MOOOO.

JSON Prompting Power

AI TOOLS

JSON Prompting Power
JSON Prompting Power, slide 2 of 7
JSON Prompting Power, slide 3 of 7
JSON Prompting Power, slide 4 of 7
JSON Prompting Power, slide 5 of 7
JSON Prompting Power, slide 6 of 7
JSON Prompting Power, slide 7 of 7

Structure your AI prompts like a design system - modular, predictable, and easy to iterate.

Most prompts are written as long, messy sentences that confuse the AI. JSON fixes this by breaking your idea into structured fields - just like components in a design system. The result is prompts that are easier to edit, more consistent, and far more predictable in their output.

Why JSON

Instead of writing one long sentence, you separate each intention into its own field. Change one thing at a time without rewriting everything. It mirrors how designers think - in layers, not paragraphs.

Keep It Modular

Take a prompt like "A cinematic shot of a young designer giving a talk on stage with warm lighting in a conference hall" and break it into separate fields: Shot, Action, Lighting, Background. Modular prompts mean faster edits, reusable pieces, and more control - just like swapping components in Figma.

The 8 Core Fields

Shot defines the frame type (Close-Up, Wide). Action describes what happens (Running, Presenting). Lighting sets the light setup (Soft Glow, Dramatic). Background is the scene setting (Office, Stage). Camera covers lens and angle (35mm, Top View). Style is the art direction (Pixar, Minimal). Mood sets the emotional tone (Dreamy, Cinematic). Character specifies who is in the scene (Designer, Child).

Example JSON Prompt

Start with shot, action, mood, character, camera, style, lighting, and background. Change one field at a time to create entirely new versions - just like tweaking tokens in a design system. The output becomes predictable, repeatable, and easy to share with your team.

Pro Trick - Extend Your Fields

Once you have the basics, go further. Add fields like textures, composition, and color_theme to unlock even more precision. The more specific your fields, the more on-brand and consistent your results.

More articles

  • Seed Numbers in AI Prompts

    Seed numbers are the secret to consistent AI-generated content - understand them and you unlock reproducible creativity.

  • AI-Powered UX Writing

    Create better microcopy faster with AI - learn how to draft, iterate, and localise UX copy without slowing down your design process.

  • 5 Figma Plugins, Part 1

    Five AI-powered Figma plugins that supercharge your workflow so you can design smarter, not harder.

  • Measuring UX Like a Pro

    Great UX is not a lucky guess - it is a science backed by numbers. Here are 6 powerful metrics every designer and product team should track.

  • From Figma to Notion by n8n

    How I used n8n to automatically turn every Figma comment into a Notion task - no copy-paste, no coding, no lost feedback.

  • Meet Nano Banana

    Google's Gemini 2.5 Flash model lets you edit photos step by step while keeping faces consistent and results realistic.

  • 5 Figma Plugins, Part 2

    Five Figma plugins that save hours every week, each one solving a specific pain point that slows down design work.

  • AI in UX Research

    How I use AI to move faster, think deeper, and focus more on people rather than paperwork across every stage of UX research.