Arity
Building an AI design practice — not just using one
Authoring Cursor user guides, an AI-friendly Figma pattern library, brand-voice skills, and AI onboarding for non-designers across Arity.
- Days → hours Concepting compression AI-assisted design sprints replaced multi-day concepting cycles.
- Non-designers Upskilled into super users Marketing colleagues self-serving on lightweight creative work.
- 1 source Of brand voice truth Tone & voice skill reused by every AI workflow.
TL;DR
- Turned individual Cursor + Figma Make wins into a shared design practice the rest of Arity could plug into.
- Authored the brand voice and tone skill that keeps AI output on-brand across teams.
- Compressed early-stage concepting from days to hours — without sacrificing craft.
The wedge: AI as practice, not party trick
When Cursor and Figma Make first showed up inside Arity, the question wasn’t “is this useful?” — it was obviously useful. The question was: how do we make it useful for the team, not just for the person who happens to be good at prompts?
I treated that question as a UX problem. The “users” were my colleagues. The “product” was an AI design practice — a small set of opinionated tools, guides, and rituals that turned individual productivity into team output.
What I built
Cursor user guides for design and product teams
A practical, opinionated guide to using Cursor inside our workflow — covering prompt patterns, when to reach for Cursor vs. when to stay in Figma, how to integrate AI output with our existing design system, and the failure modes to watch out for.
An AI-friendly Figma pattern library
Most pattern libraries are organized for humans. I architected ours so AI tools could also read it cleanly — consistent naming conventions, tokenized properties, rich annotations, and predictable variant structures. The output quality from AI tooling jumped meaningfully once the library spoke a language the model could parse.
Brand voice + tone skills
I authored tone, voice, and brand-alignment skills (and Cursor rules) so AI-generated copy and design output consistently sound like Arity. One source of truth, called by every workflow that touches user-facing language.
AI onboarding for non-designers
I led cross-functional AI onboarding for marketing colleagues — turning non-designers into capable “super users” of the AI design tools. The goal wasn’t to replace design; it was to free design capacity by letting marketing self-serve on lightweight creative needs.
A repeatable AI-assisted design sprint
I established a sprint format that compresses early-stage concepting from days to hours: a scoped problem, a structured set of prompts, a critique loop, and a clear handoff back into the normal design process.
Outcomes
- Concepting cycles shortened from days to hours, freeing design capacity for higher-order UX strategy
- Marketing teammates now self-serve on lightweight creative work using the patterns and skills I authored
- AI-generated output across the org now reliably reflects Arity’s brand voice — because it’s all calling the same skill
- The pattern-library + skills approach is now part of how new tools get evaluated inside the design org
Reflection
The biggest mistake I see other teams make with AI design tooling is treating it as personal productivity. The leverage isn’t there. The leverage is in shared infrastructure — a pattern library AI can read, a brand voice it can call, a sprint format that integrates cleanly with the human work.
That’s what this case is really about: turning a clever tool into something the whole team can stand on.
Want to dig deeper?
The dedicated AI design practice page goes into the actual artifacts — sample skills, prompt patterns, and the pattern-library annotations. Take a look if you want to see what this looks like in the wild.