add ons and then get add ons that then brings you to the marketplace, and from there, you would search GPT for sheets. Well, let's take a closer look at this. From what you can see here, we have a example sheet, and what we're going to do is look at some of the outputs that can provide. So we're going to apply a simple prompt to many cells. As you can see here, it's giving us the formula. And what you will see is that once we have this plug in enabled, we then get the GPT formula available to us. And with that comes all of the parameters that you can use. So for a simple prompt, we would just add the GPT. And we're going to write a tag line, and we're going to take it from A 22. So it's going to write a simple tag line, and it's using row 22 and column A. And after a while, it gives us the tag line for a car. Quite simple, but where the power comes in is you're able to then drag it down and apply it in bulk to all of these rows. So if we drag it down, it then starts running those proms on each of the rows. As you can see, it's done that all for us. And within a matter of seconds, we were able to have all of those values populated. Another example is to fix mistakes. So typing errors, typos, grammatical errors, that sort of thing. So the command is GPT. Edit. I'm having a lot of trouble seeing the microphone or the keyboard through the microphone here. I'll do my best. And we want to Use row 19 and Column A. So it's going to run that, and we're asking it to fix the mistakes. Again, we can run that for all of the rows. Very ent, as you can see, it's made all of the corrections. It can be used for translation as well. Data preparation. What's quite neat here is we're going to use the extract formula to try and get the e mail address from this cell. So let's come in here. A 43, and we want the e mail address. So let's have a look. We're expecting John Smith. There we go. And that's extracted for us. We can then run that down for all values, sir. This is so handy. If you had data that had come in, and it's in a very messy format, you're able to within a matter of seconds, just clean it up with the power of Cha GBT. Analyze, we can summarize long content and reduce it into a summary as long as we want, less than five words, that's pretty tight, so let's move it up to let's say 15 words. So we'll just run that. And there we go. It has provided the summary, but it's given a bit more in the way of wording. And you're able to categorize things like customer feedback, analyze sentiment, which is really good. So if you had a whole list of reviews that came in, or you're wanting to bulk edit some reviews that have come in for your brand, you're able to do that in a very quick way and know which ones need your attention first. Then one last trick I'm going to show you here is using the Chat GPT vision. So you're able to take images and chat GPT. We'll be able to understand what that image is about and output it to your cell inside of sheets. So very, very nifty. Let's run this one. So we're looking at B 15 and C 15. So it is going to download the image from the URL. And then it will provide us with a product description for this. Let's just scroll out here so you can see bet. Right. There we go. Let's just stretch this out so you can see, experience the ultimate comfort with these classic black crock clogs, featuring a lightweight durable design with ventilation ports, breathability, all of that. So it's created a very neat and nifty description there. So these are just a couple of examples of what is possible with this great plug in GPT for sheets. There is a small cost to it, and if we have a look at the packs that you're able to buy. It becomes very, very cost effective when you're working with large amounts of data. Here, I mean, $29 for up to 29 million tokens. Of course, you can choose the GPT model that you'd like to use to further increase the cost effectiveness. Some models will cost more per run than the others. So you do have those options there. Minor cost. But if you think of the capabilities and the time it would save, it does make it a very cost effective tool. And the fact that you can do it in bulk with Google Sheets is just absolutely super. This is one tool I highly recommend. It is GPT for sheets, and I'd love for you to take a look at it and play around. They do offer a free trial. So see what you can do and see how it can help you. That's it for this lesson. I'll catch you in the next one. Goodbye. 21. Optimise Your AI Interactions: Simplify Prompts with PhraseExpress: Welcome back to a new lesson on Phrase Express and how I can help you with all of your chat GPT or Gemini prompting needs. So in the lesson, I'm going to be walking you through how I use phrase Express to set up all of my prompts so that I can standardize them and also have them easily accessible. It saves a ton of time, and it just makes sure that I use the same prompts again and again, and it is just a great way to save time. So we're going to be looking at a collection of the most common chat GBT prompts. This will show you how you can use phrase express to just organize and set them up. We're going to create a handy all in one prompt using the prompt framework. And you'll see that it's a very versatile prompt that will automatically output the selections that we make. So it's a dynamic prompt as well. Then you're going to learn how to assign an auto text and hot key. So that is where you can quickly access all of your prompts, and from there you're able to get the one that you need in the quickest amount of time. So this is a really cool tool just to enhance your Chat GBT experience, and it's easily done with phrase Express, so stick around, and we're going to look at how to do that. So we're back in Phrase Express, and I just wanted to show you how I use it with Chat GPT and Gemini. So, if we have a look here, we've got some prompts that I've set up. So much like phrases, where you can have a boiler plate, which will spit out a bit of text. You can use it for prompting as well. So you can either have just a generic text prompt, which outputs a predefined prompt that you set, or you can get a little bit creative and start to have inputs and build out a prompt based on selections that you make. So for the first example, this is a act as prompt. So we are choosing the role, and then we are choosing the action. And then we are choosing what the topic is. And then we are going to ask it to display it in a specific format. Now, you could type this out normally, but it just makes it a lot more dynamic and powerful when you have it already set up here. It's just going to save a bit of time, and you have all of the lists pre populated. So it's just a really more efficient way to do it. So let's take a look at this in action. So if we put in the auto text, we then get the context menu where we can start to choose all of our prompts, and let's go into the first one. So I'm going to head tab. It then brings up the input form. So act as this is the role that we want the GBT to take on. It's going to give more personalized, more tailored, more relevant responses to that role. So here we are going to say, let's have a look copyright mindset coach. We're going to choose that and create. So this is the action it must perform. Here are all the options, essay, recipe, add copy, headline, et cetera. So we want to let's say do a summary. And now the topic is going to be how to beat procreation. How to be procrastination, and we want the format to be in marked down. So that's it. We are happy with that, and then we click. And it's basically created that for us. Then we can run the prompt. And there it is. It's giving us the output. And some really cool sections here. It's broken it down. We've got key strategies to overcome, set clear goals, prioritize. So that's just a nifty little way to have all of the roles kind of set up there. And of course, you could write that out and type that out. But having it there means that you just have all of the options available to you. So you're not missing out anything, and it'll standardize the response each and every time. We jump back into phrase express. Let's look at the next one. So we're going to create a e commerce product description. So here is the prompt that we've laid out. So act as an ecommerce copywriter, write a 300 500 word product description, and then adding some relevant details, benefits it might have, all of that. So we've added in all of these parameters and considerations for the GBT to use when it is crafting its response. And then lastly here, We will have the input form, and that is where we will add the products. If we add more than one, it's going to give us descriptions for more than one product. But for this example, we'll just use a single product. So let's hop it over to Chat GBT and give that a try. So we come in here. It's going to be a height adjustable bamboo standing desk, and there is some information there as to its size, so we'll run that. And then, as you can see, it is spitting out the product description. Of course, I've asked it to use the pain agitation solution framework. So from that, it's given quite a comprehensive description that we could use. Of course, in this state, it's not ready to use. I would need to go in and edit it and just polish it up and make sure that it is really ready for an E commerce website. But at least there it's given you a very solid and very well structured description to work from. Okay, so if we come back here, the next one is asking ten questions about a topic. So this is a prompt that you can use just to understand more about a specific topic, and these will be questions that you can ask. It's good to use these with ChachBT and Gemini because it shows you some of the things that you might not have thought of. So it lists all of the questions, and it just helps you think more on the topic and come up with more information around it because then what would happen is those questions you would then use to formulate a new Chat GPT prompt, where it would cover everything, and it would give a very fully inclusive and comprehensive response. So if we go back to Chat GPT, And I think what I'm going to do, just to save a bit of time here is create a hot key for this instead. Let's do P for prompts. Right. So we want to next go into the question topic. So what is the topic? Let's keep it at AI productivity, but you could add anything you want to, and we'll ask it. And there is just giving us the response. And this would just help us dive a bit deeper into the topic and just be able to ask Chat GBT the right questions to be able to get the right answers, essentially. Okay. So the next one is if we compare in contrast. So this is to outline the similarities, differences, qualitative characteristics, quantitative factors, functionality, impact, key takeaways, and other factors into a table. And an example of this would be a B, Apple Microsoft or things like that. So if we head over to Jach BT, all right. So we're going to compare the tests, the texts. So here, instead of Apple vers Microsoft, let's say click up and Trello. There we go. And we're going to submit that. So there we go. It's coming back with its response and it's just giving a really cool breakdown of the differences between these two software. And that's just a great prompt to compare two different topics. So, yeah, I think you get the idea here. Um Here's another example. So I want to learn about a topic, identify and share the most important 20% of learnings from this topic that will help me understand 80% of it. This is a classic one, and this is from earlier lessons, as you might remember, the Perito principle or the 80 20 rule. So this is a prompt just to really get out the most important aspects of any topic very quickly. Here's another one. Your role is that of a problem solver. Give me a step by step guide to solving, and then you insert your problem. And then here we can summarize content as well. So all the text you would add there. This one we can actually run. So let's just Let's just do this one quickly and just to show you. P summarize, and here. Let's come in here and bring up this tips and tricks of using text expanders. So it's just summarizing everything from this really lengthy script. It's just taking at the key points and making it a lot easier to read and understand. And that's it. I mean, this is one way that I use a phrase expressed to enhance my prompts and use it more effectively in Chachi BT and Gemini. It just means that I have all of the prompts ready and waiting and organized. And I really find it to be helpful, so why not give it a try and see if it helps you. That's it for this lesson. I'll catch you in the next one. 22. Best AI Powered Tools: Hi, welcome to another AI list, and we're looking at some of my top AI powered tools, because generative AI is not just restricted to a GPT or Gemini. There are some really clever tools out there that unlock the generative AI models like Cha GPT. So we're going to look at three of these. These are my top picks. The first one is in video that allows you to create videos just from a prompt. Means you can turn scripts into professional videos easily and with the power of AI, as well as customize them completely with stock library items such as stock videos, graphics, Jeffs, audio, and much much more. Then write Sonic. This is a very powerful tool that allows you to create product descriptions, as well as generative text and creative writing. It is a top tool for content creators, and it really makes it easy to do all of these creative tasks using AI. What's more is that you can also create images, as well as audio, that is text to speech, so you're able to convert your spoken words into a AI generated audio file. That is really nifty. And then lastly, Otter AI. This is a meeting companion that is incredibly smart and uses the power of AI. To transcribe your meetings so that you can easily refer back to them. It also records the audio of your meeting so that you're not just having the transcription. You can have the audio file as well, but the transcriptions are searchable, and it has a speaker identification, so it knows exactly who is in the meeting. And it's just a really great tool for meetings as well as interviews. And it's just a really great tool to have with you when you are having a meeting. So let's dive into these tools and see what they have to offer. 23. Powerful Video Creation with Invideo: Hey, and welcome to this lesson on in video, where we are going to be looking at this incredibly powerful AI video generation tool that makes professional AI videos just from the scripts that you provided. It's an incredibly powerful tool, and you also have access to a stock media library to access things like video as well as audio, to just personalize and enhance the AI created videos. So one of the best features is the text to video generation. You're able to instantly create videos from text prompts. So that means you don't need any video creation skills. You just describe your idea and let AI do the rest. Then it features intuitive editing with text commands, so you can make edits using simple text prompts, which means you can easily adjust your video without complex software, making it perfect for beginners and experts alike. It also has multi language support, so you can create and translate videos in 50 languages. This means you can have a global reach with your videos. A really cool feature is a voice cloning, so you can train it on your own voice so that you can add voiceovers to all of your videos. So this would save time on recording audio for future videos as you would just then only need to have text This saves time on recording future videos, as you would only need to provide a script, and the AI clone can speak the rest. It also has a massive stock media library where you can access over 16 million stock media assets. These are great to enhance your videos with high quality images, videos, and audio. These are all searchable via AI as well. So this is just a super cool tool, and it's so simple to use, but yet so powerful. And if you are into making content, which is video, it makes that a breeze. So this is definitely one of those AI tools that you need to check out, and I can't recommend it enough. So make sure to give it a try and see what you think. But that's it for this lesson on in video. I hope it was insightful, and I will see you in the next lesson where we are going to be looking at right Sonic. That's it for this one. See you in the next one. Good bye. 24. Effortless Content Creation: How AI Can Write, Design, and More with Writesonic: Hey, and welcome to another lesson. This is the right Sonic lesson, and it's a very powerful AI platform that has a whole lot of tools that can really help your online content creation, and just allow you to interact with an AI via the chat interface. So that is done via the internal tool called Chat Sonic. It's a lot like Chat GPT. It's got a prompt field, so you can just have a conversation with the hatsnic bot. And it'll give you replies much like you would see in Chat GBT. On the back end, it is connected to Chat GPT, so you get all the power of the open AI language models, as well as Chat Sonic, it has photosnic, which is great for creating stunning visuals. It also has audiosnic, which is great for professional sounding audio. And another nifty feature for content creators and website owners is that it has a suite of SEO tools. So you're able to analyze your content based on keywords, as well as competitors to be able to see how it ranks and how you can boost your rankings through AI and get the recommendations for how to do it. So Without further ado, let's get into it and take a look at right Sonic. All right. So here we have the interface. As you can see, everything is laid out. We have some pinned templates here. This is where any of your most frequently used templates would appear. We have other links to different tools here as well. If we have a look at the menu bar, we have the history, so you're able to find any previous chats. It keeps all of them for you, so you're able to retrieve them easily enough. The AI article writer. So this is where Right Sonic really shines in that. It has an incredibly effective and powerful article writer. I mean, the whole Right Sonic system is really based on this, and it's kind of their flagship tool. So my current plan and membership, it doesn't have access to the article writer. However, I didn't want you to miss out on what it looks like and what it's capable of. So I'm going to show a demo. That you are able to see what you could achieve with Right Sonic. Tired of AI generated content that feels generic and disconnected. Introducing Wright Sonic's AI article writer, where every word counts, and every article generates traffic. Bid farewell to outdated hallucinated content. Wright Sonic brings to the table real time factual content, complete with trustworthy citations. Enter a topic. Pick your language, and let Wright Sonic learn from your competitors or your own data. Pick trending keywords, An engaging title and an outline generated after extensive web research on your Topics intent and your competitors top ranking articles. With writ Sonic, your content resonates with your brand's unique style and voice. In under 2 minutes, create concise blog posts or in depth reports and articles. All SEO optimized, ready to impress your customers and rank on Google with automated internal linking with the option to choose Article length 500-5 thousand words. Watch your content climb to the top of Google search results, surpassing competitors. Your journey to Content Excellent starts now with WR Sonic. There, you're able to see it is an incredibly powerful platform, and I mean, for content creation articles, it could not be easier to make powerful resonating keyword rich articles that can help you rank, and this tool absolutely is able to do that for you. So let's get back into write Sonic and move on to some of the other features. So the knowledge base. This is a handy little section where you're able to add text snippets. So things that you reuse a lot, you would add here, and you can then call them up inside of hatsnic, as well as across the platform, wherever there's the option to add your own content or a prompt or anything like that. You're able to access all of your snippets here. Same thing with documents. You can upload PDFs and that sort of thing. To be able to easily retrieve them when you are on the platform, either through a chat sonic prompt or anywhere else. So let's move on to Chat Sonic. This is the bread and butter of write Sonic. It's the Chat GPT style interface where you can run queries and prompts. So you're able to upload documents as well, upload images so that it can read the images, upload audio as well, add URL so that it's able to cl the website. So let's give it a prompt, an example prompt. I'm just going to copy this one that I've made up, so this is for a fictitious ultimate productivity tool called Booster Pi. We've just asked it to act as a professional Ecommerce copywriter. We've given it the brief and given it some instructions there. We've given it a brief description of what it does and how it works. And also included some keywords that we want to organically weave into the description so that the final output is SEO optimized. So let's just copy that, add it to the prompt here. An Nifty feature here is you're able to improve the prompts. So it is rewriting the prompt based on best practices. So it's just added some different sections and tweak the placement of certain things. So now we're able to send that message, and it will reply back with a detailed and SEO optimized product description. So as we can see there, we made a point of saying that we want bullet points because we wanted to be easily readable so that somebody who might prefer to just skim through content can pick up all of the bullet lists, but it also includes all of the sections of text, the paragraphs, and inside there, it will have the keywords that we defined as well. So from this, you're able to get a 500 to 600 word article. If you wanted a 2000 or 3,000 word article, you would just specify that. But within a matter of minutes, it was able to give us a very concise and comprehensive description for this fictitious productivity tool. And from here, We would add a few elements. We would make sure it's engaging, we would add media, and after that, it would be ready for publishing. So, already, in a matter of seconds, we were able to get a description. So as you can imagine, that could be a huge time saver for content creators. If you're running a website, that sort of thing, that would be the tool to to go to. So let's look at some more of the features. So these SEO tools, they're not available on my plan, but we can still have a look and see what they would look like. So here you would optimize and check for search engine optimization. And here you would add in your content, or you could even start to generate content for it to check. So you're able to humanize it as well. Rewrite it. So if you took a article that is already in existence, you could rewrite it and just adapt it for your own needs. SEO, it's got other tools there, which we can't see at the moment. So you're able to do keyword research. This will give you the amount of volume on a specific keyword, so the amount of time that's being searched and the difficulty of ranking for that keyword as well. Topic clusters. This is another nifty little feature so that you can get keyword clusters to see all of the related keywords for a specific cluster. AI content Gap analysis. So this will take the article, and it will compare it against other articles out there, your competitors, whoever you want to compare it against, and it'll give you a breakdown of what is missing and the opportunities to rank higher than your competitors. Answer the people. So this is really great for idea generation and coming up with topics to write for, you're able to enter a topic or keyword, and it would expand those to all sort of related keywords and topics. So you can get a good coverage of the content. Then photosonic. This is where you're able to use it to create visuals. Some really good examples here. As we can see, you would add your prompt, and this would include all of the elements that you want to see in the image. Again, you can also enhance that. And recent generation. So this is what the community is doing. These are examples of the images that you can create. So really stunning graphics here. Of course, with each one of these, you can see what the prompt was for that. You can in essence, recreate it for yourself. So you would try this, and then it would preload that into the prompt, which is pretty cool. Audiosnic. This is a great way to have text to speech. So if you maybe had a blog article that you wanted to paste in here, it could create the audio, so it would transcribe it word for word, and you're able to change the characters, so you could have all sorts of different sounds. Welcome to Audiosnic. You go to platform for human like text to speech experiences. So, as you can hear, I mean, that is incredibly realistic. That does not sound like EI at all. Welcome to Audio Sonic. You go to platform for human like text to speech experiences from the bustling city of New York to the serene Landscape. So definitely human like, and you'd be able to choose any one of those avatars to be able to use, generate the audio, and that could accompany your videos or any other content where you need some real professional sounding audio. So that is it for the best features. There's one last thing I'd like to show you, and that is the integrations. You are able to integrate write Sonic with wordpress. So if you're running a blog, whether that's hosted on wordpress.com, or it's a self hosted blog. You're able to use it to publish contents. So whatever prompts and articles that you're generating, you can push them to your wordpress blog straightaway. Same thing with Zapier. It just gives you the option to publish content to any platform that Sepia is connected to, and then you're able to connect it to Google Search Console. So that is really great for just checking the search engine optimization factors and ensuring that your content is going to rank as high as possible. So that is it for right Sonic. I mean, it's one of those platforms where it's kind of like a Swiss Army knife, but it's an AI powered Swiss Army knife. So you're able to get a lot of tools here for a relatively low price. I'm currently on the Chat Sonic plan, which gives you access to all of this. It's got GBD four, unlimited generations, Google Integration, all of that, and that is at $12 a month if you paid annually or 15 if you're paying monthly. So it's at the moment, $5 less than had GBT, but you get all of that extra functionality. Now, if you were to move up to the individual plan, this is where you start to get access to the AI article writer, some other elements, the article re writer, all of that, you get all of these templates as well as credits as well. So if you only needed to use the writer six version, a few times, then you'd still have access to that. You've also got higher quality for the photosnic images that you produce. That is right Sonic. I hope this can give you just a taste of how powerful it can be and just how much productivity you would gain by using a AI power tool like this. So that's it for this lesson. I'll catch you in the next one. Bye. 25. Automate Note-Taking in Meetings: Boost Productivity with Otter.ai: It's a new lesson and a new AI tool. We're looking at Otter AI in this one, which is a super smart AI powered meeting companion. So it is able to transcribe your meetings, so you never miss an important detail. It's also got some other incredible features such as real time transcription, so you can see the transcription happening as you're having the meeting. It has speaker identification, which means it knows whose voice is speaking, so it can properly transcribe the meeting. You're able to search highlights. So once the transcription is created, you can then search it for specific highlights and text that is relevant for you. Audio recording, it has a full recording in audio format of the meeting, which is really good if you need to refer back to it. It has all sorts of sharing and collaboration. It has automated summaries as well. This is a great way to get the minutes of a meetings. So if you weren't able to attend, you could simply get the summary, which is a quick review of everything that was discussed. It then has seamless integrations with all of your favorite tools. So of course, it works with Zoom. It works with Google Meet, it works with Microsoft Teams, and it can also integrate with tools like Slack and Salesforce and HubSpot and all of that. And lastly, it has multi language support, which means that you're able to speak in your native language, and it will transcribe perfectly. So this is an incredibly powerful tool for meetings and collaborative work spaces where you are able to bring the power of AI to your meetings and have these great features. So this is definitely something to look at if you're in a team It has a free plan as well, so you can test it before you commit. And it's just a great tool that I think is going to make your life a lot easier. So if you're one of those people that has a lot of meetings throughout the day, this is definitely the AI tool that you want to be using. So that wraps up this lesson. I will see you in the next one. Good bye. 26. Using ChatGPT Canvas to Boost Your Productivity and Reporting: Hey, guys, and welcome to this new lesson. We're going to be looking at Canvas today, which is a new type of feature that ChaGBT has introduced, and it just allows you to be a bit more interactive with the responses received from ChaGIBT. So as you'll see, we're going to dive into the Canvas interface in a moment. But you'll be able to see how we can interact with the responses that we receive from ChaGIBT as well as do some really cool things like edit some of the content, make it more creative, edit the formatting, shorten it, as well as a few other tips and tricks, which I'll cover in a moment. So without further ado, let's jump in and have a look at Canvas for hat GBT. So as you can see here, on the interface, to be able to access Canvas, first of all, you would need to have a Chat GPT plus account, so that is the paid account. Once you're there, you're either able to simply select it as one of the models. That takes you into the Canvas interface, or you're able to access Canvas by just requesting it in your prompt. So let's have a look and see the interface and just what to expect. So here, we're in the Canvas mode, and I'm just going to put in a random prompt. So I've got this ready and waiting for us here. And it's a prompt to create an article. You're a content marketer, write a 500 word So optimized article 0N the benefits of using neutropic infused coffee to improve focus at work. The tone should be friendly and informative, include interesting statistics and other snippets of information and place it throughout the article. Also include the bullet lists and key points for readers that want to skim. And then I've included a bit of a catch for Chat EPT to look at, which is that it should read like David Attenborough narrating a wildlife documentary. So let's see what we get from that. So as you can see, already, it's expanded out the interface. So we are in full canvas mode now. And as you can see here, it's done a pretty good job of just laying out everything. I mean, from an outline point of view, that looks pretty good. Obviously, for the best results, it would need to be humanized, so to go in and do all of the editing. But this is where it becomes super powerful because you're able to start editing right here in the interface. So on this window, you can see you're now able to have different context windows and menus. So you're able to select AskchatGBT on a piece of the response. So here, I could say, make it more creative and concise. So what would happen then is it would update it right there in the window. The same thing can be done with bigger parts of text. You can say, expand this for more detail. And then it would go ahead and basically just expand that out to provide more information right there in front of you. So it's doing this, and then it is re writing with the input that it received. So it's edited everything out there, and we're able to see it's gone in and added a few more details. So having a look at the other options that you can work with, if we go down here, there is another context menu with a few actions here, and you're able to add emojis. So if you wanted to take the document and just spice it up with some emojis, it's able to do that. I can do the entire document or just a piece of the document. But as you can see, it's pretty liberal with the emojis that it's putting in there. So it's probably one to use sparingly. But if you're somebody that is expressing their words and enjoy using emojis, then you're going to love this feature. Alright, so moving on to the next one. So once you're happy, once you've done all the editing, and also you're able to do a bit of formatting, basic things like making text bold, italicizing and then changing the heading level, which is really great when you're putting together a document, especially if it's intended for the web because you can have all of the headings properly formatted. So if we wanted to say, right, well, we're happy with this version and we want to come here and add the final polish. It would then just adjust the titles formatting and just make sure that everything is the same. So it keeps that consistency, which is really good just to make sure at the end of the article that everything is consistent. And another function on this context menu is the reading level. So if you wanted to have the reading level intended for a different audience, so maybe it was a younger readership or it was a more advanced, more technical document, you're able to increase that level. So if we wanted to move that up to a grad school level, we could. If we wanted to move it up to college, you get all of these options to be able to do that. And if we click the college level, Okay, so you would need to select the entire content, and then let's move that to college level. And there we go. It starts to just rewrite it. And let's have a look here for those of you for a quick overview. So it does the subtle changes. Obviously, it swaps out some of the words. So there you can see it would just adjust the vocab, the terminology, and just the overall readability of the article based on who would be reading it. Then we can adjust the length. So if we wanted to really just shorten this down, we could reduce the length. And what would happen is it would come there and just do some serious edits, and already there, it sort of reduced that down to probably almost half of the size. So that's really effective if you wanted to just take a really sort of bloated piece of content and just reduce it down for brevity and conciseness. And those are the context menu functions over there. Then I wanted to show you how to get a bit more interactive and use some more powerful features. And for that, we're going to be looking at some reports. So we're going to create a fictitious report, and you'll be able to see just how that works inside of Canvas. So I've prepared a prompt for us. Let's just start with a new chat here. Put in the prompt. So we're going to be creating some dummy data for a fictitious ecommerce company selling a unique kind of coffee. It will consist of product sales globally, broken down into territories. Ensure you include charts. Once completed, then creates an executive report from the report analysis. So this would be really helpful if you are wanting to take your own data and use that to generate summaries, executive summaries, reports, gather insight, that sort of thing, it becomes really powerful and even can help you with creating the charts for the summaries and reports. As you'll see, it's able to do that, as well. So let's have a look. Let's send the response off. Okay, so it's analyzing at the moment. It is creating the data on the back end. We can actually have a look at this. This is where it's creating everything, and then immediately it pops into Canvas mode. Let's just close this just to be able to see. And here we have it. So on the right hand column, we have the text output, which is the summary. So it has taken down all of the information from the data that it created. So this is the data that it made for us. And then created the summary and gave us some really, really cool insights and overview. So, I mean, as an example, here, the challenges in cost management, the Asia Pacific region had one of the lowest profit margins. So it's able to really dive into your data and provide strategic and well guided advice. So once we have that, then of course, have access to all of the same functionality. We can then ask ChachiBT to edit or explain. We can format things as we want. So if we were happy with this, what we could then do is, create a word document. And then what it would do is create that document for us so that we could edit it further, or even just email it as it is. Here it is. We can download that. Let's save it in there. And if we have a look, there it has everything all nicely laid out. And you'll notice that we don't have the charts in this saved file. And that's just because the canvas can't handle that at the moment. It's likely to be a feature in the future. But what you can still do is save those charts and images. So if we say, we want to have this one, let's call it chart three. We want to have that one. But we want to have a bit more of a visually interesting chart. So I'm going to ask ChahPT to create a stacked bar chart for product sales across the top five countries. Top five countries for the last 12 months. Okay. So I think this is going to give it a bit more information so that it can format the chart a bit better. There we go. Right. So there we have the chart, and from here, we're able to download that. That's looking much better. So let's then switch to our report in Microsoft Word. And from here, we're able to place the charts as we'd like. Where is it over there? So we would come in with this one, and then we would come in. With the strategic recommendations, just as an example, just throwing them in here in random places, let's go for chart number four. So there we have it. Within a few minutes, we're able to take all of that data and create quite a comprehensive executive report that we can then pass on to stakeholders. And this was all done with power of canvas inside of ChaPT. And that is canvas. So that was just a brief introduction into some of the cool functionality that you can achieve, and that's possible with Canvas. Another thing to note is a very popular use case is that of programming and coding. So it becomes an incredibly powerful coding assistant. It's able to render the code as if it was a browser, so you get a web view of the code that you are creating and producing in real time. I'll cover that in another lesson because it is really good to see. But for this lesson, it was more focused on the text editor side of things, creating reports and also the data visualization. So I hope you were able to see the capabilities and the power that Canvas can help you with. So that wraps it up for this lesson, and I will see you in the next one. Goodbye. 27. Using ChatGPT for Email Summaries from Long Email Threads: Hey, there and welcome to this lesson. We're going to be looking at how to get up to speed with a message thread. There might have been situations where you were out of the office or you had an important project that you need to attend to, and there was a whole load of emails that were passed between team members and yourself being included or CC on the messages, and you need to get up to speed with everything. One way of doing it. The manual way is reading through all those message threads and just understanding what was said and who it was said to and what's needed going forward. That's one way of doing it. Of course, the most efficient way to do it is to use chat GPT, just to extract out all of the information that matters to you and that you need to action from. So let's have a look at how you would do that. Look at the email we're going to be working with here. It is a multi thread email, so there are nine messages in total. This, of course, works much better with longer message threads and where there's multiple people involved, there's only two people in this message thread here. So it's a simple example, but you'll get the idea of how this works. So all we would need to do is print the email out, save it as a PDF. And this is how it will look before it's saved as a PDF, and then you're able to work with that quite easily. So once we have that PDF, let's hop into Chat GBT. And from here, I'm using the four oh mini model, which is really quick and fast. So it's great for kind of simple tasks that you need carried out during the day. And what we're going to do is we're going to paste in that email thread as well as a very simple prompt that's going to just ask it to get me up to speed, analyze the provided PDF. I then want to know all the participants. I then want to know the timeline to map out all of the events that were happening. Key points, summarize main topics, decisions and action items as well. This is quite important. And then obviously action items will be included there as a separate list, which is really important. Tone, just to kind of get a feel for how it's being received by everyone and the overall mood. And then, lastly, any attachment links that were included in the email attachments. So I'm going to run this and then we can see how it creates the info. So from that long email thread that would have taken maybe ten to 15 minutes to go through or a bit quicker if you're a speed reader. But here we have a very simple breakdown of everybody involved in the conversation, the participants. We have a timeline of events, which is really good if you need to point out specifics or action things based on when they were done, here we're able to see everything. Then all the key points were listed, action items for everyone involved. And the overall tone and attachments. So that pretty much has everything we need. We can quickly skim through that. We can then decide from this email, is there anything that we need to get involved with? What are the action items, all of that. And we were able to do that in a matter of minutes with just a couple of clicks. So this is one quick and easy way to get up to speed with large email threads. I hope you enjoyed the lesson, and I will see you in the next one. Goodbye. 28. Using ChatGPT for Brainstorming & Mindmaps: Hey, guys, and welcome to another lesson. In this lesson, I'm going to show you how to use Chat GPT, as well as a custom GPT, to be able to come up with original ideas as well as brainstorm using a mindmap. This is really good to be able to lay out an idea and be able to just expand on different subtopics and create a whole mind map of the ChaGPT is incredibly quick at being able to create all of the subtopics and nodes around a parent topic. So in this example, we're going to be coming up with a business idea, which is for online coffee brand. And you'll see just how quickly HAGPT can develop all of the subtopics and the nodes that we would use for our mind. Let's get into the lesson and show you how to use HAC IPT, as well as a custom GPT called Whimsical to create stunning Mind Maps. Whimsical is a free to use application. It also has a custom GPT in the GPT store, which means it's available for you to use. And this is just one of the best that I've found, and we're going to use it to come up with our own original mindmap. So to get there, let's start in HACEPT. We're going to be using the 40, mini Model, which is just great for everyday task, sort of simple application that you need to use, and we're going to be asking it to come up with a business idea for an online coffee brand. So I've already created the prompt. It's over here. You're a business strategist. Help me brainstorm a new business idea for an online coffee company, use innovative ideas for 2025 and provide the nodes and topics for a mind map in a list format that I can further use to brainstorm. So we're going to run this prompt inside of Chachi BT. So here we are. We're going to paste it over here. And what's going to happen then is it's going to give us the entire all of the topics as well as the subtopics that we can use for a mind map. Now, the next step is to create this mind map. So there's two ways of doing it. I'm going to show you both ways. But the best way that I found, which has a lot more detail is to use Chat GPT to ideate all of the nodes and subtopics for the idea or the task at hand. But you are also able to use the actual custom GPT. So let's start with the second one first, and to get to this custom GBT you would just open up your sidebar inside of Cha GBT, and from here, you can go to explore GPTs. This then opens up the marketplace where you can see all of the available GBTs. And from here, we're going to search for whimsical and there it is the first one. So this just gives an overview of the custom GBT, and we're able to see the ratings as well, which is quite important because anybody can put up a custom GBT. So you want to just make sure that it has good reviews and it's working as people hoped it would. So once we have that, you can add it to the sidebar. I've got it already added there. So once it is there, you're able to access it from your GBTs list over here. So because I have a few already, I need to go to the Seymour section, and from there we have whimsical diagrams. So the first way to do this is we can run that prompt inside of the whimsical diagrams GBT. So let's do that. And I think let's just go back to the prompt and add it here. And then it will run that for us, creating all of the subtopics and nodes that we would need for a really simple mind map. So then at the end of that, would you like me to generate a mind map? So we'd say, yes. And it's then going to generate the mind map from all of those topics. So, I mean, as you can see here, it's doing a really good job. It's got some sections for innovation, customer experience, technology, sustainability, all of that. And then here we just need to authorize this. Once we allow, it starts the action, and it starts doing everything on the back end. So it's making the API call to whimsical. And from there, you're able to see it has created that, and we can actually load up that mindmap and it's there waiting for us available to start further brainstorming or mind mapping. So that's one simple, quick and easy way to do it. The other way would be to use Cha HIPT which we did before. So we're going to come out of whimsical, and we're going to go back to our query that we ran initially. That was the first one. So here, as you can see, we got a lot more detail in all of this. I mean, we got ideas for subscription models, ethical sourcing, that sort of thing. So as you can imagine, the custom GBT that Whimsical is set up for is more adapted to take and create the mind map, whereas if we give it what it needs to do, it's going to do a much better job than actually ideating all of the topics that we need. So that's just a little tip there. You can get it to work at quite a basic level. But if you want to take it a step further, using Chat GPT to first come up with the list of topics and the nodes that you'd like in the mind, ma'am, is a much more efficient way to do this, and you'll have an expanded view of that and just get a bit more information squeezed out of it. So we are going to take all of these topics and copy them. And then what we would do is then switch back into whimsical, the whimsical custom GBT. And from there, we can say, create a mind map from the following. And it knows exactly what to do with all of this. So there we go. It's going to start the action. Okay, here, so we're just going to allow it again. And then from there, it sends all of the data over to Whimsical. And we have it there. And as you can see, it's a lot more detailed and a lot more comprehensive. So it just really depends on the depth that you would like to go to. I mean, this could be a bit overwhelming, to be honest, but you have the option there of going for a more simple, quick and light version using the whimsical custom GBT a more expanded view of the topic by using Chat GPT. And if we wanted to compare that, I mean, here we can see if we go in, very, very detailed and granular from the look of this, which is really, really great. And comparing that to the one before, it's more of a high level view of it. So it just depends on what you're looking for. But essentially, that is how you would use custom GBTs. And of course, there are many other GBTs available. Some of the best brands and apps are creating their own custom GBTs for you to use. But I found for mind mapping, whimsical, really great to use, and having the ability to do it all seamlessly from withinside Cha GPT just makes it a winner in ideation and brainstorming workflows. So I hope you were able to see what's possible, and that wraps it up for this lesson, and I will see you in the next one. Goodbye. 29. Using ChatGPT for Key Points and Summaries of Contracts & Legal Docs: Hey, guys, and welcome to another lesson. In this lesson, we're going to be looking at how hat GPT can help you summarize big contracts with large amounts of data and clauses and conditions into a short summary that contains all of the relevant details that you need to make a decision. This is especially good for contracts contracts to work, estimates, proposals, that sort of thing. It's just a great way to take all of that legal jargon and condense it down into something that means something to you that you can easily understand. After that, we're going to be looking at how you can use hATGPT to help you with any legal issues that you might be having. We're going to have a fictitious scenario where a flight was missed and we're going to use hachPT to try and get some compensation for that. Let's dive into it. Here we are in the ChachIPT interface. We're using the four oh mini model, and what we're going to do is take a large contract and I'll just show you what is inside this contract. We'll open this up. So this is just a contract between a fictitious company and myself for the purposes of this demonstration, and it's for creating content for this company over a fixed period and it just has all of the information there. So there's a few pages here. This is quite a short contract. So of course, this works better with large contracts, but you'll get the idea of how this can be used. So what we're going to do here is upload that contract paste it in there. Then we just need to have a simple prompt, something like this. You are my contract attorney. Please review the contract and summarize the following key details. So we want to know the parties involved, the key dates, the scope of work, compensation and pay terms, termination, confidentiality, disputes, and then any other additional clauses. Don't worry. I will provide this prompt as APDF in the lesson resources, so you're able to work with it yourself and have the exact same prompt that I'm using here. I'm going to copy this and we're going to jump back into hachBT there, we are going to paste it in here and run the query. From that lengthy contract, we're able to just get the bite size bullet points that matter, and it allows us to quickly skim through all of the details and from this summary, we'd be able to flag anything that stands out, anything that we don't agree with or could cause a potential issue or needs further negotiation. This is just really great as a first pass at a contract. You have all the information there and it's there for you to review. So that's the contract use, which is quite handy. Next, we're going to move on to just how ChatEPT could help you in certain legal situations. So here is the prompt that we're going to be working with. And just to set the scene and give you the context of this, it's going to be where a flight was missed and it was due to a delay out of my control, but I wasn't compensated by the airlines. So what I would like to do is have hat GPT search their terms and conditions, all of their legal documentation on their website, which is publicly available, and just use that in a supporting argument to be able to send them an email and hopefully claim some compensation. So let's have a look and see how that would work. So back into ChatBT, let's start up a new chat. And we are going to enable search the web mode. So this will allow ChaGBT to go out and search the web pages and retrieve the information from there. So we're going to paste in that prompt. It has everything it needs, and we're going to run that. So we've asked Cha CPT to go through all of that, to look through all the terms and conditions and their legal documentation, to be able to provide a supporting argument to present to the customer service department at the airline, which is Ryan Air. Now, I have nothing against Ryan Air. I've actually flown with them on many occasions and they've been absolutely nothing but a pleasure, so um this is no indication of their abilities as an airline. This is just a fictitious or just used purely for example sake. Here we go. It is providing us all of the information, and here we have the email template that is provided to us. What is really good is it's citing some of the actual clauses from their terms and conditions. And you would then just copy and paste this into your email. We can see from the sources that were used, it has actually gone out and it's read through all of the terms and conditions pages. That gives confidence that what we're stating here is actually what is public information. And that's it. I mean, that just gives you an idea of how you can use ChaiPT in a legal sense for contracts, proposals, that sort of thing, as well as just searching through publicly available information to be able to assist you with any legal matters or issues where things might not have gone how you had planned, and you'd like to try and get things sorted out and fixed. So that's it for this lesson. I hope there was some tips there that you can use going forward, but I will see you in the next lesson. Goodbye.