13 Transforming Content with AI

A case study on paper is a story someone else finished. A case study powered by AI is a conversation the student has to navigate.

This chapter covers two complementary workflows: transforming static teaching materials into interactive experiences, and turning AI conversations into professional deliverables. Both put AI to work on the formatting while you focus on the thinking.

13.1 From Static to Interactive

You have a well-designed case study in Word or PDF. Students read it, maybe discuss it, then move on. The learning moment is brief and passive.

AI can transform that static document into an interactive HTML experience — with input fields for student responses, decision trees where choices lead to different outcomes, reflection prompts with saveable responses, and self-assessment checklists with feedback. The result uploads directly to your LMS, works in any browser, and needs no installation.

13.1.1 The Transformation Process

Identify the document — a case study, worksheet, or activity guide
Locate interaction points — questions, decisions, reflections
Mark enhancement opportunities — where could students input or respond?
Use AI to generate the interactive HTML

13.1.2 The Prompt

Transform this static [document type] into an
interactive HTML webpage:

[Paste your document content here]

Create:
1. Professional HTML with embedded CSS styling
2. Input fields for each question/reflection
3. Save/print functionality for student responses
4. Professional appearance for university students
5. Mobile-responsive design

Requirements:
- All CSS embedded (no external files)
- JavaScript for save/print functionality
- Clear instructions for students

Output: Complete HTML file ready to upload to
your LMS.

For more complex scenarios, you can request branching decision trees where student choices affect outcomes, progress tracking, feedback at each stage, and a score summary at the end. The AI generates a single HTML file you upload directly.

13.1.3 What You Can Transform

The same approach works for:

Static case studies → interactive scenarios with decision points
Paper worksheets → digital forms with save/print
Reading guides → self-paced activities with reflection prompts
Assessment rubrics → self-assessment checklists with feedback
Lecture handouts → interactive study guides

13.1.4 Design Principles

One file, self-contained. All CSS and JavaScript embedded — no external dependencies to break.
Mobile-responsive. Students will use phones. Design for it.
Accessible. Screen reader compatible, keyboard navigable, sufficient contrast.
Printable. Students should be able to save their work.
Progressive. Start with a basic transformation. Add complexity (branching, scoring) in later iterations.

13.2 From Conversation to Document

The second workflow runs in the opposite direction: you have a productive AI conversation, and you want it to produce a professional deliverable.

The core principle: the conversation is the work. The document is the output of that work. This is fundamentally different from “use AI to write a report” (which replaces thinking) versus “use AI to help you think through an analysis, then generate the presentation of that thinking” (which amplifies thinking).

13.2.1 Application 1: Data Analysis → Presentation

You have a dataset with interesting patterns. The workflow:

Step 1 — Upload and explore:
"I've attached a CSV with [describe data]. Can you
describe the structure, identify data quality issues,
tell me what patterns you notice, and suggest 3-5
visualisations that would be most revealing?"

Step 2 — Request specific analysis:
"Let's look deeper at [pattern]. Can you run
[specific analysis] and explain what it means
for [business context]?"

Step 3 — Generate the deliverable:
"Create a PowerPoint presentation (8-10 slides)
showing these findings. Include charts, key
insights on each slide, and speaker notes
explaining what to say."

One conversation produces an exploration, an analysis, and a presentation. Students learn data literacy through natural language — they do not need to code.

13.2.2 Application 2: Qualitative Analysis → Research Memo

For interview data, field notes, or open-ended survey responses:

"I have interview transcripts from [describe].
Conduct thematic analysis: identify major themes,
supporting quotes, and relationships between themes.
Then create a research memo (1500 words) with
themes, evidence, and implications."

Students learn research methodology by doing it conversationally — the AI handles the formatting while they handle the thinking.

13.2.3 Application 3: Generic Document Creation

AI can generate professional documents directly from conversations:

Word reports — specify structure (executive summary, analysis, recommendations), word count, and formatting
Excel spreadsheets — with formulas, conditional formatting, and dashboard charts
CSV files — ready for further analysis
Executive briefs — one-page summaries for stakeholders

The key: have the thinking conversation first, then request the formatted output. If you skip the thinking and go straight to “write me a report,” you get delegation. If you explore, question, and refine before requesting the document, you get amplified thinking with a professional deliverable at the end.

13.2.4 Tool-Specific Options

Different AI tools handle document creation differently:

ChatGPT generates downloadable files (Word, Excel, PowerPoint) directly in conversation
Claude Artifacts creates documents in a side panel you can edit in-place
Google Gemini exports directly to Google Docs and Sheets
MS Copilot integrates directly into Office applications — the conversation happens inside Word, Excel, or PowerPoint

The prompting principles are identical across all of them. Choose whichever fits your workflow.

13.3 Assessment Strategy

For assignments using either workflow, assess the thinking, not the deliverable:

Process evidence (40%) — the conversation or notes showing what questions the student asked, what patterns they explored, what they refined
Critical review (30%) — did they review AI output critically? Did they correct errors, adjust interpretations, make it their own?
Communication quality (20%) — is the final deliverable clear, professional, and accurate?
Reflection (10%) — can they explain what AI did versus what they decided?

Design assignments that require students to submit their conversation alongside the deliverable. The conversation is where the learning is visible.

13.4 Your Next Step

Try both workflows yourself before using them with students:

Static to interactive: Take one existing case study or worksheet and transform it. Upload it to your LMS. See how it looks.
Conversation to document: Take a dataset or topic you know well. Have a 5-minute exploratory conversation with AI, then ask for a presentation or report. Review it critically — what would you edit?

Once you have tried both, you will see which fits your teaching context. Most educators find the static-to-interactive workflow useful for creating reusable teaching materials, and the conversation-to-document workflow useful for student assignments where the process matters more than the product.

# Transforming Content with AI > A case study on paper is a story someone else finished. A case study powered by AI is a conversation the student has to navigate. This chapter covers two complementary workflows: transforming static teaching materials into interactive experiences, and turning AI conversations into professional deliverables. Both put AI to work on the formatting while you focus on the thinking. ## From Static to Interactive You have a well-designed case study in Word or PDF. Students read it, maybe discuss it, then move on. The learning moment is brief and passive. AI can transform that static document into an interactive HTML experience — with input fields for student responses, decision trees where choices lead to different outcomes, reflection prompts with saveable responses, and self-assessment checklists with feedback. The result uploads directly to your LMS, works in any browser, and needs no installation. ### The Transformation Process 1. **Identify the document** — a case study, worksheet, or activity guide 2. **Locate interaction points** — questions, decisions, reflections 3. **Mark enhancement opportunities** — where could students input or respond? 4. **Use AI to generate the interactive HTML** ### The Prompt ``` Transform this static [document type] into an interactive HTML webpage: [Paste your document content here] Create: 1. Professional HTML with embedded CSS styling 2. Input fields for each question/reflection 3. Save/print functionality for student responses 4. Professional appearance for university students 5. Mobile-responsive design Requirements: - All CSS embedded (no external files) - JavaScript for save/print functionality - Clear instructions for students Output: Complete HTML file ready to upload to your LMS. ``` For more complex scenarios, you can request branching decision trees where student choices affect outcomes, progress tracking, feedback at each stage, and a score summary at the end. The AI generates a single HTML file you upload directly. ### What You Can Transform The same approach works for: - **Static case studies** → interactive scenarios with decision points - **Paper worksheets** → digital forms with save/print - **Reading guides** → self-paced activities with reflection prompts - **Assessment rubrics** → self-assessment checklists with feedback - **Lecture handouts** → interactive study guides ### Design Principles - **One file, self-contained.** All CSS and JavaScript embedded — no external dependencies to break. - **Mobile-responsive.** Students will use phones. Design for it. - **Accessible.** Screen reader compatible, keyboard navigable, sufficient contrast. - **Printable.** Students should be able to save their work. - **Progressive.** Start with a basic transformation. Add complexity (branching, scoring) in later iterations. ## From Conversation to Document The second workflow runs in the opposite direction: you have a productive AI conversation, and you want it to produce a professional deliverable. The core principle: **the conversation is the work. The document is the output of that work.** This is fundamentally different from "use AI to write a report" (which replaces thinking) versus "use AI to help you think through an analysis, then generate the presentation of that thinking" (which amplifies thinking). ### Application 1: Data Analysis → Presentation You have a dataset with interesting patterns. The workflow: ``` Step 1 — Upload and explore: "I've attached a CSV with [describe data]. Can you describe the structure, identify data quality issues, tell me what patterns you notice, and suggest 3-5 visualisations that would be most revealing?" Step 2 — Request specific analysis: "Let's look deeper at [pattern]. Can you run [specific analysis] and explain what it means for [business context]?" Step 3 — Generate the deliverable: "Create a PowerPoint presentation (8-10 slides) showing these findings. Include charts, key insights on each slide, and speaker notes explaining what to say." ``` One conversation produces an exploration, an analysis, and a presentation. Students learn data literacy through natural language — they do not need to code. ### Application 2: Qualitative Analysis → Research Memo For interview data, field notes, or open-ended survey responses: ``` "I have interview transcripts from [describe]. Conduct thematic analysis: identify major themes, supporting quotes, and relationships between themes. Then create a research memo (1500 words) with themes, evidence, and implications." ``` Students learn research methodology by doing it conversationally — the AI handles the formatting while they handle the thinking. ### Application 3: Generic Document Creation AI can generate professional documents directly from conversations: - **Word reports** — specify structure (executive summary, analysis, recommendations), word count, and formatting - **Excel spreadsheets** — with formulas, conditional formatting, and dashboard charts - **CSV files** — ready for further analysis - **Executive briefs** — one-page summaries for stakeholders The key: have the thinking conversation first, then request the formatted output. If you skip the thinking and go straight to "write me a report," you get delegation. If you explore, question, and refine before requesting the document, you get amplified thinking with a professional deliverable at the end. ### Tool-Specific Options Different AI tools handle document creation differently: - **ChatGPT** generates downloadable files (Word, Excel, PowerPoint) directly in conversation - **Claude Artifacts** creates documents in a side panel you can edit in-place - **Google Gemini** exports directly to Google Docs and Sheets - **MS Copilot** integrates directly into Office applications — the conversation happens inside Word, Excel, or PowerPoint The prompting principles are identical across all of them. Choose whichever fits your workflow. ## Assessment Strategy For assignments using either workflow, assess the thinking, not the deliverable: - **Process evidence (40%)** — the conversation or notes showing what questions the student asked, what patterns they explored, what they refined - **Critical review (30%)** — did they review AI output critically? Did they correct errors, adjust interpretations, make it their own? - **Communication quality (20%)** — is the final deliverable clear, professional, and accurate? - **Reflection (10%)** — can they explain what AI did versus what they decided? Design assignments that require students to submit their conversation alongside the deliverable. The conversation is where the learning is visible. ## Your Next Step Try both workflows yourself before using them with students: 1. **Static to interactive:** Take one existing case study or worksheet and transform it. Upload it to your LMS. See how it looks. 2. **Conversation to document:** Take a dataset or topic you know well. Have a 5-minute exploratory conversation with AI, then ask for a presentation or report. Review it critically — what would you edit? Once you have tried both, you will see which fits your teaching context. Most educators find the static-to-interactive workflow useful for creating reusable teaching materials, and the conversation-to-document workflow useful for student assignments where the process matters more than the product.