AI in my work

A traditional designer with deep AI experience.

AI has changed how I do design work. I'm trained in the craft, with a career in it since 2004, and I now pair that with Claude every day: more options up front, faster iteration, and working front-end code as part of design review. It has made me much faster.

Skills shown AI-accelerated design Prompt fuel Figma ↔ Claude Front-end prototypes Prompt-based apps Claude ChatGPT MCP development AI product design
My AI-accelerated workflow

From a sentence to approved, working front end.

The craft decisions stay mine. Claude handles the volume and the busywork, so I spend my time judging and refining instead of pushing pixels.

1
Start with prompt fuel

My term for feeding the model my own designs and skills: an established design system, existing UI layouts, and my WWMD review skill. Better fuel means a better first round.

2
More options out of the gate

I ask for several directions up front instead of committing early. A wider range means better decisions and fewer late surprises.

3
Tweak in Figma, digest back into Claude

I refine by hand in Figma, then feed the changes back to Claude so the next pass builds on my decisions.

4
Review in working front-end code

Review happens in a running front end, not a static mockup. Stakeholders click through real behavior, and approved code hands off to engineering right away.

5
Ship sooner

Strong first rounds cut time to development and to market.

Why it works
AI multiplies a designer's judgment. It doesn't replace it.

I came up through traditional design, and that foundation is what makes the AI output good. I know what a strong layout looks like, which option to cut, and when something is almost right. The tools add the speed. The taste behind them has been building since 2004.

Faster
Design production with Claude in my workflow, without lowering the craft
How I use it

The tools behind the workflow.

01 · Prototype
I prototype in my design system

I've taught Claude the design system I built for MNTN Select, so it can turn a screen, flow or idea into a working HTML prototype that looks and behaves like the real product. Stakeholders can click through the UX themselves instead of imagining it from static frames.

It extends how I've always worked: I'm a big fan of proof of concept.

Try one: the Budget & Goal prototype ↗
02 · Connect
I connect Claude to Figma through MCP

With the Figma MCP, Claude reads my designs and components directly and can write back into the file, so design context doesn't get lost in screenshots and copy-paste. I use MCPs, the Model Context Protocol servers that connect an assistant to the tools a team already uses, across my whole workflow.

03 · Review
I review builds against my designs

I've captured my design taste as a review skill I call WWMD (What Would Matt Do). Give it engineer screenshots and the Figma designs, and Claude lists everything that doesn't match, judged against the design system and my own rules. QA gets faster and more consistent, and I spend my time on the judgment calls.

04 · Hand off
I turn design changes into Jira tickets

Figma comments and annotated screenshots become clear, well-formed Jira tickets for engineering. Claude drafts, I approve, and it files them through the Atlassian connector. Fewer vague handoffs, fewer rounds of clarification.

I also build prompt-based apps and use ChatGPT alongside Claude. Details are available in conversation.

AI work

See it in the work.

AI products I designed, and projects made faster with my AI workflow.

FlightPlan on a laptop, showing the chat and the suggested purchase
AI product · MNTN Select
FlightPlan

A prompt-based assistant that turns a campaign description into a media plan. Designed in about a week, built in about a month.

Read the case study →
The FlightPlan chat beside a plan panel that lists what it still needs
Design review · MNTN Select
Flight Plan empty state

Five concepts, each a working prototype built with Claude, reviewed against acceptance criteria before the team picked one.

See the design review →
A whiteboard showing the UX workflow
Team and process · MNTN
Product Design Workflow

The team workflow, now with AI in it: designs and the design system as prompt fuel, and front-end code as the review step.

Read the project →
MNTN campaign report with KPI cards, an impressions chart, and recommendations to accept or decline
Product UI · MNTN
MNTN product design

Reporting, monitoring and creative tools. Recent work starts from our design system as prompt fuel for strong first rounds.

See the work →
Try the working prototypes

Front-end prototypes built with Claude from the Select design system. This is what stakeholders click through in review.

FlightPlan
The working mock

Switch between grid and list, expand a deal, and flip between light and dark.

Open the prototype ↗
Flight Plan empty state
Five concepts, one prototype

Mark Content, Demographic, Budget and Timing as learned, in any order, and watch each concept respond.

Open the prototype ↗
Budget & Goal
The campaign setup prototype

Add a budget, pick a goal, and switch to the empty and blocked states from the settings icon.

Open the prototype ↗
See every AI skill, each linked to the work →
AI in the product

Where AI belongs in a product.

Use it where it adds clear value

AI earns its place when it removes real work, not when it's added for its own sake.

Protect trust

Be careful not to compromise trust or feel intrusive, especially when a product asks for people's data.

Do the work for the user

The best use is quiet: collect what can be collected automatically so people do less and get to value faster.

The MNTN welcome screen on a laptop
Case study · MNTN
AI-Assisted Onboarding

Only 15% of users finished onboarding. I moved billing to a higher-intent moment and used AI to gather site and company details automatically.

Read the case study →

More broadly, I've led 0→1 work at MNTN that includes AI-powered features that improved campaign workflows and surfaced actionable insights. My MNTN Select case study includes AI-assisted media planning.

Read the MNTN Select case study →
Leading a team with AI
I lead by example. I learn the tools hands-on, and I encourage my team to keep learning too.

The design landscape keeps changing. I stay current through continuous learning and build a culture where trying new tools carefully is part of the job.

Talk with me about AI and design
© Matthew Cassella · Northport, NY
LinkedIn