{"id":14883,"date":"2023-05-01T07:30:33","date_gmt":"2023-05-01T12:30:33","guid":{"rendered":"https:\/\/c1mdev.com\/c1m.ai\/?p=14883"},"modified":"2024-09-17T09:13:09","modified_gmt":"2024-09-17T09:13:09","slug":"how-to-use-prompt-engineering-to-train-the-model","status":"publish","type":"post","link":"https:\/\/c1mdev.com\/c1m.ai\/how-to-use-prompt-engineering-to-train-the-model\/","title":{"rendered":"How to Use Prompt Engineering to Train the Model\u00a0\u00a0"},"content":{"rendered":"<p><span data-contrast=\"auto\">I was tasked with the assignment of writing an article about <span id=\"urn:enhancement-e7e4b5f6-c020-4531-bfda-ddacc7457a2f\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> and how to best use it to train the language model in AI for the purposes of writing digital marketing <span id=\"urn:enhancement-2e8cde2f-3bdc-4700-8ed5-231735922d8b\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog posts<\/span>, and emails.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><strong>The prompts I was given were:\u00a0\u00a0<\/strong><\/p>\n<ul>\n<li><span data-contrast=\"auto\">Concept: Human-supervised AI for <span id=\"urn:enhancement-690dc021-a0a3-4864-b81a-47a34b67ae9c\" class=\"textannotation disambiguated wl-thing wl-no-link\">digital marketing<\/span>\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Naming styles generically\u2026 public domain styles vs real<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559737&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">SUB-PROMPT: I wonder if we could evolve the Brandscript format so that it could be fed directly into a prompt. or portions of it used in a prompt. Since Brandscript drives how we write, there may be some additions or modifications to it that would essentially allow <span id=\"urn:enhancement-f1fd070d-46a2-44ee-823d-d8d836deb35a\" class=\"textannotation disambiguated wl-thing wl-no-link\">Jasper<\/span> or <span id=\"urn:local-text-annotation-fz7cm4xvbk3nurfby6hg8q1cs4fjrkdq\" class=\"textannotation disambiguated wl-thing wl-no-link\">ChatGPT<\/span> to &#8220;learn&#8221; from Brandscript within the prompt.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559737&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">Notice that the first two prompts are rather truncated and high-level. This is due to the fact that they were written during a phone conversation. The Sub-Prompt was a more complete thought as there was a very specific goal in mind.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">I include this here because it\u2019s interesting to note the difference between prompts given from one human to another, compared to what we\u2019ll learn needs to be done when communicating between human to AI.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">In this article, we\u2019ll discuss what exactly is <span id=\"urn:enhancement-aa9ae9d0-a626-4aa2-a2fa-cd807f5f6fdd\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span>, how AI prefers to be prompted, how <span id=\"urn:enhancement-c61535da-fe7b-46be-a603-f8fe83696fbf\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> works and its benefits, and finally provide examples of successful prompts for creating text.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\">\u00a0<span id=\"urn:local-text-annotation-z0pfz0tcqcs20lis7780wm4uwh85midm\" class=\"textannotation disambiguated wl-thing wl-no-link\">What Are AI Prompts<\/span>?<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\">Prompting is an essential component of interaction with AI tools. It&#8217;s how you tell the AI what to do and what result you want. When prompting through text, like when conversing with ChatGPT, specificity matters\u2014if your query or statement is specific enough, such as &#8220;explain how to bake bread in simple terms,&#8221; then your answer will be more detailed than a general one, such as &#8220;how do you bake bread.&#8221;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\">\u00a0<span id=\"urn:local-text-annotation-q5cuewr0w7mk1zki054ze4cryeaso8a8\" class=\"textannotation disambiguated wl-thing wl-no-link\">What is AI Prompt Engineering<\/span>?<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\">Through <span id=\"urn:enhancement-fcb5d635-36e9-496b-8486-9bdd206cc1dd\" class=\"textannotation disambiguated wl-thing wl-no-link\">prompt engineering<\/span>, you can empower <a href=\"https:\/\/c1mdev.com\/c1m.ai\/embracing-ai-as-evolution-is-not-cheating\/\" target=\"_blank\" rel=\"noopener\"><span id=\"urn:enhancement-8bf8097a-01ce-4fd6-ba78-80e94258838e\" class=\"textannotation disambiguated wl-thing wl-no-link\">AI tools<\/span><\/a> to generate the most desirable results possible. An editor specializing in prompting is responsible for transforming concepts and ideas into a language that an <span id=\"urn:enhancement-e548d6de-b897-4dd1-807b-da5a4cd5dc76\" class=\"textannotation disambiguated wl-thing wl-no-link\">AI tool<\/span> comprehends. By utilizing prompts, you have the capability of educating <span id=\"urn:local-text-annotation-dtfb23cy8bh313y2lzjyjw5naw1fl33c\" class=\"textannotation disambiguated wl-thing wl-no-link\">artificial intelligence models<\/span> so that they achieve pre-defined outcomes.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">AI <span id=\"urn:enhancement-b582e113-6fd0-4935-b141-4b6fb1931cf6\" class=\"textannotation disambiguated wl-thing wl-no-link\">prompt engineering<\/span> is a powerful tool that allows users to craft prompts and train AI models for particular undertakings, like generating jokes or giving step-by-step instructions on baking a cake. These prompts help the model become more precise in its output which helps make it even more user-friendly and easy to use.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Take, for instance, the prompt &#8220;tell me a joke.&#8221; You&#8217;re likely to get diverse\u2014or even unrestricted\u2014answers. Yet when you use AI prompts that are optimized, and feature thought progression, the results will considerably improve.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\">A Conversation with Jasper<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\">The logic behind the following exercise is that before I can successfully <a href=\"https:\/\/c1mdev.com\/c1m.ai\/c1m-and-the-use-of-ai-for-content-generation\/\" target=\"_blank\" rel=\"noopener\"><span id=\"urn:local-text-annotation-n9ia8q1kmvfwil32o7nvap08q97o0lju\" class=\"textannotation disambiguated wl-thing wl-no-link\">prompt AI<\/span><\/a> to write about a subject, in this case, <span id=\"urn:enhancement-63a0d186-21bc-4ce9-9d17-a85228989714\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span>, I should ask the AI how it prefers to be prompted. The following is my chat with Jasper using the Beta Chat feature.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">I have formatted the exchange as I would an interview with a human. All emphasis is mine.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> Jasper, can you give me specific examples of how you like to be prompted for the best results?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper Chat:<\/span><\/b><span data-contrast=\"auto\"> Here are a few examples of prompts I often use when writing <span id=\"urn:enhancement-f37c4f57-8c3c-4c50-8020-a60f31776663\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog posts<\/span> or articles:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">What can we learn from this news story?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">How can technology be leveraged to solve this problem?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What are the implications of this political decision?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What kind of impact will this change have on our lives?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">How can we bridge the gap between different generations\/cultures\/ideologies?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What trends will shape the future of our industry\/society?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> What are specific examples of poor text prompts that would not produce good results?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> Poor text prompts that would likely not produce good results include:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">What do you think of this topic?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">How long does it take to finish this project?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What is the best way to start a blog?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Does this product have any flaws?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What are people saying about this issue?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Why did the government make this decision?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> How do you like to be prompted?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> I usually prefer prompts with open-ended questions that allow for creative exploration. Questions such as:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">What can we learn from this trend?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">How is this concept challenging our beliefs and values?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">How can we use technology to solve complex problems?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What are the implications of this policy change?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">How has this idea changed our society\/industry over time?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">What will be the lasting impact of this innovation?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> Are there words you prefer in a prompt?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> I tend to prefer prompts with words such as:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">Explore<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Analyze<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Compare<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Discover<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Evaluate\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Investigate<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> What words would you recommend I avoid when giving you prompts?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> I recommend avoiding words such as:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">Prove<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Justify<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Prescribe<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Specifically<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Tell or Describe\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> Why don&#8217;t you like the prompt \u201cdescribe\u201d?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> The word \u201cdescribe\u201d can lead to overly detailed or simplistic narratives, which can limit the creativity and originality of the content I write. Therefore, it&#8217;s better to use words like &#8220;analyze,&#8221; &#8220;evaluate,&#8221; and &#8220;explore&#8221; which give me more creative freedom.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> Do you have any more thoughts on how best to use prompts?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> Absolutely! When providing prompts, it is best to <\/span><b><span data-contrast=\"auto\">focus on the feeling and message you want me to convey<\/span><\/b><span data-contrast=\"auto\">. For example, instead of specifying a certain story setting or telling me how to interpret a theme, provide me with keywords that inspire the desired emotion or sentiment. This will help me channel my creativity in the right direction and <span id=\"urn:enhancement-d5ffc0b3-3773-4b04-96ec-fe75e36606fd\" class=\"textannotation disambiguated wl-thing wl-no-link\">create content<\/span> that properly reflects your intent. Additionally, <\/span><b><span data-contrast=\"auto\">use synonyms<\/span><\/b><span data-contrast=\"auto\"> and try to avoid using the same word over and over as this can limit my creative thinking.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> Discover the best method for <span id=\"urn:enhancement-bcaf7f2d-60a2-4c08-8812-b6a344cfb3b6\" class=\"textannotation disambiguated wl-thing wl-no-link\">prompt engineering<\/span>.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> One of the most effective methods for <span id=\"urn:enhancement-8ca5b751-c5d4-46f0-a0a7-c4326b62d894\" class=\"textannotation disambiguated wl-thing wl-no-link\">prompt engineering<\/span> is to <\/span><b><span data-contrast=\"auto\">start with a general concept<\/span><\/b><span data-contrast=\"auto\">, then break it down into smaller ideas and questions. This allows you to explore more creative angles and find other new directions to take your content in.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Finally, try to keep an open mind towards the process, as unexpected ideas often lead to the most interesting stories and posts.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Editor:<\/span><\/b><span data-contrast=\"auto\"> Evaluate the best methods for writing prompts for a <span id=\"urn:enhancement-e7c01086-b95d-4442-9957-fd255d1dbb9e\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span>.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Jasper:<\/span><\/b><span data-contrast=\"auto\"> <span id=\"urn:enhancement-ecd35702-8650-4d98-a1dd-24f9532e9742\" class=\"textannotation disambiguated wl-thing wl-no-link\">Writing effective prompts<\/span> for <span id=\"urn:enhancement-dda7b495-032d-4e37-95d3-a2b663479171\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog posts<\/span> requires <\/span><b><span data-contrast=\"auto\">understanding the <span id=\"urn:enhancement-09f05c74-6bcf-41a0-bb00-8e69569e2420\" class=\"textannotation disambiguated wl-person wl-no-link\">target audience<\/span><\/span><\/b><span data-contrast=\"auto\"> and crafting language that resonates with them. It is important to select words that evoke the desired emotion or sentiment, as this will help guide the content in a more meaningful way.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Additionally, use <\/span><b><span data-contrast=\"auto\">concrete examples and actionable ideas<\/span><\/b><span data-contrast=\"auto\"> to give readers tangible takeaways from your <span id=\"urn:enhancement-581af42c-fd73-47fc-9c76-e8a67f3f8d6e\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span>.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Thank you, Jasper, for an enlightening conversation.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Ironically, AI is teaching me how to better use AI most effectively. The student has become the teacher.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\">\u00a0Four Tips for <\/span><\/b><span id=\"urn:local-text-annotation-brhn80e3h74zg0j1uz30ehrf8mkuysxo\" class=\"textannotation disambiguated wl-thing wl-no-link\">Writing\u00a0Prompts<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\"><b><\/b>\u00a0<\/span><\/h2>\n<h4><b><span data-contrast=\"auto\">1 AI Performs Best When Context is Provided\u00a0<\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">To get the most out of this technology, <\/span><b><span data-contrast=\"auto\">create a prompt tailored to your exact requirements<\/span><\/b><span data-contrast=\"auto\">. For example, rather than simply \u201cWrite about productivity,\u201d you can craft something more specific such as \u201cCompose a <span id=\"urn:enhancement-96304142-0108-4e26-b0be-ab90a69fcf89\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span> on small businesses and their need for efficiency.\u201d\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">By providing these directions, which include both content type (blog) and topic specificity (small business focus), an <span id=\"urn:local-text-annotation-610y9b5kx1an0h15ovw2inejr0kenfwq\" class=\"textannotation disambiguated wl-thing wl-no-link\">AI bot<\/span> is able to provide considerably more help.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Here&#8217;s another example, this time with different types of details.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><b><span data-contrast=\"auto\">Basic prompt:<\/span><\/b><span data-contrast=\"auto\"> &#8220;Write about how to protect your information on <span id=\"urn:enhancement-fb13a3ef-c6ad-4b14-abd1-b198f95f4ab9\" class=\"textannotation disambiguated wl-thing wl-no-link\">social media<\/span>.&#8221;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><b><span data-contrast=\"auto\">Better prompt:<\/span><\/b><span data-contrast=\"auto\"> &#8220;As a professional threat intelligence provider, write an email to a client who is new to <span id=\"urn:enhancement-cf1f9615-4e44-4e9e-a858-fc74070bb762\" class=\"textannotation disambiguated wl-thing wl-no-link\">social media<\/span> and wants to know the best practices for posting safe content.&#8221;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">The second prompt asks the AI to take on a specific role (&#8220;professional threat intelligence provider&#8221;), and I give the AI specific context about the type of client. I also specify what type of content I want (&#8220;email&#8221;).<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Jasper can change the style of writing it creates, so, in cases where that matters, I want to be sure to include context for how the content will be used.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><b><span data-contrast=\"auto\">Basic prompt:<\/span><\/b><span data-contrast=\"auto\"> &#8220;Write a poem about house boating on Shasta Lake.&#8221;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><b><span data-contrast=\"auto\">Better prompt: <\/span><\/b><span data-contrast=\"auto\">&#8220;Write a poem in the style of Henry David Thoreau about house boating on Shasta Lake.&#8221;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">This can be adapted to all sorts of business tasks, too\u2014e.g., &#8220;write a professional but friendly email&#8221; or &#8220;write a formal executive summary.&#8221;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h4><b><span data-contrast=\"auto\">2 Include Helpful Information Upfront<\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">In some cases, you may already have text about the subject which you wish to expand upon to rephrase. For example, if I wanted to craft a fascinating introduction about myself, the AI will require some assistance. It doesn\u2019t know who I am (which is a little offensive, but I\u2019ll get over it) so I have to provide the necessary information for the tool to be effective.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Doug\u2019s resume: [paste entire resume here]\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\"><strong>Prompt:<\/strong> write a witty introduction about Doug.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">I could also use the prompt, \u201crephrase the information about Doug, introducing me to a stranger.\u201d<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h4><b><span data-contrast=\"auto\">3 Give Examples\u00a0<\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">To ensure that the AI understands what type of reply you are expecting, <\/span><b><span data-contrast=\"auto\">including examples in your prompt can be beneficial<\/span><\/b><span data-contrast=\"auto\">. For instance, if a chat-based conversation is desired between the user and an agent then include an example dialogue before ending with &#8220;Agent&#8221;. This serves to provide more context for the AI to respond accordingly.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">In this example, your conversation with the AI may play out as follows:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">You are an expert baker answering users&#8217; questions. Reply as agent.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><strong>Example conversation:\u00a0<\/strong><\/p>\n<ul>\n<li><span data-contrast=\"auto\">User: Hey can you help me with something<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Agent: Sure! What do you need help with?<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">User: I want to bake a cake but don&#8217;t know what temperature to set the oven to.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Agent: For most cakes, the oven should be preheated to 350\u00b0F (177\u00b0C).<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<h4><b><span data-contrast=\"auto\">4 Use Some of These Handy Expressions<\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">To get the most out of AI, you should <\/span><b><span data-contrast=\"auto\">know the precise phrase <\/span><\/b><span data-contrast=\"auto\">that it will respond to.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Here are a few useful examples: &#8220;Let&#8217;s think step by step&#8221; encourages logical thinking and can be particularly helpful when figuring out process methods. Conversely, &#8220;Thinking backwards&#8221; assists if an incorrect conclusion is reached.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Additionally, <\/span><b><span data-contrast=\"auto\">contextual phrases<\/span><\/b><span data-contrast=\"auto\"> like \u201cIn the style of [famous person]\u201d and \u201cAs a [insert profession\/role]\u201d help shape how much information the bot has access to in order for it to make more informed decisions.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h4><b><span data-contrast=\"auto\">5 Be as Specific or Descriptive as Possible<\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">For example, instead of simply typing, &#8220;Write an essay about digital marketing,&#8221; you can make a more detailed demand such as: &#8220;Write a 500-word essay on the benefits of digital marketing in the style of Neil Patel.&#8221;\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Ensure that your prompts are <\/span><b><span data-contrast=\"auto\">devoid of any unnecessary jargon<\/span><\/b><span data-contrast=\"auto\"> or vague language.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">One takeaway here is that more words aren\u2019t necessarily better, but specific words make a difference.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h4><b><span data-contrast=\"auto\">6 Understand the Anatomy of <span id=\"urn:local-text-annotation-krn32xlz35s7darq4jessuxmfwyjb4fs\" class=\"textannotation disambiguated wl-thing wl-no-link\">AI prompts<\/span><\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">Creative technologist Paul DelSignore identified <\/span><b><span data-contrast=\"auto\">four fundamental components<\/span><\/b><span data-contrast=\"auto\"> that make up a prompt: <\/span><b><span data-contrast=\"auto\">content type, description, style, and composition<\/span><\/b><span data-contrast=\"auto\">. Thus, with these essential elements in mind, your end result will be well equipped to satisfy any specifications desired.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h4><b><span data-contrast=\"auto\">7 Ask Jasper to Finish Your Thoughts<\/span><\/b><\/h4>\n<p><span data-contrast=\"auto\">One way to encourage a more in-depth look at a topic is by prompting Jasper to finish a line of text you give it, similar to how Google auto-completes prompts, but more complex.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">An example of this would be the prompt:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">\u201c<span id=\"urn:enhancement-b8a56011-9122-49b5-9e73-59dbd764b294\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> is important because\u2026\u201d<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\">Just the Facts, Ma\u2019am<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\">Back 1,737 words earlier, I started using a Jasper Recipe to gather information for this blog. After the initial prompt to learn <span id=\"urn:enhancement-7d46abb2-8f6f-48a5-8ef2-8ace451fde87\" class=\"textannotation disambiguated wl-thing wl-no-link\">what is Prompt Engineering<\/span>, I proceed with completing the Recipe and writing the blog.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">The steps I took were to cut and paste the Jasper response into the Content description\/ brief dialog box, included the tone of voice and keyword then I filled in the prompts.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">\u00a0&gt;write an introduction<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">&gt;write a blog outline<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">&gt;write about {OUTLINE_ITEM_1}<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">&gt;write about {OUTLINE_ITEM_2}<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">&gt;write about {OUTLINE_ITEM_3}<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">&gt;write a blog conclusion on {OUTLINE_ITEM_1}, {OUTLINE_ITEM_2}, {OUTLINE_ITEM_3}<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">I want to note when using Recipes in Jasper, the items after each &gt; are the prompts. These prompts are actually generated by Jasper, so in a sense, Jasper is prompting itself. The Editor\u2019s role is to herd Jasper and keep it going in the correct direction.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Here are the exact prompts used.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p>Content description\/brief<\/p>\n<p><span id=\"urn:enhancement-37d464aa-3975-4f6b-88f2-c94f486f42a4\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> is a powerful tool that can help train models quickly and effectively. The process utilizes prompts to guide the learning process, allowing the model to focus its attention on relevant data points. By providing precise guidance for the model\u2019s learning, <span id=\"urn:enhancement-4806ad4a-588e-40c0-8bd5-77f770ae0526\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> reduces the need for exhaustive manual tuning or parameter tweaking, thus saving time and effort.<\/p>\n<p>Tone of voice<\/p>\n<p>witty, informative, factual<\/p>\n<p>&gt;write about How does <span id=\"urn:enhancement-f8c21bc7-ce71-4961-ac58-317b50ea9542\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> Work?<\/p>\n<p>&gt;write about specific examples of prompts used for writing<\/p>\n<p>&gt;write about tips for successful <span id=\"urn:enhancement-4bf448d1-4e0b-4a29-8967-6c61f540b485\" class=\"textannotation disambiguated wl-thing wl-no-link\">prompt engineering<\/span> when writing a <span id=\"urn:enhancement-23e7358f-db17-4e43-9ea6-09384fbba843\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span><\/p>\n<p>&nbsp;<\/p>\n<p><span data-contrast=\"auto\">Based on these prompts here is the text generated. I have edited the text for grammar, voice, and eliminated any redundancy. It should be noted that running the prompts above more than once will often produce unique results and I have found that creating text this way and then editing the multiple results into one cohesive article often produces the best final results.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">The use of asterisks in Jasper is essential in getting the best results. by typing three asterisks (***) under a paragraph, this tells Jasper not to look at anything written above. The logic behind this is that Jasper will refer back to what it has written as if it was new information and will often repeat itself. The asterisks block this and forces Jasper to create new text on the subject you are requesting.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">My takeaway from this is that one prompt can produce varying degrees of correct answers but a melding of those answers ultimately produces the best final article.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">All emphasis is my own and added during the editing process.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\"><span id=\"urn:local-text-annotation-ab9549x7upjgv83ivqnrwejrzdgppbsn\" class=\"textannotation disambiguated wl-thing wl-no-link\">How Does Prompt Engineering Work<\/span>?<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\"><span id=\"urn:enhancement-04571c00-63a7-4175-b799-ae0e41eb7430\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> has two main components: the prompt and the model. The prompt is a set of predefined instructions or questions that guide the machine learning model in its exploration of relevant data points. These prompts serve as a form of immediate feedback, allowing for faster training and improved accuracy.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">On the other hand, the model is responsible for responding to these prompts by analyzing data points and making decisions based on its environment. This process works in an iterative manner, with each new iteration increasing its accuracy until it achieves desired results.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<h2><b><span data-contrast=\"auto\">Write About Specific Examples of Prompts Used for Writing<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\"><span id=\"urn:enhancement-d943da83-c1e2-40df-b442-f9062d3179b8\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> involves the use of prompts to guide the model\u2019s learning process. Examples of common prompts used in <span id=\"urn:enhancement-8071fc6d-df19-4346-ac88-a0850050b9bb\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> are:\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\"> Probing for specific details about a given topic, such as \u201cWhat is the capital city of France?\u201d\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\"> Encouraging creative thinking by asking hypothetical questions like \u201cIf you could travel anywhere in the world, where would you go?\u201d\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\"> Telling stories or providing anecdotes that can be used to explain a concept or idea, such as \u201cOnce upon a time\u2026\u201d\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\"> Asking rhetorical questions to stimulate conversation and critical thinking, like \u201cHow would you solve this problem?\u201d\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\"><span id=\"urn:enhancement-eeddb957-70d1-4253-b8d1-22d308762716\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> leverages these prompts to facilitate a more efficient learning process for the model, helping it stay focused on the most relevant information while also avoiding being overwhelmed by too much data.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Here are a few examples of successful <span id=\"urn:enhancement-b931dcfe-a22b-47c4-8364-ccbf535decd7\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> for writing <span id=\"urn:enhancement-6479f7e8-b148-47f5-82b5-bde501ad6c43\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog posts<\/span>:\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ol>\n<li><span data-contrast=\"auto\"> A travel blog used <span id=\"urn:enhancement-3302e599-ae95-401c-a01b-6e24cef63cd0\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> to generate detailed reviews of hotels and restaurants around the world. By providing prompts that focused on location, amenities, cuisine type, and other relevant information, they were able to quickly produce comprehensive reviews in a fraction of the time it would have taken through manual effort.\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\"> A technology publication utilized <span id=\"urn:enhancement-023cb826-4f59-460d-b129-bee28e884a69\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> to create articles about emerging trends in their field. By setting up prompts related to the most recent developments in their industry, the model was able to keep readers up-to-date on the latest news without the need for intensive manual research.\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\"> A lifestyle blog used <span id=\"urn:enhancement-4ebaf956-de1c-47b6-8eec-91918f046554\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> to quickly <span id=\"urn:enhancement-ccca1ec2-7ee5-45df-89f4-b16f748857e6\" class=\"textannotation disambiguated wl-thing wl-no-link\">create content<\/span> about health and wellness topics. By providing prompts that focused on nutrition, exercise tips, mental health advice, and other relevant subjects, they were able to generate content that was both timely and accurate in a fraction of the time it would have taken through traditional methods.\u00a0<\/span><\/li>\n<\/ol>\n<h2><b><span data-contrast=\"auto\">Write About Tips for Successful Prompt Engineering When Writing a Blog Post<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\">Keep prompts focused. Avoid using overly broad or ambiguous prompts. The result will be incoherent content with little value for readers. Instead, use specific and actionable prompts that will generate meaningful insights into the topic at hand.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Here are examples for Jasper Chat.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">Draft a <span id=\"urn:enhancement-548555ca-aac8-43d8-9389-fdabfd763404\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span> about [insert topic] using a compelling opening sentence&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Create an outline that ties the <span id=\"urn:enhancement-cbd472fa-93d4-4fb9-b232-81b3995664d0\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span> together logically&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Research and provide sources to back up claims&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Format the blog visually with images and headings&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Find me quotes to use in my <span id=\"urn:enhancement-5390ee79-e039-4544-a434-c24521158b6d\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span>&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Suggest phrases that will grab readers\u2019 attention&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Come up with interesting questions to ask in my <span id=\"urn:enhancement-bc8a68ae-85ee-4be7-9bc9-202c76e9868a\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span>&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Research statistics that I can cite in the post&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Write a strong call-to-action at the end of the post&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Generate a list of quotes about [insert topic] for the <span id=\"urn:enhancement-fb54d12a-6fc5-4f2e-9c29-5db9bccee6de\" class=\"textannotation disambiguated wl-thing wl-no-link\">blog post<\/span>&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Search for appropriate metaphors to use in the post about [insert topic]&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Brainstorm interesting discussion topics relevant to the post about [insert topic]&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Summarize recent research related to the subject matter&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<li><span data-contrast=\"auto\">Create a compelling conclusion to emphasize the main ideas&#8230;<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259,&quot;335559991&quot;:360}\">\u00a0<\/span><\/li>\n<\/ul>\n<h2><b>Exploring Innovative Ways of Content Creation with <span id=\"urn:local-text-annotation-zqrxxoxlz4cy8efptd0zjoamwen06dpm\" class=\"textannotation disambiguated wl-thing wl-no-link\">Prompt Engineering<\/span> <\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/h2>\n<p><span data-contrast=\"auto\">Research indicates that well-crafted prompts for AI tools are more likely to result in successful interactions. According to one study, 78% of users who used natural language prompts experienced a positive outcome from the <span id=\"urn:enhancement-2d72b524-5398-448d-ac3c-18a0953fe80e\" class=\"textannotation disambiguated wl-thing wl-no-link\">AI tool<\/span>. Compared this with only 52% who experienced a positive outcome using non-natural language prompts.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Another study found that 83% of participants preferred natural language when interacting with AI tools over other forms of prompts.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Finally, research indicates that using visuals along with text instructions increases accuracy and reduces errors by up to 22%.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">At its most basic definition, <\/span><b><span data-contrast=\"auto\">AI is essentially predicting what you want it to say<\/span><\/b><span data-contrast=\"auto\">, not much different from when Google auto-fills your inquiry, or your text app auto-fills the word you may be spelling. <\/span><b><span data-contrast=\"auto\">The difference<\/span><\/b><span data-contrast=\"auto\"> is <\/span><b><span data-contrast=\"auto\">you can teach the AI model<\/span><\/b><span data-contrast=\"auto\"> to learn when you give it effective prompts and ample context.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>I was tasked with the assignment of writing an article about Prompt Engineering and how to best use it to train the language model in&#8230;<\/p>\n","protected":false},"author":1,"featured_media":14942,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[],"class_list":["post-14883","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-marketing"],"_links":{"self":[{"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/posts\/14883","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/comments?post=14883"}],"version-history":[{"count":2,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/posts\/14883\/revisions"}],"predecessor-version":[{"id":23572,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/posts\/14883\/revisions\/23572"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/media\/14942"}],"wp:attachment":[{"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/media?parent=14883"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/categories?post=14883"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/c1mdev.com\/c1m.ai\/wp-json\/wp\/v2\/tags?post=14883"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}