{"id":43360,"date":"2026-01-16T17:51:36","date_gmt":"2026-01-16T12:21:36","guid":{"rendered":"https:\/\/www.inogic.com\/blog\/?p=43360"},"modified":"2026-01-19T17:43:32","modified_gmt":"2026-01-19T12:13:32","slug":"ai-powered-report-generation-using-copilot-studios-document-output-preview","status":"publish","type":"post","link":"https:\/\/www.inogic.com\/blog\/2026\/01\/ai-powered-report-generation-using-copilot-studios-document-output-preview\/","title":{"rendered":"AI-Powered Report Generation Using Copilot Studio\u2019s Document Output (Preview)"},"content":{"rendered":"<h3><img decoding=\"async\" class=\"alignnone size-full wp-image-43446\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1.png\" alt=\"\" width=\"2100\" height=\"1200\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1.png 2100w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1-300x171.png 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1-1024x585.png 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1-768x439.png 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1-1536x878.png 1536w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1-2048x1170.png 2048w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/AI-Powered-Report-Generation-Using-Copilot-Studios-Document-Output-Preview-1-660x377.png 660w\" sizes=\"(max-width: 2100px) 100vw, 2100px\" \/><\/h3>\n<h3><strong>Table of Contents<\/strong><\/h3>\n<p>1. <a href=\"#introduction\">Introduction<\/a><\/p>\n<p>2. <a href=\"#business\">Business Context: Vocational Assessment Reports<\/a><\/p>\n<p>3. <a href=\"#solution-overview\">Solution Overview and Data Flow<\/a><\/p>\n<p>4. <a href=\"#high-level-data-flow\">High-Level Data Flow<\/a><\/p>\n<p>5. <a href=\"#step-by-step-configuration\">Step-by-Step Configuration<\/a><\/p>\n<ul>\n<li>Create a Prompt in AI Builder (Copilot Studio)<\/li>\n<li>Set the Prompt\u2019s Output to Document<\/li>\n<li>Prepare and Upload a Word Document Template<\/li>\n<li>Add Prompt Instructions and Inputs<\/li>\n<li>Test the Prompt<\/li>\n<li>Use Prompt in Power Automate Flow<\/li>\n<li>Run the Power Automate Flow and Generate the Report<\/li>\n<\/ul>\n<p>6. <a href=\"#generated-report\">Reviewing the Generated Report (Example Outcome)<\/a><\/p>\n<p>7. <a href=\"#conclusion\">Conclusion<\/a><\/p>\n<h3 id=\"introduction\">Introduction<\/h3>\n<p>Many industries rely on formal assessment or evaluation reports that are time-consuming to prepare, compiled from multiple data sources\u2014both structured and unstructured\u2014and require strict formatting and compliance.<\/p>\n<p>For example, insurance claim reports, loan assessments, vocational assessments, and medical assessments often demand human judgment to evaluate multiple documents, analyze data, and produce a structured report. Traditionally, this process involves manual review, summarization, and document assembly, making it slow and error-prone.<\/p>\n<p>With the introduction of the <a href=\"https:\/\/learn.microsoft.com\/sl-si\/microsoft-copilot-studio\/generate-document-output-prompt\" target=\"_blank\" rel=\"noopener\">Document Output (preview)<\/a> capability in Copilot Studio, generating such reports has become significantly easier and faster.<\/p>\n<p>This feature allows you to generate a Microsoft Word document directly from a Copilot Studio prompt, using:<\/p>\n<ul>\n<li>Clear instructions<\/li>\n<li>Structured data<\/li>\n<li>Unstructured documents (PDFs, images, handwritten notes)<\/li>\n<\/ul>\n<p>It can be applied to scenarios such as invoice generation, request-for-proposal (RFP) documents, assessment reports, agreements, or contracts.<\/p>\n<p>In this blog post, we\u2019ll explore how to use Copilot Studio\u2019s Document Output feature to generate reports by reading and synthesizing data from multiple sources using AI.<\/p>\n<p>For demonstration, we\u2019ll use a Vocational Rehabilitation use case, though the same approach applies across many industries.<\/p>\n<h3 id=\"business\">Business Context: Vocational Assessment Reports<\/h3>\n<p>In the vocational rehabilitation industry, assessors are required to generate Vocational Assessment Reports, which play a critical role in determining a worker\u2019s employability and rehabilitation pathway following an injury or health-related incident.<\/p>\n<p>Preparing these reports is typically manual and fragmented:<\/p>\n<ul>\n<li>Case information resides in structured systems such as case management or CRM platforms<\/li>\n<li>Injury history exists in medical or insurance documents<\/li>\n<li>Employment history and skills are reviewed via resumes<\/li>\n<li>Critical insights are captured as handwritten or free-text interview notes<\/li>\n<li>A standardized template must be followed for regulatory compliance<\/li>\n<\/ul>\n<p>Assessors often spend hours reading, summarizing, and copy-pasting information from multiple sources into a single report.<\/p>\n<p>Now, let\u2019s see how we can configure a solution using Copilot Studio\u2019s Document Output feature to streamline this process.<\/p>\n<h3 id=\"solution-overview\">Solution Overview and Data Flow<\/h3>\n<p>To demonstrate this scenario, the solution consists of three main components:<\/p>\n<ol>\n<li><strong>Microsoft Dataverse<\/strong> \u2013 Stores structured case data and related unstructured files (resume, medical history, handwritten notes) attached to a custom Case entity<\/li>\n<li><strong>Power Automate<\/strong> \u2013 Orchestrates the end-to-end process<\/li>\n<li><strong>Copilot Studio Prompt (AI Builder)<\/strong> \u2013 A custom prompt configured with Document Output (preview) to generate a Word document<\/li>\n<\/ol>\n<h3 id=\"high-level-data-flow\">High-Level Data Flow<\/h3>\n<ol>\n<li>A Case record is created in Dataverse with basic details and attached documents (resume, medical history, interview notes).<\/li>\n<li>A user selects the Case record and manually triggers a Power Automate flow.<\/li>\n<li>The flow retrieves structured data and document content, then executes the Copilot Studio prompt.<\/li>\n<li>The prompt returns a fully formatted Word document (\u201cVocational Assessment Report.docx\u201d).<\/li>\n<li>The flow attaches the generated document back to the Case record.<\/li>\n<li>The assessor downloads and reviews the AI-generated report.<\/li>\n<\/ol>\n<p>This automation delivers a high-quality first draft in minutes instead of hours.<\/p>\n<h3 id=\"step-by-step-configuration\">Step-by-step configuration:<\/h3>\n<p>Now, let\u2019s walk through how to configure this solution step by step.<\/p>\n<ul>\n<li><strong>Create a Prompt in AI Builder (Copilot Studio)<\/strong>\n<ul>\n<li>Navigate to <a href=\"https:\/\/make.powerapps.com\" target=\"_blank\" rel=\"noopener\">https:\/\/make.powerapps.com<\/a> and go to AI Hub.<img decoding=\"async\" class=\"alignnone size-full wp-image-43363\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-1.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"1400\" height=\"508\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-1.jpg 1400w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-1-300x109.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-1-1024x372.jpg 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-1-768x279.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-1-660x239.jpg 660w\" sizes=\"(max-width: 1400px) 100vw, 1400px\" \/><\/li>\n<li>Click Build your own prompt<img decoding=\"async\" class=\"alignnone size-full wp-image-43364\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-2.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"1011\" height=\"445\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-2.jpg 1011w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-2-300x132.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-2-768x338.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-2-660x291.jpg 660w\" sizes=\"(max-width: 1011px) 100vw, 1011px\" \/><\/li>\n<li>In the prompt creation screen, give your prompt a name (e.g., \u201cGenerate Vocational Assessment Report\u201d). Then add your instructions, define the input(s), select the model you want to use, and configure the model\u2019s response settings.<img decoding=\"async\" class=\"alignnone size-full wp-image-43365\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-3.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"1413\" height=\"738\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-3.jpg 1413w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-3-300x157.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-3-1024x535.jpg 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-3-768x401.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-3-660x345.jpg 660w\" sizes=\"(max-width: 1413px) 100vw, 1413px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li><strong>Set the Prompt\u2019s Output to Document<\/strong>\n<ul>\n<li>By default, a prompt\u2019s output is text. To enable the prompt to return a Word document, change the output type to the new Document (preview)<\/li>\n<li>In the prompt editor, find the Prompt Response section and click on the Output Select Document (preview).<\/li>\n<li>Once \u201cDocument (preview)\u201d is selected, an option for Document settings will appear.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><img decoding=\"async\" class=\"alignnone size-full wp-image-43366\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-4.png\" alt=\"Report Generation Using Copilot Studio\" width=\"1215\" height=\"330\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-4.png 1215w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-4-300x81.png 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-4-1024x278.png 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-4-768x209.png 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-4-660x179.png 660w\" sizes=\"(max-width: 1215px) 100vw, 1215px\" \/><\/p>\n<ul>\n<li><strong>Prepare and upload a Word Document template<\/strong>\n<ul>\n<li>The document output feature requires a Word document template that the AI will use for the report layout. This template should contain placeholders for all the dynamic fields that will be filled in.<\/li>\n<li>Create a Microsoft Word document that will serve as your report template. In this document, include all the sections and formatting you want in the final report, and use placeholders enclosed in double curly braces for any fields that need to be replaced with data. For example: {{CaseNumber}}, {{WorkerName}}, {{AssessorName}}, {{TotalPages}}, {{CurrentDate}}, etc.<\/li>\n<\/ul>\n<\/li>\n<li>Tip: Make sure the placeholder names are clear and indicative of the content they represent. The AI model will use these names to infer what data to insert. Also, ensure you have the data available for each placeholder, either from structured input or that the AI can deduce it from context.\n<ul>\n<li>You can also include some placeholders that the AI will generate on the fly. For instance, {{TotalPages}} can be filled by the AI with the total number of pages in the final document, and {{CurrentDate}} could be the date when the report is generated. These don\u2019t need to come from your data source; the AI can figure them out.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li>Example template structure for the Vocational Assessment report:<\/li>\n<\/ul>\n<ol>\n<li><strong>Cover page:<\/strong> Title and total pages placeholder<img decoding=\"async\" class=\"alignnone size-full wp-image-43367\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-5.png\" alt=\"Report Generation Using Copilot Studio\" width=\"649\" height=\"163\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-5.png 649w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-5-300x75.png 300w\" sizes=\"(max-width: 649px) 100vw, 649px\" \/><\/li>\n<li><strong>Case overview:<\/strong> Basic details of the case (case number, worker info, assessor info, injury details, etc.). These will map to fields in the Dataverse Case record.<br \/>\n<img decoding=\"async\" class=\"alignnone size-full wp-image-43368\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-6.png\" alt=\"Report Generation Using Copilot Studio\" width=\"388\" height=\"150\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-6.png 388w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-6-300x116.png 300w\" sizes=\"(max-width: 388px) 100vw, 388px\" \/><\/li>\n<li><strong>Purpose of Assessment:<\/strong> Static text explaining the purpose of the vocational assessment (this section might not have any placeholders if it\u2019s the same for every report).<img decoding=\"async\" class=\"alignnone size-full wp-image-43369\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-7.png\" alt=\"Report Generation Using Copilot Studio\" width=\"572\" height=\"101\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-7.png 572w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-7-300x53.png 300w\" sizes=\"(max-width: 572px) 100vw, 572px\" \/><\/li>\n<li><strong>Worker Background Summary:<\/strong> A summary of the worker\u2019s background, including age (which could be calculated from DOB), education level, current employment status, and primary language. This information might come from the worker\u2019s resume attached to the case.<img decoding=\"async\" class=\"alignnone size-full wp-image-43370\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-8.png\" alt=\"Report Generation Using Copilot Studio\" width=\"460\" height=\"125\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-8.png 460w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-8-300x82.png 300w\" sizes=\"(max-width: 460px) 100vw, 460px\" \/><\/li>\n<li><strong>Injury and Medical History:<\/strong> Details of the worker\u2019s injury and medical history, pulled from the medical history document attached to the case.<img decoding=\"async\" class=\"alignnone size-full wp-image-43371\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-9.png\" alt=\"Report Generation Using Copilot Studio\" width=\"486\" height=\"191\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-9.png 486w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-9-300x118.png 300w\" sizes=\"(max-width: 486px) 100vw, 486px\" \/><\/li>\n<li><strong>Employment and Vocational History:<\/strong> The work history, qualifications, and possibly a summary of the worker\u2019s skills, derived from the resume document.<img decoding=\"async\" class=\"alignnone size-full wp-image-43372\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-10.png\" alt=\"Report Generation Using Copilot Studio\" width=\"555\" height=\"193\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-10.png 555w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-10-300x104.png 300w\" sizes=\"(max-width: 555px) 100vw, 555px\" \/><\/li>\n<li><strong>Interview observations:<\/strong> Notes and observations from the face-to-face interview, extracted from the handwritten notes image.<img decoding=\"async\" class=\"alignnone size-full wp-image-43373\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-11.png\" alt=\"Report Generation Using Copilot Studio\" width=\"537\" height=\"86\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-11.png 537w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-11-300x48.png 300w\" sizes=\"(max-width: 537px) 100vw, 537px\" \/><\/li>\n<li><strong>Transferable Skills Analysis:<\/strong> An AI-generated section listing skills the worker can perform or transfer, based on their experience, education, and any current restrictions. (This section\u2019s content is synthesized by the AI using all available information.)<img decoding=\"async\" class=\"alignnone size-full wp-image-43374\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-12.png\" alt=\"Report Generation Using Copilot Studio\" width=\"610\" height=\"153\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-12.png 610w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-12-300x75.png 300w\" sizes=\"(max-width: 610px) 100vw, 610px\" \/><\/li>\n<li><strong>Assessor Declaration:<\/strong> A section for the assessor\u2019s declaration or commentary. (Static text)<img decoding=\"async\" class=\"alignnone size-full wp-image-43375\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-13.png\" alt=\"Report Generation Using Copilot Studio\" width=\"606\" height=\"75\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-13.png 606w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-13-300x37.png 300w\" sizes=\"(max-width: 606px) 100vw, 606px\" \/><\/li>\n<li><strong>Signature:<\/strong> Placeholder for the assessor\u2019s name and date (Assessor\u2019s name likely comes from the case data; date can be the current date).\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 <img decoding=\"async\" class=\"alignnone size-full wp-image-43376\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-14.png\" alt=\"Report Generation Using Copilot Studio\" width=\"285\" height=\"59\" \/><\/li>\n<\/ol>\n<ul>\n<li>Once your Word template is ready with all the desired placeholders, upload it to the Prompt: In the prompt editor, click on Document settings (in the Model Response section) and upload your Word document.<img decoding=\"async\" class=\"alignnone size-full wp-image-43377\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-15.png\" alt=\"Report Generation Using Copilot Studio\" width=\"963\" height=\"192\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-15.png 963w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-15-300x60.png 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-15-768x153.png 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-15-660x132.png 660w\" sizes=\"(max-width: 963px) 100vw, 963px\" \/><\/li>\n<\/ul>\n<ul>\n<li>Copilot Studio will analyze the template and show a list of the fields it detected (the text inside {{ }} in the document). Verify this list to ensure all your placeholders are recognized.<img decoding=\"async\" class=\"alignnone size-full wp-image-43378\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-16.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"474\" height=\"545\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-16.jpg 474w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-16-261x300.jpg 261w\" sizes=\"(max-width: 474px) 100vw, 474px\" \/><\/li>\n<\/ul>\n<ul>\n<li><strong>Add Prompt instructions and Inputs<\/strong>\n<ul>\n<li>Now it\u2019s time to write the instructions for the prompt (this is the heart of the \u201cprompt engineering\u201d for your solution).<\/li>\n<li>In the Instructions field of the prompt editor, describe what the AI should do to generate the report. Be specific about which pieces of information to use and how to use them.<\/li>\n<li>For example, you might write instructions like:<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<pre class=\"lang:css gutter:true start:1\">You are tasked with generating a comprehensive Vocational Assessment report by extracting and synthesizing information from multiple sources including case details, a resume, notes from a face-to-face interview, and an injury history document.\r\n### Instructions:<\/pre>\n<p>1. **Extract Key Information:**<\/p>\n<p>&#8211; From the case details, identify background information, current status, and any relevant contextual data. &#8211; From the resume, extract work history, skills, qualifications, and career progression. &#8211; From the interview notes, capture personal insights, preferences, limitations, and goals. &#8211; From the injury history document, summarize medical and physical limitations impacting vocational capabilities.<\/p>\n<p>2. **Analyze and Integrate Data:**<\/p>\n<p>&#8211; Assess how the injury history affects the individual\u2019s ability to perform past or potential job roles. &#8211; Identify transferable skills and suitable vocational options considering the injury and personal preferences. &#8211; Highlight any barriers to employment and potential accommodations or rehabilitation needs.<\/p>\n<p>3. **Structure the Vocational Assessment Report:**<\/p>\n<p>&#8211; **Case overview:** Brief overview of the individual and case. &#8211; **Worker Background Summary:** Background information from resume. &#8211; **Injury and medical history:** Summary of injury history and its vocational impact extracted from history document. &#8211; **Employment and Vocational History:** Extracted from resume. &#8211; **Interview observation:** Key points from face-to-face interview notes. &#8211; **Transferable Skills Analysis:** Suitable job roles, training needs, and accommodations. &#8211; **Assessor Information:** Use consultant details as an Assessor information.<\/p>\n<p>4. **Ensure Clarity and Professional Tone:**<\/p>\n<p>&#8211; Use clear, concise language. &#8211; Maintain an objective and professional tone throughout the report. Provide the following documents for assessment: &#8211; Case Details\u00a0 CaseDetails &#8211; Resume\u00a0 Resume &#8211; Interview Notes\u00a0 InterviewNotes &#8211; Injury History\u00a0 History<\/p>\n<p>Basically, <strong>tell the AI how to combine and synthesize the input data for each part of the report.<\/strong> Also specify the tone or style if necessary (e.g., formal, concise, professional).<\/p>\n<ul>\n<li>Next, add the input sources that the prompt will use. In Copilot Studio, you can add input parameters to your prompt which can be of type \u201cText\u201d, \u201cDocument\u201d, or \u201cImage\u201d, etc. In our case, we have multiple sources:\n<ol>\n<li>Add a Text input for the structured case details (this will receive a text block or JSON with all the case info from Dataverse).<\/li>\n<li>Add Document\/Image inputs for each of the files: one for the Resume, one for the Medical History, and one for the Interview Notes (image). Give each input a clear name like CaseDetails, ResumeDocument, MedicalHistoryDocument, InterviewNotesImage.<\/li>\n<\/ol>\n<\/li>\n<li>When adding content in the Instructions, you can reference these inputs. For example, if you named an input \u201cResumeDocument\u201d, you can instruct: <em>\u201cSummarize the worker\u2019s education, work history, and skills from the ResumeDocument.\u201d<\/em> Copilot will pass the content of the actual resume file into the prompt when it runs.<\/li>\n<li>Click on \u201cAdd content\u201d or enter \u201c\/\u201d in the prompt where you want to use the content<img decoding=\"async\" class=\"alignnone size-full wp-image-43379\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-17.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"668\" height=\"562\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-17.jpg 668w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-17-300x252.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-17-660x555.jpg 660w\" sizes=\"(max-width: 668px) 100vw, 668px\" \/><\/li>\n<li>This will open a list with the following options,<img decoding=\"async\" class=\"alignnone size-full wp-image-43380\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-18.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"475\" height=\"535\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-18.jpg 475w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-18-266x300.jpg 266w\" sizes=\"(max-width: 475px) 100vw, 475px\" \/><\/li>\n<li>For Case details, use Text type of input and for rest Resume, Interview Notes, Injury History use Image or document type of input.<img decoding=\"async\" class=\"alignnone size-full wp-image-43381\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-19.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"589\" height=\"525\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-19.jpg 589w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-19-300x267.jpg 300w\" sizes=\"(max-width: 589px) 100vw, 589px\" \/><\/li>\n<li>After writing the instructions and setting up all inputs, save the prompt.<\/li>\n<li>\n<h3><strong>Test the prompt<\/strong><\/h3>\n<\/li>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Before wiring everything into a flow, it\u2019s best to test the prompt on its own to see how it performs. In the prompt editor, you can provide sample values for each input and run a test.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Click on each input parameter in your prompt and provide sample content. For instance, fill the case details input with some example data (or actual data from a test case), attach a sample resume PDF for the resume input, a sample medical report PDF for the medical history, and a sample image (or text) for the interview notes.<img decoding=\"async\" class=\"alignnone size-full wp-image-43382\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-20.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"684\" height=\"515\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-20.jpg 684w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-20-300x226.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-20-660x497.jpg 660w\" sizes=\"(max-width: 684px) 100vw, 684px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Once all inputs have sample data, click Test in the prompt editor. The AI will generate a response using the template and instructions.<\/li>\n<li>The layout is preserved and the content falls in the right sections.The result of the test will be a Word document (you should see a download or preview of the generated document). Download it and verify that:<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ol>\n<li style=\"list-style-type: none;\">\n<ol>\n<li style=\"list-style-type: none;\">\n<ol>\n<li style=\"list-style-type: none;\">\n<ol>\n<li>All the template fields are populated with sensible content.<\/li>\n<li>The layout is preserved and the content falls in the right sections.<\/li>\n<li>The AI is correctly extracting and summarizing the information for each part.<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>The test output also typically shows the values it determined for each placeholder field, which is useful for debugging if something didn\u2019t fill in as expected. If you notice any placeholders not filled or incorrect, you can adjust your instructions or make sure the input data covers that field properly. Iterate and test again if needed.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>\n<h3><strong>Use prompt in Power Automate flow<\/strong><\/h3>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Now that the prompt works, integrate it into a Power Automate flow to automate the end-to-end process. In Power Automate, you\u2019ll use the AI Builder \u2013 Run a prompt<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Trigger:<\/strong> The flow is triggered by the action \u201cWhen a row is selected\u201d (Dataverse) on the Case table. This provides the Case ID as input.For the vocational assessment scenario, I created a manual trigger flow on the Case table in Dataverse (so a user can run the flow from a specific case record). In the flow:<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Get Case Record:<\/strong> Add a Dataverse action Get a row by ID to retrieve all the details of the selected Case (using the Case ID from the trigger). This gives you structured data like Case Number, names, etc.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><img decoding=\"async\" class=\"alignnone size-full wp-image-43383\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-21.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"1240\" height=\"457\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-21.jpg 1240w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-21-300x111.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-21-1024x377.jpg 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-21-768x283.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-21-660x243.jpg 660w\" sizes=\"(max-width: 1240px) 100vw, 1240px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Download Files:<\/strong> For each file attachment on the case (resume, medical history, interview notes), add a Dataverse Download a file or an image You\u2019ll point each action to the Case record and the specific file column (e.g., \u201cResume File\u201d, \u201cMedical History File\u201d, etc.). This step is necessary because the prompt expects the content of those files as inputs. After this step, you will have (in flow memory) the file content for each document.<img decoding=\"async\" class=\"alignnone size-full wp-image-43384\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-22.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"651\" height=\"260\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-22.jpg 651w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-22-300x120.jpg 300w\" sizes=\"(max-width: 651px) 100vw, 651px\" \/> <img decoding=\"async\" class=\"alignnone size-full wp-image-43385\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-23.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"495\" height=\"604\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-23.jpg 495w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-23-246x300.jpg 246w\" sizes=\"(max-width: 495px) 100vw, 495px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Run Prompt:<\/strong> Add the Run a prompt (AI Builder) action. Select the custom prompt you created (it should appear by the name you gave it). Once you select it, the action will show fields corresponding to the prompt\u2019s inputs (CaseDetails, ResumeDocument, etc.).<img decoding=\"async\" class=\"alignnone size-full wp-image-43386\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-24.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"556\" height=\"313\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-24.jpg 556w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-24-300x169.jpg 300w\" sizes=\"(max-width: 556px) 100vw, 556px\" \/> Map the outputs from the previous steps to these prompt inputs: for CaseDetails (text), you can compose a single text blob or JSON string that includes all the needed case info (or simply pass the outputs of the Get Record step if the prompt can parse that). For the documents, assign the file content outputs from the download steps to the respective prompt inputs. <img decoding=\"async\" class=\"alignnone size-full wp-image-43387\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-25.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"858\" height=\"426\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-25.jpg 858w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-25-300x149.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-25-768x381.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-25-660x328.jpg 660w\" sizes=\"(max-width: 858px) 100vw, 858px\" \/> <img decoding=\"async\" class=\"alignnone size-full wp-image-43388\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-26.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"517\" height=\"263\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-26.jpg 517w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-26-300x153.jpg 300w\" sizes=\"(max-width: 517px) 100vw, 517px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Capture Prompt Output<\/strong>:The prompt will output a document. In the \u201cRun a prompt\u201d action, after selecting your prompt, you\u2019ll see an output property like \u201cDocument Output Content (Bytes)\u201d (and possibly the file name). This is the binary content of the generated Word doc. You\u2019ll use this in the next step.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Attach Document to Case<\/strong>:Add a Dataverse action Add a new row on the Notes table (Annotation entity) associated with the Case. Configure it to create a note linked to the Case record, with the document content from the prompt as an attachment. You\u2019ll set fields like: regarding (the Case), document body (the file content from the prompt, possibly needs base64), filename (e.g., \u201cVocational Assessment Report.docx\u201d), and mime type (\u201capplication\/vnd.openxmlformats-officedocument.wordprocessingml.document\u201d for Word doc). This will attach the generated report to the case. <img decoding=\"async\" class=\"alignnone size-full wp-image-43389\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-27.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"844\" height=\"463\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-27.jpg 844w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-27-300x165.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-27-768x421.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-27-660x362.jpg 660w\" sizes=\"(max-width: 844px) 100vw, 844px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Save the flow.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Run the Power Automate Flow and Generate the Report<\/strong><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Now it\u2019s time to see everything in action. Go to your Case in Dataverse (Power Apps).<img decoding=\"async\" class=\"alignnone size-full wp-image-43390\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-28.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"1106\" height=\"659\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-28.jpg 1106w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-28-300x179.jpg 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-28-1024x610.jpg 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-28-768x458.jpg 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-28-660x393.jpg 660w\" sizes=\"(max-width: 1106px) 100vw, 1106px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>On the record\u2019s page, use the Flow menu (the on-demand flow menu) to run your Power Automate flow for that record. (In modern interfaces, there might be a button like \u201cRun Flow\u201d or the flow might appear in a contextual menu for the record.)<img decoding=\"async\" class=\"alignnone size-full wp-image-43391\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-29.png\" alt=\"Report Generation Using Copilot Studio\" width=\"1050\" height=\"221\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-29.png 1050w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-29-300x63.png 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-29-1024x216.png 1024w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-29-768x162.png 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-29-660x139.png 660w\" sizes=\"(max-width: 1050px) 100vw, 1050px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>When the flow runs, it will execute the steps: gathering data, running the prompt, and attaching the output document.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>After the flow finishes, refresh the Case record and check the Notes\/Attachments. You should find a new attachment (Note) with the Vocational Assessment Report Download this Word document and review it.<img decoding=\"async\" class=\"alignnone size-full wp-image-43392\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-30.jpg\" alt=\"Report Generation Using Copilot Studio\" width=\"630\" height=\"291\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-30.jpg 630w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-30-300x139.jpg 300w\" sizes=\"(max-width: 630px) 100vw, 630px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h3 id=\"generated-report\">Reviewing the Generated Report (Example Outcome)<\/h3>\n<p><em>(Here I\u2019ll describe what the final document contains, based on my test with sample data:)<\/em><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Cover Page:<\/strong> The generated report\u2019s cover page shows the title of the report. In my template, I had a placeholder for total pages ({{TotalPages}}), and I can see the AI correctly filled in the total page count here (e.g., \u201cTotal pages: 4\u201d). This confirms that the dynamic fields like page count and current date worked.<img decoding=\"async\" class=\"alignnone size-full wp-image-43393\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-31.png\" alt=\"Report Generation Using Copilot Studio\" width=\"649\" height=\"151\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-31.png 649w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-31-300x70.png 300w\" sizes=\"(max-width: 649px) 100vw, 649px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Case Overview:<\/strong> This section is populated with basic case details pulled directly from the Dataverse case record. All the fields I included in the template were filled in accurately with the case data.\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 <img decoding=\"async\" class=\"alignnone size-full wp-image-43394\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-32.png\" alt=\"Report Generation Using Copilot Studio\" width=\"393\" height=\"160\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-32.png 393w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-32-300x122.png 300w\" sizes=\"(max-width: 393px) 100vw, 393px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Purpose of Assessment:<\/strong> This section was static in my template (no placeholders), and as expected, it remains unchanged and properly present in the output, explaining the purpose of the assessment.<img decoding=\"async\" class=\"alignnone size-full wp-image-43395\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-33.png\" alt=\"Report Generation Using Copilot Studio\" width=\"934\" height=\"148\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-33.png 934w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-33-300x48.png 300w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-33-768x122.png 768w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-33-660x105.png 660w\" sizes=\"(max-width: 934px) 100vw, 934px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Worker Background Summary:<\/strong> This section is filled with details from the worker\u2019s resume. For example, the worker\u2019s age was calculated from the date of birth found in the resume, education level and current employment status were identified and inserted, and the primary language would be here if it was mentioned in the resume. (In my test, I noticed the Primary Language field came out empty because the resume didn\u2019t explicitly mention the worker\u2019s language. This is a good reminder to ensure the input data covers all placeholder fields, or handle it in the prompt logic.)<img decoding=\"async\" class=\"alignnone size-full wp-image-43396\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-34.png\" alt=\"Report Generation Using Copilot Studio\" width=\"509\" height=\"128\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-34.png 509w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-34-300x75.png 300w\" sizes=\"(max-width: 509px) 100vw, 509px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Injury and Medical History:<\/strong> This section contains a summary of the worker\u2019s injury and medical background, extracted from the medical history document. The prompt pulled key details about the injury and treatment history and placed them here. I also included a {{SummaryMedicalHistory}} field in the template for a high-level summary; the AI generated a concise summary of the medical document and filled it in appropriately.<img decoding=\"async\" class=\"alignnone size-full wp-image-43397\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-35.png\" alt=\"Report Generation Using Copilot Studio\" width=\"615\" height=\"332\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-35.png 615w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-35-300x162.png 300w\" sizes=\"(max-width: 615px) 100vw, 615px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Employment and Vocational History:<\/strong> Here, the report shows a synopsis of the worker\u2019s employment history and vocational background from the resume. For instance, it listed past job roles and durations. I also had the AI extract a list of the worker\u2019s skills from the resume, which it did quite well. Additionally, because I included a {{SummaryOfResume}} field, the AI provided an overall summary of the resume content in a few sentences.<img decoding=\"async\" class=\"alignnone size-full wp-image-43398\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-36.png\" alt=\"Report Generation Using Copilot Studio\" width=\"628\" height=\"384\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-36.png 628w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-36-300x183.png 300w\" sizes=\"(max-width: 628px) 100vw, 628px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Interview Observations:<\/strong> This section is derived from the image of the handwritten interview notes. Impressively, the AI managed to extract the handwritten text and then paraphrase or clean it up for clarity. The result is a paragraph that captures the key observations the assessor noted during the interview, now neatly typed out.<img decoding=\"async\" class=\"alignnone size-full wp-image-43399\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-37.png\" alt=\"Report Generation Using Copilot Studio\" width=\"614\" height=\"103\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-37.png 614w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-37-300x50.png 300w\" sizes=\"(max-width: 614px) 100vw, 614px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Transferable Skills Analysis:<\/strong> In this section, the AI generated a list of skills and capabilities that the worker could potentially transfer to new job opportunities, based on everything it learned about the worker (experience, education, limitations from injury). This was not explicitly in any source document, but because the prompt instructions asked for an analysis, the AI produced a reasonable list of transferable skills. It adds a forward-looking touch to the report that can be very useful for the rehab process.<img decoding=\"async\" class=\"alignnone size-full wp-image-43400\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-38.png\" alt=\"Report Generation Using Copilot Studio\" width=\"607\" height=\"219\" srcset=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-38.png 607w, https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-38-300x108.png 300w\" sizes=\"(max-width: 607px) 100vw, 607px\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li><strong>Assessor\u2019s Declaration and Signature:<\/strong> The final part of the report includes the assessor\u2019s declaration text (which was static text in the template) and a signature line. The assessor\u2019s name was pulled from the case data and inserted into the signature section, and the Current Date was filled in (for the date of signing the report). These came out correctly in the test document.\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0<img decoding=\"async\" class=\"alignnone size-full wp-image-43401\" style=\"border: 1px solid #000000; padding: 1px; margin: 1px;\" src=\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2026\/01\/Copilot-Studio-39.png\" alt=\"Report Generation Using Copilot Studio\" width=\"200\" height=\"62\" \/><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Overall, the generated report closely followed the layout of my Word template, and all the placeholders were replaced with relevant information. There were a couple of minor omissions where data was missing (like the primary language example), but those can be addressed by refining the source data or prompt instructions. The document retained all formatting (headings, bullet points, etc.) from the template, giving a polished look as if someone had composed it manually.<\/p>\n<h3 id=\"conclusion\">Conclusion:<\/h3>\n<p><strong>Copilot Studio\u2019s Document Output (preview) capability transforms how structured reports are created.<\/strong> In the vocational assessment scenario, assessors can now generate a comprehensive first draft in seconds, dramatically reducing administrative effort while improving consistency and accuracy. While this example focused on vocational rehabilitation, the same approach applies to:<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Medical summaries<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Legal documentation<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Insurance claim reports<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Financial assessments<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>With a well-designed template and clear prompt instructions, AI handles the heavy lifting allowing professionals to focus on analysis, judgement, and decision-making.<\/p>\n<pre class=\"lang:css gutter:true start:1\"><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Table of Contents 1. Introduction 2. Business Context: Vocational Assessment Reports 3. Solution Overview and Data Flow 4. High-Level Data Flow 5. Step-by-Step Configuration Create a Prompt in AI Builder (Copilot Studio) Set the Prompt\u2019s Output to Document Prepare and Upload a Word Document Template Add Prompt Instructions and Inputs Test the Prompt Use Prompt\u2026 <span class=\"read-more\"><a href=\"https:\/\/www.inogic.com\/blog\/2026\/01\/ai-powered-report-generation-using-copilot-studios-document-output-preview\/\">Read More &raquo;<\/a><\/span><\/p>\n","protected":false},"author":15,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[2746,2361],"tags":[3287],"class_list":["post-43360","post","type-post","status-publish","format-standard","hentry","category-copilot","category-technical","tag-report-generation-using-copilot-studios"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts\/43360","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/users\/15"}],"replies":[{"embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/comments?post=43360"}],"version-history":[{"count":0,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts\/43360\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/media?parent=43360"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/categories?post=43360"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/tags?post=43360"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}