{"id":582,"date":"2025-08-05T11:05:49","date_gmt":"2025-08-05T10:05:49","guid":{"rendered":"https:\/\/anapoly.co.uk\/labs\/?page_id=582"},"modified":"2025-08-08T16:24:55","modified_gmt":"2025-08-08T15:24:55","slug":"precision-content-prompt-pack","status":"publish","type":"page","link":"https:\/\/anapoly.co.uk\/labs\/precision-content-prompt-pack\/","title":{"rendered":"Precision Content Prompt Pack"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Precision Content Prompt Pack<\/h2>\n\n\n\n<p>Version: 01, 1 August 2025<br>Authors: Alec Fearon and ChatGPT-4o.<\/p>\n\n\n\n<p class=\"is-style-text-annotation is-style-text-annotation--1\">Transparency label: AI-assisted<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Purpose<\/h2>\n\n\n\n<p>This is a six-step process for converting a source document into a structured format that is easy for an LLM to understand. The format is based on the <a href=\"https:\/\/en.wikipedia.org\/wiki\/Darwin_Information_Typing_Architecture\">Darwin Information Typing Architecture<\/a> (DITA) and ideas developed by <a href=\"https:\/\/www.precisioncontent.com\">Precision Content<\/a>. It has the following content types:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Reference (what something is)<\/li>\n\n\n\n<li>Concept (how to think about it)<\/li>\n\n\n\n<li>Principle (why it works)<\/li>\n\n\n\n<li>Process (how it unfolds)<\/li>\n\n\n\n<li>Task (how to do it)<\/li>\n<\/ul>\n\n\n\n<p>The six steps are carried out in sequence, one at a time. They clean, segment, type, clarify, and re-package the original source material. There is human review at the end of each step.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">To use <\/h2>\n\n\n\n<p>First, open a chat in ChatGPT and upload <a href=\"https:\/\/anapoly.co.uk\/labs\/media\/precision_content_prompt_pack.md\">this file<\/a> into the chat; it is in <a href=\"https:\/\/en.wikipedia.org\/wiki\/Markdown\">Markdown<\/a> (.md) because that is easy for LLMs to read. <br>Note: you can drag &amp; drop the file into the chat or use the upload button. <\/p>\n\n\n\n<p>Tell ChatGPT: \u201cPlease create a new canvas from this markdown file so we can work together using the precision content prompt pack.\u201d ChatGPT will:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Read the file<\/li>\n\n\n\n<li>Create a canvas<\/li>\n\n\n\n<li>Use each ## heading to split the file into separate cards<\/li>\n\n\n\n<li>Preserve formatting and headings<\/li>\n<\/ul>\n\n\n\n<p>Then upload the source file into the chat. Tell ChatGPT: &#8220;Please convert the uploaded file [filename] into precision content using the steps defined in the canvas Anapoly AI Labs Precision Content Prompt Pack. Begin Step 0.&#8221;<\/p>\n\n\n\n<p>ChatGPT will extract the content of the file and clean it as per Step 0 \u2013 Pre-Processing. It will paste the cleaned material into the \u201c\ud83d\udcc4 Source Document\u201d card for you to review. That sets you up to proceed with the following steps. The output of each step is put into the &#8220;Work Area &#8211; Output by Step&#8221; card in the canvas. Edit the output of each step as necessary before proceeding to the next step.<\/p>\n\n\n\n<p>The final output is put into the card &#8220;Review Notes \/ Final Output \/ Glossary&#8221;. You can tell ChatGPT to export it from there as a file for download. If it is to be used as reference material, filetype .md is recommended.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 0 \u2013 Pre-Processing<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Clean the raw input before analysis.<\/p>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Clean the following document for structured analysis. Remove:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Repeated headers\/footers<\/li>\n\n\n\n<li>Navigation links, timestamps, metadata<\/li>\n\n\n\n<li>Formatting glitches (e.g. broken paragraphs)<\/li>\n<\/ul>\n\n\n\n<p>Retain all meaningful content exactly as written. Do <em>not<\/em> summarise, interpret, or reword.<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 1 \u2013 Segmenting the Document<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Divide into discrete, meaningful segments.<\/p>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Break this cleaned document into a numbered list of coherent segments. Each segment should reflect a single topic, paragraph, or unit of meaning.<\/p>\n\n\n\n<p>Format:<br><strong>[1]<\/strong> [text]<br><strong>[2]<\/strong> [text]<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 2 \u2013 Typing the Segments<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Label each segment by information type.<\/p>\n\n\n\n<p><strong>Types:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Reference \u2013 what something is<\/li>\n\n\n\n<li>Concept \u2013 how to think about it<\/li>\n\n\n\n<li>Principle \u2013 why it works<\/li>\n\n\n\n<li>Process \u2013 how it unfolds<\/li>\n\n\n\n<li>Task \u2013 how to do it<\/li>\n<\/ul>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>For each segment, assign the most relevant type. Include a short justification.<\/p>\n\n\n\n<p>Format:<br><strong>[1]<\/strong> Type: [type] \u2013 [reason]<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 3 \u2013 Rewriting for Precision<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Convert to structured, plain-language modules.<\/p>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Rewrite each segment according to its type:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Use short declarative sentences<\/li>\n\n\n\n<li>Bullet points for steps or lists<\/li>\n\n\n\n<li>Avoid vagueness or repetition<\/li>\n<\/ul>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 4 \u2013 Grouping by Type<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Reorganise output by information type.<\/p>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Sort all rewritten segments under clear headings:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\ud83d\uddc2 Reference<\/li>\n\n\n\n<li>\ud83e\udde0 Concept<\/li>\n\n\n\n<li>\u2696\ufe0f Principle<\/li>\n\n\n\n<li>\ud83d\udd04 Process<\/li>\n\n\n\n<li>\ud83d\udd27 Task<\/li>\n<\/ul>\n\n\n\n<p>Preserve segment numbers.<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 5 \u2013 Structured Output Bundle<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Package the content for reuse.<\/p>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Format output with markdown or minimal HTML.<br>Include metadata at the top:<\/p>\n<\/blockquote>\n\n\n\n<pre class=\"wp-block-code\"><code>Title: &#91;your title]\nSource: &#91;file name or link]\nDate: &#91;today's date]\nContent type: Precision Content<\/code><\/pre>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Step 6 \u2013 Glossary Generation<\/h2>\n\n\n\n<p><strong>Purpose:<\/strong> Extract and define key terms.<\/p>\n\n\n\n<p><strong>Prompt:<\/strong><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Identify important terms in the text and define each using only information in the document.<\/p>\n\n\n\n<p>Format:<br><strong>Term<\/strong>: [definition]<\/p>\n<\/blockquote>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udcc4 Source Document<\/h2>\n\n\n\n<p>[Paste the cleaned or raw source text here after Step 0.]<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Work Area \u2013 Output by Step<\/h2>\n\n\n\n<p>Use this section to draft segmented content, types, rewrites, and grouped outputs.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Review Notes \/ Final Output \/ Glossary<\/h2>\n\n\n\n<p>Use this area for human commentary, final outputs, or glossary results.<\/p>\n<!-- PMB print buttons is only displayed on a single post\/page URLs-->","protected":false},"excerpt":{"rendered":"<p>Precision Content Prompt Pack Version: 01, 1 August 2025Authors: Alec Fearon and ChatGPT-4o. Transparency label: AI-assisted Purpose This is a six-step process for converting a source document into a structured format that is easy for an LLM to understand. The format is based on the Darwin Information Typing Architecture (DITA) and ideas developed by Precision [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"categories":[],"tags":[43,47,221,222,212,10],"class_list":["post-582","page","type-page","status-publish","hentry","tag-ai-tools","tag-chatgpt","tag-context","tag-precision-content","tag-prompt","tag-use-cases"],"_links":{"self":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/pages\/582","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/comments?post=582"}],"version-history":[{"count":12,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/pages\/582\/revisions"}],"predecessor-version":[{"id":668,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/pages\/582\/revisions\/668"}],"wp:attachment":[{"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/media?parent=582"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/categories?post=582"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/anapoly.co.uk\/labs\/wp-json\/wp\/v2\/tags?post=582"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}