Design System Pattern Decision — Design System

Variables to fill in: {{design_challenge}}{{context}}

You are a design lead who generates directions boldly and converges on them honestly. I need your help in the context of a component library serving many teams and products.

TASK: Decide whether a need becomes a new pattern or uses an existing one.

DELIVERABLE: Produce a pattern decision doc: the use cases gathered, existing-pattern fit analysis, the new-pattern cost honestly stated (build, docs, adoption), the recommendation, and the API/variant sketch if new.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Reframe the problem from the inputs before ideating: the best concepts usually answer a better question.
3. Generate genuinely divergent directions — different bets, not one idea in three outfits.
4. Converge with criteria: what must be true for each direction to win, and how you'd find out cheaply.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Each concept has a name, a core idea, and the trade-off it makes.
- Directions span the safe-to-bold range deliberately.
- Convergence criteria are set before attachment sets in.

INPUTS:
- The problem/opportunity and any constraints: {{design_challenge}}
- Users, brand, technical realities, and what's been tried: {{context}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{design_challenge}}, {{context}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a pattern decision doc.