{"id":4065,"date":"2023-05-19T10:43:19","date_gmt":"2023-05-19T14:43:19","guid":{"rendered":"https:\/\/technology.dcds.edu\/?p=4065"},"modified":"2024-03-14T10:59:03","modified_gmt":"2024-03-14T14:59:03","slug":"the-art-of-prompt-engineering-for-optimal-performance","status":"publish","type":"post","link":"https:\/\/technology.dcds.edu\/index.php\/the-art-of-prompt-engineering-for-optimal-performance\/","title":{"rendered":"The Art of Prompt Engineering for Optimal Performance"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"4065\" class=\"elementor elementor-4065\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-d7e9dc9 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"d7e9dc9\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-edaf51e\" data-id=\"edaf51e\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-8488425 elementor-widget elementor-widget-text-editor\" data-id=\"8488425\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">Perhaps you\u2019ve heard of the quickly blossoming careers of prompt engineers who make up to $335,000 a year and wondered what a prompt engineer does.\u00a0 Well, prompt engineers are people who help train AI chatbots to improve their responses. Prompt engineering is the process of creating a well-defined prompt or input into a generative text model (something like ChatGPT) to generate a desired output.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">While writing this blog post, I asked ChatGPT to explain prompt engineering to me and it replied stating when writing a prompt, \u201cthe quality of the prompt can have a significant impact on the quality and relevance of the generated text.\u00a0 Some key components of effective prompt engineering are to identify and clarify specific words to create the desired output, organizing the input text in a way that is clear and understandable, to ensure you have proper grammar, punctuation, and spelling, and to test and refine the prompt to achieve optimal results.\u00a0<\/span><\/p><p><span style=\"font-weight: 400;\">Therefore, the key to unlocking the full potential of AI technologies is to possess good prompt skills along with the ability to effectively evaluate\u00a0 and refine your prompts.\u00a0 This can be done using the PREP Framework for prompt writing and the EDIT framework to evaluate the response.\u00a0\u00a0<\/span><\/p><p><span style=\"text-decoration: underline;\"><b>PREP Framework:<\/b><\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-45fb4ec elementor-widget elementor-widget-image\" data-id=\"45fb4ec\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"768\" height=\"159\" src=\"https:\/\/technology.dcds.edu\/wp-content\/uploads\/2023\/05\/IMG_0007-768x159.jpg\" class=\"attachment-medium_large size-medium_large wp-image-4094\" alt=\"\" srcset=\"https:\/\/technology.dcds.edu\/wp-content\/uploads\/2023\/05\/IMG_0007-768x159.jpg 768w, https:\/\/technology.dcds.edu\/wp-content\/uploads\/2023\/05\/IMG_0007-300x62.jpg 300w, https:\/\/technology.dcds.edu\/wp-content\/uploads\/2023\/05\/IMG_0007-1024x212.jpg 1024w, https:\/\/technology.dcds.edu\/wp-content\/uploads\/2023\/05\/IMG_0007-1536x318.jpg 1536w, https:\/\/technology.dcds.edu\/wp-content\/uploads\/2023\/05\/IMG_0007-2048x424.jpg 2048w\" sizes=\"(max-width: 768px) 100vw, 768px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bb6abd1 elementor-widget elementor-widget-text-editor\" data-id=\"bb6abd1\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">To excel in your prompt writing, consider embracing the power of the PREP framework.&nbsp; PREP encompasses four components\u2014Prompt, Role, Explicit, and Parameters\u2014which should help pave the way to acquiring desired responses.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>P<\/b><span style=\"font-weight: 400;\">rompt: Introduce the question with a prompt<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>R<\/b><span style=\"font-weight: 400;\">ole: Give it a role or voice<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>E<\/b><span style=\"font-weight: 400;\">xplicit: Be explicit in your instructions<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>P<\/b><span style=\"font-weight: 400;\">arameters: Set the parameters of the answer<\/span><\/li>\n<\/ul>\n<div><a href=\"https:\/\/docs.google.com\/document\/d\/1yqq0MsvW0Lrf0e86stQqr6zcG-zXcZI-knJ3zav3yNY\/edit?usp=sharing\">Here are some examples using the Prep framework<\/a><\/div>\n<div>&nbsp;<\/div>\n<div>\n<p><span style=\"text-decoration: underline;\"><b>EDIT Framework:<\/b><\/span><\/p>\n<p><span style=\"font-weight: 400;\">While the PREP framework equips you with the skills to generate remarkable responses, it is equally crucial to have a structured process for evaluating and refining generative outputs.&nbsp; The EDIT Framework (Evaluate, Determine, Identify, and Transform) provides such a process. &nbsp; By following this model, you can actively engage with AI technologies to assess, refine, and improve AI-generated outputs to ensure its accuracy and quality.&nbsp;<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>E<\/b><span style=\"font-weight: 400;\">valuate: Evaluate your AI output content for language, facts, and structure<\/span>&nbsp;<\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>D<\/b><span style=\"font-weight: 400;\">etermine: Determine accuracy and corroborate with source<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>I<\/b><span style=\"font-weight: 400;\">dentify: Identify biases and misinformation in output<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>T<\/b><span style=\"font-weight: 400;\">ransform: Transform content to reflect adjustments and new findings<\/span><\/li>\n<\/ul>\n<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-fe5420e elementor-widget elementor-widget-html\" data-id=\"fe5420e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div style=\"position: relative; width: 100%; height: 0; padding-top: 75.0000%;\n padding-bottom: 0; box-shadow: 0 2px 8px 0 rgba(63,69,81,0.16); margin-top: 1.6em; margin-bottom: 0.9em; overflow: hidden;\n border-radius: 8px; will-change: transform;\">\n  <iframe loading=\"lazy\" style=\"position: absolute; width: 100%; height: 100%; top: 0; left: 0; border: none; padding: 0;margin: 0;\"\n    src=\"https:&#x2F;&#x2F;www.canva.com&#x2F;design&#x2F;DAFjTEW7Gi8&#x2F;view?embed\" allowfullscreen=\"allowfullscreen\" allow=\"fullscreen\">\n  <\/iframe>\n<\/div>\n<a href=\"https:&#x2F;&#x2F;www.canva.com&#x2F;design&#x2F;DAFjTEW7Gi8&#x2F;view?utm_content=DAFjTEW7Gi8&amp;utm_campaign=designshare&amp;utm_medium=embeds&amp;utm_source=link\" target=\"_blank\" rel=\"noopener\">EDIT: Diagnostic Questioning<\/a> by Dean Haratsaris\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-eddb38b elementor-widget elementor-widget-text-editor\" data-id=\"eddb38b\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><span style=\"font-weight: 400;\">By combining the power of prompt engineering through the PREP framework with the comprehensive evaluation approach offered by the EDIT framework, you can confidently leverage AI generative technologies.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Perhaps you\u2019ve heard of the quickly blossoming careers of prompt engineers who make up to $335,000 a year and wondered what a prompt engineer does.\u00a0 Well, prompt engineers are people who help train AI chatbots to improve their responses. Prompt engineering is the process of creating a well-defined prompt or input into a generative text [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":4098,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4065","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-teched-toolbox","entry","has-media"],"_links":{"self":[{"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/posts\/4065","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/comments?post=4065"}],"version-history":[{"count":40,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/posts\/4065\/revisions"}],"predecessor-version":[{"id":4107,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/posts\/4065\/revisions\/4107"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/media\/4098"}],"wp:attachment":[{"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/media?parent=4065"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/categories?post=4065"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/technology.dcds.edu\/index.php\/wp-json\/wp\/v2\/tags?post=4065"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}