Content Modeling

Content modeling decomposes content into its logical components and elements, and it's what makes dynamic, structured pages possible. A static page is manually built and self-contained; a dynamic page is generated from a consistent set of components governed by a template. Structuring content this way enables real capabilities: contextual navigation through metadata-driven links between related pages, content chunked into well-labeled sections that improve scanability, and content reuse, the same underlying content displayed differently depending on where and how it appears.

A content model has three key elements: content types, the distinct kinds of content objects a space comprises, each sharing common attributes and a common purpose; content components, the logical parts each content type breaks down into, balanced against the cost and complexity of actually building and maintaining that many discrete pieces; and access structures, the metadata that defines how components and pages relate to and link with each other.

Every reusable "related articles" list, every author bio that shows up consistently across dozens of pages, and every filterable product listing all trace back to the same underlying decision: someone modeled the content into components before building the page around it.

Exercise

The scenario: A recipe website is moving from static HTML pages, each recipe hand-built as a single unstructured page, to a CMS-driven architecture. The product team wants three specific capabilities: contextual navigation between related recipes, filtering by ingredient and dietary requirement, and personalized recipe recommendations.

Which content model element is most directly responsible for enabling filtering by ingredient and dietary requirement?
Which content model element is most directly responsible for enabling contextual navigation between related recipes?
Try It With Your Data: Content Type Discovery

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt is made of (RICE breakdown)
R

Role

Casts the AI as: You're a content strategist analyzing documentation to create a content model.

I

Instructions

Names 7 specific outputs to produce, so the response comes back structured rather than a general summary.

C

Context

Content domain, Total pages and Target audience tell the AI what your specific situation is, not a generic one.

E

Expected format

For each content type: a name, what job it does for the user, how it differs from nearby types, and one example URL or title.

Brief description
Whole number
Who this content is for
Assembled prompt

        
        
      
Try It With Your Data: Content Classification

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt is made of (RICE breakdown)
R

Role

Casts the AI as: You are a content strategist and information architect who specializes in classifying documentation using the Diátaxis framework.

I

Instructions

Names 5 specific outputs to produce, so the response comes back structured rather than a general summary.

C

Context

Background tell the AI what your specific situation is, not a generic one.

E

Expected format

Output as structured table: columns for page/title, proposed type, confidence, and a one-line reason grounded in the page content.

Whole number
e.g. "API"
Brief description of current structure
Why you're reorganizing
What you're trying to achieve
Assembled prompt

        
        
      
Try It With Your Data: Metadata Schema Generator

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt is made of (RICE breakdown)
R

Role

Casts the AI as: You're a content architect designing metadata schemas for documentation.

I

Instructions

Spells out exactly what to analyze and return.

C

Context

Content type definition tell the AI what your specific situation is, not a generic one.

E

Expected format

Group attributes by category: required identifying fields, descriptive fields, relationship fields, and administrative/workflow fields.

e.g. "API Reference Page"
e.g. Docusaurus, Contentful, custom CMS
What this metadata should enable (search, filtering, etc.)
Any technical limits
What this content type does for users
Anything else that defines this content type
e.g. Learning Metadata
Assembled prompt

        
        
      
Try It With Your Data: Relationship Mapper

Fill in your own details below; the prompt updates as you type. When it's ready, copy it into Claude or whatever AI tool you use.

What this prompt does

Use this prompt when: Starting content modeling from scratch.

  • Designing content models with interconnected types
  • Building navigation that shows related content
  • Planning cross-linking strategy
  • Implementing "Related Content" features
One per line: Type name, brief description
Your CMS, SSG, or documentation platform
Approximate counts per type
How users navigate between content
Assembled prompt