Process Guide

Design Playbook

AI can build fast, but without clear design intent it will converge on safe, generic outcomes. This playbook shows how to give AI the right inputs — at the right time — to produce distinctive, high-quality design without slowing delivery.

When to use this playbook

At the start of a new Catalyst project
Mid-project when design feels generic
When stakeholders say “it looks like everything else”
Before advancing to a more polished stage

Core Principle

AI amplifies taste. It doesn't invent it.

When you give AI vague instructions, it defaults to “average” aesthetics — the statistical mean of everything it has seen. This produces competent but undifferentiated designs.

Strong design requires declared taste: specific references, precise language, and intentional constraints. Give AI clear inputs and it will amplify them. Give it nothing and it will give you nothing distinctive in return.

References

Real examples that show what “good” looks like for this project

Language

Precise vocabulary that names what you want, not vague descriptions

Constraints

Boundaries that focus AI on specific choices, not infinite options

Catalyst note

This playbook exists to replace slow, speculative design work — not to add more steps. It trades heavy mood boards, early Figma rounds, and long design cycles for fast, focused inputs that make AI output distinctive from the start.

Stage-Aware Guidance

These steps scale with your project stage. A POC doesn't need production-level design polish, but it still benefits from clear intent. Add rigour as you advance.

StageDesign ExpectationRecommended Steps
POCClear hero, consistent tone, credibilitySteps 1–4
MVPCoherent system, repeatable patternsSteps 1–6
MMPPolished flows, brand alignmentSteps 1–7
PRODFull system consistency, accessibility, performanceAll steps + iteration

The Playbook

Seven recommended steps for getting distinctive design from AI. Click each step to expand.

1

Design Intent

Prevent generic output by explicitly declaring intent before writing code

Before starting a Catalyst build, capture four things that will anchor AI toward distinctive output.

1

Real-world reference

A production site or app that's realistic and credible. Something actually shipped, not a concept.

2

Aspirational reference

A “concept car” reference. May be more expressive or experimental than what you'll actually build.

3

Declared vibe

3–5 adjectives that describe the feeling you're aiming for.

“technical and restrained”“editorial and expressive”“enterprise calm”
4

Audience signal

Who must this design convince? Different audiences need different visual signals.

foundersoperatorsexecutivesconsumers

Output

A short design intent note. This can live in chat context, a project doc, or a markdown file in your repo. Keep it concise — 4–6 sentences is enough.

Common mistake

Skipping this step and planning to “fix design later” is the most common source of generic AI output. By the time you realise the design is bland, you've already built significant code around those patterns.

How to Use This Playbook

Early POC

Focus on Steps 1–4. Capture intent, inject visual context, and get the hero right. Skip the later steps until you need them.

MVP / MMP

Add Steps 5–7. Structure your sections, iterate surgically, and extract style tokens to prevent drift across multiple surfaces.

Mid-Project Fix

Apply this playbook retroactively if design feels generic. Start with Step 1 (intent) even if you've already built. It's never too late to redirect.

Catalyst note

These steps are recommendations, not gates. Use what helps, skip what doesn't apply. The goal is distinctive design, not process compliance.

Common Failure Modes

Patterns that consistently lead to generic or weak design outcomes.

No references

Starting with no visual grounding, expecting AI to invent a distinctive style

Text-only prompts

Describing design in words when a screenshot would be 10x more effective

Full regeneration loops

Re-generating entire pages when one element is wrong, losing good decisions

Skipping the hero

Trying to design everything at once instead of nailing the visual anchor first

Polish at the end

Treating design as a final coat of paint rather than a foundational input

Vague direction

'Make it look modern' instead of specific vocabulary and concrete references

How This Fits Catalyst

This playbook replaces slow, speculative design work. Instead of mood boards, Figma rounds, and long design debates, you give AI focused inputs upfront and let it amplify your declared taste.

The result: distinctive design at Catalyst speed. You keep the proof-led delivery model, stakeholders still see real software fast, and the output looks like it belongs to your project — not a template.

Next Steps