Design

Modularizing AI design workflows into step-specific skills

AI is organized into separate skills for requirements, research, user stories, information architecture, wireframes, validation, UX copy, prototyping, and Figma handoff so each stage of the design process can be run, improved, and debugged independently instead of relying on one giant prompt.

Why the human is still essential here

The designer reviews each checkpoint before the next step begins, keeping judgment, approvals, and design decisions in human hands while AI handles bounded execution.

How people use this

Requirements intake skill

AI turns kickoff notes and stakeholder messages into a structured requirements brief that the designer can approve before research begins.

ChatGPT / Claude

User story drafting skill

After requirements are approved, AI generates prioritized user stories and edge cases as a separate step instead of bundling them into one giant design prompt.

Claude / Notion AI

Figma handoff skill

At the end of the workflow, AI produces organized handoff notes, component specs, and implementation cues inside the design file without touching earlier steps.

Figma AI / ChatGPT

Need Help Implementing AI in Your Organization?

I help companies navigate AI adoption -- from strategy to production. Whether you are building your first LLM-powered feature or scaling an agentic system, I can help you get it right.

LLM Orchestration

Design and build LLM-powered products and agentic systems

AI Strategy

Go from idea to production with a clear implementation roadmap

Compliance & Safety

Build AI with human-in-the-loop in regulated environments

Related Prompts (4)

Latest community stories (1)

Personal Story
Blog

I turned my design process into a dozen small skills, not one giant prompt

The first version of my design workflow was one enormous prompt. Thousands of words describing every step of how we design. I was pretty proud of it. It held together for about three steps and then quietly fell apart.

Not with an error. It failed the way a big prompt always does. The model lost the thread halfway down, blended two steps into one, skipped the one in the middle, and handed me something that looked like process but wasn't. And I couldn't fix it, because touching one part broke three others. One block of text, no seams.


The deeper problem was worse than maintenance. A single prompt gave the AI nowhere to stop. It ran from requirements straight to a prototype in one breath, sailing past every point where a human should have said "wait." It was automating the exact thing I'd promised to keep human.


Think of it as a team, not a prompt


The fix was to stop treating it as a prompt and start treating it as a team. A team isn't one person holding the whole job in their head. It's small roles with clear handoffs, and a check before the next person picks it up.

PS
Prateek SinghSenior Product Designer
Aug 7, 2026