{"id":29060,"date":"2025-09-20T18:06:12","date_gmt":"2025-09-20T16:06:12","guid":{"rendered":"https:\/\/res-group.eu\/?p=29060"},"modified":"2026-04-09T12:19:27","modified_gmt":"2026-04-09T10:19:27","slug":"how-to-correctly-prompt-an-llm-an-operational-framework","status":"publish","type":"post","link":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/","title":{"rendered":"How to Correctly Prompt an LLM: an Operational Framework"},"content":{"rendered":"<div class=\"fusion-fullwidth fullwidth-box fusion-builder-row-1 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling scarica-white-paper-CLINT-DB\" style=\"--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;\" ><div class=\"fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap\" style=\"max-width:1248px;margin-left: calc(-4% \/ 2 );margin-right: calc(-4% \/ 2 );\"><div class=\"fusion-layout-column fusion_builder_column fusion-builder-column-0 fusion_builder_column_1_1 1_1 fusion-flex-column\" style=\"--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:0px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;\" data-scroll-devices=\"small-visibility,medium-visibility,large-visibility\"><div class=\"fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column\"><div class=\"fusion-text fusion-text-1 fusion-text-no-margin\" style=\"--awb-margin-bottom:40px;\"><p><span data-contrast=\"auto\">In this article, we outline a number of reflections on the effective use of <strong>Artificial Intelligence models<\/strong>, and in particular <strong>Large Language Models (LLMs)<\/strong>.\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">The starting idea is simple: to obtain reliable results, every application that leverages these tools should adhere to the principle of \u201c<em>zero use of prior knowledge<\/em>\u201d.\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">By following this principle, the model is prevented from relying on outdated information or on biases acquired during the training phase. <\/span><\/p>\n<p><span data-contrast=\"auto\">By explicitly providing, at the time of prompting, all the data needed to answer the question correctly, it becomes possible to increase the transparency and reliability of the result.\u00a0<\/span><\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_2 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Index<\/p>\n<label for=\"ez-toc-cssicon-toggle-item-69e613fd4ce50\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #231d1c;color:#231d1c\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #231d1c;color:#231d1c\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-69e613fd4ce50\"  aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#The_structure_of_use_cases_building_a_framework\" >The structure of use cases: building a framework\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Use_case_internal_press_review_passive_RAG\" >Use case: internal press review (passive RAG)\u00a0<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Objective\" >Objective\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Passive_RAG_approach\" >Passive RAG approach\u00a0<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Use_case_automated_replies_to_customer_emails_active_RAG\" >Use case: automated replies to customer emails (active RAG)\u00a0<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Objective-2\" >Objective\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Active_RAG_approach\" >Active RAG\u00a0approach\u00a0<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#Conclusions\" >Conclusions\u00a0<\/a><\/li><\/ul><\/nav><\/div>\n<h2 aria-level=\"2\"><span class=\"ez-toc-section\" id=\"The_structure_of_use_cases_building_a_framework\"><\/span><b><span data-contrast=\"none\">The structure of use cases: building a framework<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span data-contrast=\"auto\">To create effective and controlled applications, a structure (framework) is proposed, consisting of three components (which we will call slots), all essential for interacting with an LLM.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p style=\"padding-left: 40px;\"><b><span data-contrast=\"auto\">Slot 1: context (input)<\/span><\/b><\/p>\n<p><span data-contrast=\"auto\">This slot must contain all the information necessary to place the model in the best possible conditions to generate the requested response. A good context includes sufficient and relevant details that allow the model to clearly understand the overall framework in which the question is situated.<\/span> \u00a0<span data-contrast=\"auto\">For example, to obtain an effective summary of a business report, it is necessary to provide the full text or, at the very least, the key points of the document, thereby ensuring an adequate informational basis on which the model can work.<\/span><\/p>\n<p style=\"padding-left: 40px;\"><b><span data-contrast=\"auto\">Slot 2: question (input)<\/span><\/b><\/p>\n<p><span data-contrast=\"auto\">This phase is necessary to state, precisely, clearly, and directly, what is expected from Artificial Intelligence. A well-structured question makes it possible to guide the LLM effectively toward the expected result, minimizing the risk of vague or out-of-context answers. For example, a question such as \u201cWhat are the key points covered in this report?\u201d is far more effective and productive than generic requests such as \u201cSummarize this document.\u201d\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p style=\"padding-left: 40px;\"><b><span data-contrast=\"auto\">Slot 3: answer (output)<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">This is the result generated by the model on the basis of the context and question previously provided. A correct formulation of the two preceding inputs encourages precise, coherent, and above all relevant answers. A well-structured approach significantly reduces the risk of obtaining ambiguous, incorrect, or off-topic responses.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<h2 aria-level=\"2\"><span class=\"ez-toc-section\" id=\"Use_case_internal_press_review_passive_RAG\"><\/span><b><span data-contrast=\"none\">Use case: internal press review (passive RAG)<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span data-contrast=\"auto\">Below is a first concrete use case, relating to the management of an internal press review in a large company. In structured business contexts, the amount of available information is often too great for end users to consume in full.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">To overcome this difficulty, it is possible to adopt an approach that combines content specific to the user\u2019s business unit with a concise summary of other relevant company news.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<h3 aria-level=\"3\"><span class=\"ez-toc-section\" id=\"Objective\"><\/span><b><span data-contrast=\"none\">Objective<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span data-contrast=\"auto\">The objective is to support the spread of knowledge within the organization, encouraging collaboration and dialogue between different business units, without overloading users with irrelevant or excessive information.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Phase 1: algorithmic step \u2013 preliminary content search<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<ul>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"10\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Preliminary input:<\/span><\/b><span data-contrast=\"auto\"> Each user has previously saved keywords representing their professional and thematic interests.<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"10\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Search:<\/span><\/b><span data-contrast=\"auto\">\u00a0By using a full-text search engine, the system quickly identifies all company news items matching the selected keywords. These news items constitute the informational material, selected both from the user\u2019s own business unit and from other relevant company content.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Phase 2: consult the LLM \u2013 generation of the press review<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<ul>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"11\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Context slot (input):<\/span><\/b><span data-contrast=\"auto\"> this is composed of the full text of the news items identified by the search engine and selected in the previous phase, in order to provide the model with a complete and structured basis to process.<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"11\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Question slot (input):<\/span><\/b><span data-contrast=\"auto\"> here the model is given a clear and specific request: \u201cUsing this company news, create a concise press review highlighting the topics of interest to the user.\u201d<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"11\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Answer slot (output):<\/span><\/b><span data-contrast=\"auto\">\u00a0the model generates a press review, a clear and concise text that effectively summarizes the topics most relevant to the user. Subsequently, through an algorithmic process, links to the original sources will be integrated, thus offering a deeper and more personalized way to consume the information.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/li>\n<\/ul>\n<h3 aria-level=\"3\"><span class=\"ez-toc-section\" id=\"Passive_RAG_approach\"><\/span><b><span data-contrast=\"none\">Passive RAG approach<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span data-contrast=\"auto\">We can define this method as \u201cpassive RAG\u201d because the query used for document retrieval derives exclusively from the keywords chosen by users and is not produced by the LLM itself. This approach makes it possible to combine the precision of full-text search with the generative model\u2019s summarization and analytical capabilities, producing a highly personalized and manageable result.<\/span><\/p>\n<h2 aria-level=\"2\"><span class=\"ez-toc-section\" id=\"Use_case_automated_replies_to_customer_emails_active_RAG\"><\/span><b><span data-contrast=\"none\">Use case: automated replies to customer emails (active RAG)<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span data-contrast=\"auto\">This section presents a second application scenario: the effective handling of customer requests received by email, using the framework illustrated above.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<h3 aria-level=\"3\"><span class=\"ez-toc-section\" id=\"Objective-2\"><\/span><b><span data-contrast=\"none\">Objective<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span data-contrast=\"auto\">The objective is to automatically extract the request expressed in a customer email in order to speed up the response process, avoiding repetitive manual activities and reducing the operational workload for the users involved in handling it.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Phase 1: identifying the question (first LLM invocation)<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<ul>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"12\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Context slot (input):<\/span><\/b><span data-contrast=\"auto\"> includes the full text of the email sent by the customer. Since emails may be written in very different formats and styles, the presence of details, even if apparently secondary, helps ensure a correct understanding of the request.<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"12\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Question slot (input):<\/span><\/b><span data-contrast=\"auto\"> the LLM is prompted as follows: \u201cThis is an email from a customer, written in free form. Identify the main question and reformulate it as an explicit question to be used as a query for our internal search engine\u201d.<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"12\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Answer slot (output):<\/span><\/b><span data-contrast=\"auto\">\u00a0the model returns a concise and precise query that captures the customer\u2019s need.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/li>\n<\/ul>\n<p><b><span data-contrast=\"auto\">Phase 2: intermediate algorithmic step \u2013 search in the corporate knowledge base<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Without further LLM invocations, the query obtained in the previous phase is used to query an internal knowledge base containing relevant company documents and information. From this search, the five most relevant documents are selected (which we might define as \u201c<em>answer candidates<\/em>\u201d).\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Phase 3: generating the response (second LLM invocation)<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<ul>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"13\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Context slot (input):<\/span><\/b><span data-contrast=\"auto\"> the original email text and the content of the \u201canswer candidate\u201d documents retrieved in the previous algorithmic phase are provided.<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"13\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Question slot (input):<\/span><\/b><span data-contrast=\"auto\"> the new request to the LLM is: \u201cThe customer sent this email and we have these company documents that should contain the answer. If you find relevant information in the documents, generate a reply email. If you do not find anything relevant, respond exactly with \u2018HUMAN INTERVENTION NEEDED\u2019&#8221;.<\/span><\/li>\n<li aria-setsize=\"-1\" data-leveltext=\"\uf0b7\" data-font=\"Symbol\" data-listid=\"13\" data-list-defn-props=\"{\" data-aria-posinset=\"1\" data-aria-level=\"1\"><b><span data-contrast=\"auto\">Answer slot (output):<\/span><\/b><span data-contrast=\"auto\">\u00a0the LLM directly generates the text of the\u00a0reply\u00a0email\u00a0or\u00a0clearly\u00a0indicates\u00a0the\u00a0need\u00a0for human\u00a0intervention.\u00a0<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/li>\n<\/ul>\n<h3 aria-level=\"3\"><span class=\"ez-toc-section\" id=\"Active_RAG_approach\"><\/span><b><span data-contrast=\"none\">Active RAG\u00a0approach<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><span data-contrast=\"auto\">This process is defined as active RAG because, unlike the previous one, the query used in the search is generated directly by the model from the content of the email sent by the customer. This ensures flexibility, adaptability, and the ability to handle heterogeneous requests, making interaction with the end customer more effective.<\/span><\/p>\n<h2 aria-level=\"2\"><span class=\"ez-toc-section\" id=\"Conclusions\"><\/span><b><span data-contrast=\"none\">Conclusions<\/span><\/b><span data-ccp-props=\"{\">\u00a0<\/span><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span data-contrast=\"auto\">This method, based on the principle of \u201c<em>zero use of prior knowledge<\/em>\u201d, guarantees transparency, control, and reliability of results. By effectively integrating generative models and document retrieval, it enables optimized management of both internal and external business communications, offering timely and precise responses to users\u2019 needs. <\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">Companies can assess this framework within their own organizational contexts, analyzing its benefits, critical issues, and opportunities, with the aim of improving their internal processes for communication and information management.<\/span><span data-ccp-props=\"{\">\u00a0<\/span><\/p>\n<\/div><\/div><\/div><\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>This article sets out a number of reflections on the effective use of Large Language Models. To obtain reliable results, every application that leverages these tools should adhere to the principle of \u201czero use of prior knowledge\u201d.<\/p>\n","protected":false},"author":7,"featured_media":25304,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","footnotes":""},"categories":[240],"tags":[238,247,280,140],"class_list":["post-29060","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-article","tag-innovation","tag-innovazione-en","tag-large-language-models","tag-natural-language-processing-en"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>How to Correctly Prompt an LLM: an Operational Framework - RES Group<\/title>\n<meta name=\"description\" content=\"Discover how to use Artificial Intelligence models effectively, in particular how to prompt Large Language Models.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to Correctly Prompt an LLM: an Operational Framework - RES Group\" \/>\n<meta property=\"og:description\" content=\"Discover how to use Artificial Intelligence models effectively, in particular how to prompt Large Language Models.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/\" \/>\n<meta property=\"og:site_name\" content=\"RES Group\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/ilGruppoRES\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-20T16:06:12+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-09T10:19:27+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/res-group.eu\/wp-content\/uploads\/2025\/04\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Federico Moretti\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Federico Moretti\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/\"},\"author\":{\"name\":\"Federico Moretti\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#\\\/schema\\\/person\\\/6d0041f0bb3512364b64da58b84b7d7d\"},\"headline\":\"How to Correctly Prompt an LLM: an Operational Framework\",\"datePublished\":\"2025-09-20T16:06:12+00:00\",\"dateModified\":\"2026-04-09T10:19:27+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/\"},\"wordCount\":2341,\"publisher\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/res-group.eu\\\/wp-content\\\/uploads\\\/2025\\\/04\\\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg\",\"keywords\":[\"innovation\",\"Innovazione\",\"Large Language Models\",\"Natural Language Processing\"],\"articleSection\":[\"Article\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/\",\"url\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/\",\"name\":\"How to Correctly Prompt an LLM: an Operational Framework - RES Group\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/res-group.eu\\\/wp-content\\\/uploads\\\/2025\\\/04\\\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg\",\"datePublished\":\"2025-09-20T16:06:12+00:00\",\"dateModified\":\"2026-04-09T10:19:27+00:00\",\"description\":\"Discover how to use Artificial Intelligence models effectively, in particular how to prompt Large Language Models.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#primaryimage\",\"url\":\"https:\\\/\\\/res-group.eu\\\/wp-content\\\/uploads\\\/2025\\\/04\\\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg\",\"contentUrl\":\"https:\\\/\\\/res-group.eu\\\/wp-content\\\/uploads\\\/2025\\\/04\\\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg\",\"width\":1920,\"height\":1080},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/article\\\/how-to-correctly-prompt-an-llm-an-operational-framework\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/res-group.eu\\\/en\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How to Correctly Prompt an LLM: an Operational Framework\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#website\",\"url\":\"https:\\\/\\\/res-group.eu\\\/en\\\/\",\"name\":\"Gruppo RES\",\"description\":\"Research, Enhance, Simplify\",\"publisher\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/res-group.eu\\\/en\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#organization\",\"name\":\"Gruppo RES\",\"url\":\"https:\\\/\\\/res-group.eu\\\/en\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/res-group.eu\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/RES_Logo-totem_Red-White-01.png\",\"contentUrl\":\"https:\\\/\\\/res-group.eu\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/RES_Logo-totem_Red-White-01.png\",\"width\":2083,\"height\":3017,\"caption\":\"Gruppo RES\"},\"image\":{\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/ilGruppoRES\\\/\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/res-research-for-enterprise-systems\\\/\",\"https:\\\/\\\/www.instagram.com\\\/gruppores\\\/\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCWoabU1ChQjanUcvS9z3qbg\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/res-group.eu\\\/en\\\/#\\\/schema\\\/person\\\/6d0041f0bb3512364b64da58b84b7d7d\",\"name\":\"Federico Moretti\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f522f976da35de3f1faf89ae7c5617437690e28597c34fb5010bc9b3444a22ac?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f522f976da35de3f1faf89ae7c5617437690e28597c34fb5010bc9b3444a22ac?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/f522f976da35de3f1faf89ae7c5617437690e28597c34fb5010bc9b3444a22ac?s=96&d=mm&r=g\",\"caption\":\"Federico Moretti\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How to Correctly Prompt an LLM: an Operational Framework - RES Group","description":"Discover how to use Artificial Intelligence models effectively, in particular how to prompt Large Language Models.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/","og_locale":"en_US","og_type":"article","og_title":"How to Correctly Prompt an LLM: an Operational Framework - RES Group","og_description":"Discover how to use Artificial Intelligence models effectively, in particular how to prompt Large Language Models.","og_url":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/","og_site_name":"RES Group","article_publisher":"https:\/\/www.facebook.com\/ilGruppoRES\/","article_published_time":"2025-09-20T16:06:12+00:00","article_modified_time":"2026-04-09T10:19:27+00:00","og_image":[{"width":1920,"height":1080,"url":"https:\/\/res-group.eu\/wp-content\/uploads\/2025\/04\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg","type":"image\/jpeg"}],"author":"Federico Moretti","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Federico Moretti","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#article","isPartOf":{"@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/"},"author":{"name":"Federico Moretti","@id":"https:\/\/res-group.eu\/en\/#\/schema\/person\/6d0041f0bb3512364b64da58b84b7d7d"},"headline":"How to Correctly Prompt an LLM: an Operational Framework","datePublished":"2025-09-20T16:06:12+00:00","dateModified":"2026-04-09T10:19:27+00:00","mainEntityOfPage":{"@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/"},"wordCount":2341,"publisher":{"@id":"https:\/\/res-group.eu\/en\/#organization"},"image":{"@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#primaryimage"},"thumbnailUrl":"https:\/\/res-group.eu\/wp-content\/uploads\/2025\/04\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg","keywords":["innovation","Innovazione","Large Language Models","Natural Language Processing"],"articleSection":["Article"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/","url":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/","name":"How to Correctly Prompt an LLM: an Operational Framework - RES Group","isPartOf":{"@id":"https:\/\/res-group.eu\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#primaryimage"},"image":{"@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#primaryimage"},"thumbnailUrl":"https:\/\/res-group.eu\/wp-content\/uploads\/2025\/04\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg","datePublished":"2025-09-20T16:06:12+00:00","dateModified":"2026-04-09T10:19:27+00:00","description":"Discover how to use Artificial Intelligence models effectively, in particular how to prompt Large Language Models.","breadcrumb":{"@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#primaryimage","url":"https:\/\/res-group.eu\/wp-content\/uploads\/2025\/04\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg","contentUrl":"https:\/\/res-group.eu\/wp-content\/uploads\/2025\/04\/Come-interrogare-correttamente-un-LLM-un-framework-operativo_Gruppo-RES-1.jpg","width":1920,"height":1080},{"@type":"BreadcrumbList","@id":"https:\/\/res-group.eu\/en\/article\/how-to-correctly-prompt-an-llm-an-operational-framework\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/res-group.eu\/en\/"},{"@type":"ListItem","position":2,"name":"How to Correctly Prompt an LLM: an Operational Framework"}]},{"@type":"WebSite","@id":"https:\/\/res-group.eu\/en\/#website","url":"https:\/\/res-group.eu\/en\/","name":"Gruppo RES","description":"Research, Enhance, Simplify","publisher":{"@id":"https:\/\/res-group.eu\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/res-group.eu\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/res-group.eu\/en\/#organization","name":"Gruppo RES","url":"https:\/\/res-group.eu\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/res-group.eu\/en\/#\/schema\/logo\/image\/","url":"https:\/\/res-group.eu\/wp-content\/uploads\/2024\/09\/RES_Logo-totem_Red-White-01.png","contentUrl":"https:\/\/res-group.eu\/wp-content\/uploads\/2024\/09\/RES_Logo-totem_Red-White-01.png","width":2083,"height":3017,"caption":"Gruppo RES"},"image":{"@id":"https:\/\/res-group.eu\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/ilGruppoRES\/","https:\/\/www.linkedin.com\/company\/res-research-for-enterprise-systems\/","https:\/\/www.instagram.com\/gruppores\/","https:\/\/www.youtube.com\/channel\/UCWoabU1ChQjanUcvS9z3qbg"]},{"@type":"Person","@id":"https:\/\/res-group.eu\/en\/#\/schema\/person\/6d0041f0bb3512364b64da58b84b7d7d","name":"Federico Moretti","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/f522f976da35de3f1faf89ae7c5617437690e28597c34fb5010bc9b3444a22ac?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/f522f976da35de3f1faf89ae7c5617437690e28597c34fb5010bc9b3444a22ac?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/f522f976da35de3f1faf89ae7c5617437690e28597c34fb5010bc9b3444a22ac?s=96&d=mm&r=g","caption":"Federico Moretti"}}]}},"_links":{"self":[{"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/posts\/29060","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/comments?post=29060"}],"version-history":[{"count":3,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/posts\/29060\/revisions"}],"predecessor-version":[{"id":29063,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/posts\/29060\/revisions\/29063"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/media\/25304"}],"wp:attachment":[{"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/media?parent=29060"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/categories?post=29060"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/res-group.eu\/en\/wp-json\/wp\/v2\/tags?post=29060"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}