The JSONification of Everything

Have you ever known the feel of something – a design, a brand's voice, a song – but struggled to explain it or copy it? It happens all the time. It's hard to turn that gut feeling into clear instructions, especially for an AI.

But what if you could capture that feeling, that structure, in a way that's easy to understand and perfect for AI?

You can, using JSON.

Why JSON Works

You probably know JSON (JavaScript Object Notation) from web development. But it's much more than that. Think of it as a simple way to break down and describe almost anything.

Why is it so useful here?

• Clear Structure: JSON uses key-value pairs, making it organized and easy for both people and AI to read.
• Flexible: It works for simple lists or very complex information. You can describe a basic logo or a detailed strategy.
• AI-Friendly: AI models are great at reading structured data like JSON. They can easily spot patterns and use the JSON as a clear blueprint to follow.

The Practical Workflow

So, how do you actually put this into practice? Here's a general workflow for asking an AI to assess data and generate a reusable JSON profile:

This process transforms subjective qualities into a concrete format that AI can reliably work with. Let's look at how you can use JSON to structure anything.

Structure anything with JSON

The real power emerges when you apply this structured approach to things not typically considered 'data'. You can create a detailed JSON profile – like a 'DNA' – for nearly anything:

• Visuals: Logos, web designs, image styles.
• Text: Writing styles, email structures, brand voice.
• Code: App structures, common patterns.
• Concepts: Business strategies, marketing plans.
• Media: Music elements, video styles, ad copy.

By breaking things down into JSON, you give an AI a detailed map. It can then understand, analyze, adapt, or even recreate the original thing, or make something new in the exact same style.

Real-World Example: Analyzing a Website with Perplexity

This process works well for various types of analysis. For instance, I used Perplexity to analyze my own website, sourcetms.com.

I prompted it to act as an expert analyst, examine the site from multiple perspectives (code, design, brand, text, etc.), and generate a JSON profile that I could potentially use as a template for another LLM to recreate a similar site.

Here's a glimpse of the process:

This generated JSON, shown below, provides a structured breakdown that's much more useful for subsequent AI tasks than a simple text description.

(Note: The example JSON above generated by Perplexity is illustrative. While useful, AI-generated profiles like this often require refinement to perfectly capture nuances or might miss specific details. The real power lies in using this structure as a starting point and customizing it for your specific needs and the capabilities of the AI you'll use for recreation.)

Example: Website Analysis Prompt & Profile

Here's a simplified version of the prompt used in the example above and the resulting JSON structure. You can adapt this for analyzing other websites or different types of content. (Remember, AI-generated profiles like the one shown are illustrative and often need refinement; the key is customizing this structure to your needs.)

Your Role: Act as an expert analyst.
Input Source Material: https://sourcetms.com/
Task: Assess this website and create a JSON profile from it. Look at the code, design, brand, style, text, font, imaging, and other perspectives I did not consider. Then, create a JSON profile I can use to provide to another LLM to recreate a website based on the JSON profile of it as a template. Use the structure defined below.
Required JSON Output Structure (Website Profile):
{
  "website_profile": {
    "technical_analysis": {
      "code": {
        "frontend_stack": ["HTML5", "CSS3", "JavaScript"],
        "responsive_breakpoints": ["Mobile: <768px", "Tablet: 768-1024px", "Desktop: >1024px"],
        "performance": {
          "load_time": "~1.2s (estimated)",
          "optimizations": ["Minified assets", "Lazy loading", "Cache headers"]
        },
        "seo": {
          "meta_tags": ["standard Dublin Core", "OpenGraph protocols"],
          "schema_markup": ["Person", "Organization"]
        }
      }
    },
    "design_analysis": {
      "layout": {
        "structure": "Single-page application (SPA)",
        "grid_system": "CSS Grid/Flexbox",
        "whitespace_ratio": "40% content / 60% negative space"
      },
      "typography": {
        "primary_font": "Sans-serif (System UI stack)",
        "font_scale": {
          "h1": "2.5rem",
          "body": "1.1rem",
          "secondary": "0.9rem"
        }
      },
      "color_palette": {
        "primary": ["#2c3e50", "#ffffff"],
        "accent": ["#3498db", "#2980b9"],
        "contrast_ratio": "4.5:1 (WCAG AA compliant)"
      }
    },
    "content_strategy": {
      "messaging": {
        "value_proposition": "Executive leadership in fintech",
        "tone": ["Authoritative", "Concise", "Achievement-focused"]
      },
      "key_content_blocks": [
        {
          "type": "professional_summary",
          "elements": ["Co-founder status", "Sector expertise", "Leadership experience"]
        }
      ]
    },
    "brand_attributes": {
      "visual_identity": {
        "logo_type": "Wordmark (text-only)",
        "imagery_style": ["Corporate headshots", "Abstract tech patterns"]
      },
      "differentiators": ["Finance-tech crossover", "Scalable solutions focus"]
    },
    "interaction_patterns": {
      "navigation": {
        "menu_type": "Anchor-linked SPA",
        "scroll_behavior": "Smooth scrolling"
      },
      "cta_strategy": {
        "primary_cta": "Contact overlay trigger",
        "secondary_cta": "Scroll-based engagement prompts"
      }
    },
    "compliance": {
      "accessibility": ["Basic ARIA labels", "Alt text on images"],
      "privacy": ["GDPR-compliant analytics setup"]
    }
  }
}

More Than Just Copying

Using JSON isn't just about copying things. It's about understanding them better. When you have that structured 'DNA,' you can ask an AI to:

• Analyze: Find strengths or weaknesses.
• Adapt: Change the format (like turning this post into a tweet thread).
• Compare: See how different styles or strategies are similar or different.

Moving beyond simple text prompts to structured JSON like this Content DNA profile grants you significantly more control and unlocks deeper insights when collaborating with AI.

So, the next time you need to distill the essence of a complex idea or style, remember JSON. It's the surprisingly simple key to unlocking more sophisticated and predictable AI generation.

Stay Updated

If you found this guide useful, consider subscribing to the newsletter for more insights on AI, development, and structured prompting. You can also find more about my work on the creator page.