Sift Chrome Extension

Introducing intentional friction to the online checkout experience

TOOLS

Figma

Claude + Figma MCP

TIMELINE

Spring 2026

2 months

ROLE

Product Designer

TEAM

Just me!

TOOLS

Figma

Claude + Figma MCP

TIMELINE

Spring 2026

2 months

CONTEXT

It started with a closet I couldn't stand to look at.

Four years ago, mid-lockdown, I stared at a closet full of clothes I no longer liked. I upcycled what I could, donated the rest, and felt immense relief.

92 million tonnes of textile waste are produced globally every year. 85% of it ends up in landfills.

The scale is enormous. The root of it is personal. That's where I started.

PROBLEM

Why do we keep buying things we don't need?

I reviewed existing research on purchase habits and the behvioral patterns associated with it. Then I ran a netnography: probes on online forums, responses collected, and a few participants interviewedโ†“

(Click to zoom in on artifacts)

Key findings from initial research:

๐Ÿ” The cost isn't just money, it's space: closets overflow and half goes unworn.

๐Ÿ” People aren't unaware, they're outwilled: the urge beats the regret in the moment.

๐Ÿ” Impulse buying is designed, not a personal flaw, people are up against good design.

๐Ÿ” It's a loop, and regret is part of it, not a way out.

๐Ÿ” Online shoppers already pause before their purchase.

TARGET AUDIENCE

Who is Sift for anyway?

CURRENT LANDSCAPE

Two tools had taken on the same problem, each solving part of it.

I spent time looking at existing tools that help people buy less:

(Click to zoom in on artifact)

โ†’ The Impulse Judge makes you type out a roast before checkout. I tested it with past interviewees, the humor wore thin fast, and it read as a novelty more than a habit.

โ†’ Think Twice, Buy Once is a mobile app that asks you to wait before buying and tracks the money you save. Without a contextual pop-up, you have to manually enter every item you're considering.

Neither covered: the moment (checkout, in context) and the experience (warm, non-judgmental, designed with care).

CONCEPT TESTING

To test my hunches, I went analog.

"What would a good friend say to someone about to impulse buy? One who cares enough to ask, but never guilts you about the answer."

I turned the sentiment above, into three lenses: money ยท space ยท need

I printed them as card packets and gave them to about 70 people, to use whenever they shopped. I wanted real stakes, during an actual online shopping session, (instead of simulating the experience) which is why I chose this route.

22 people wrote back. About 45% still bought the thing, but all of them paused, and all said they'd cherish the item more for it. Those responses sharpened the copy, tuned the tone, and gave me the confidence to start building.

THE PRODUCT

So, what is Sift?

Sift is a Chrome extension that intercepts the checkout button and fans out a deck of playing-card prompts before you buy.

^ Design note: The card metaphor and visuals came straight from the physical kit!

DESIGNS

How Sift works, and what makes Sift, Sift.

(1/4)

Pick your pillars. Choose which are active, change them mid-session, and skip at any time. It hands agency back to the shopper instead of taking it away.

(2/4)

โ†’ Reflect as much or as little as you want. Toggle between the deck and a laid-out view that shows every reflection at once. The laid-out view came from testing: people couldn't see all their notes at once, so I let them spread the deck flat.

(3/4)

โ†’ The reflections don't disappear. Saved ones land in a history page: which pillars you weighed, what you told yourself.

(4/4)

โ†’ Every exit assumes the best of you, that you mean to cherish what you buy.

(1/4)

Pick your pillars. Choose which are active, change them mid-session, and skip at any time. It hands agency back to the shopper instead of taking it away.

(2/4)

โ†’ Reflect as much or as little as you want. Toggle between the deck and a laid-out view that shows every reflection at once. The laid-out view came from testing: people couldn't see all their notes at once, so I let them spread the deck flat.

(3/4)

โ†’ The reflections don't disappear. Saved ones land in a history page: which pillars you weighed, what you told yourself.

(4/4)

โ†’ Every exit assumes the best of you, that you mean to cherish what you buy.

APPROACH

Making a pause feel grounded and integrated.

I designed everything in figma first, and kept things simple with warm colours and soft accents to reflecting the grounding experience of stopping and reflecting.

Then I moved to Claude code to prototype the designs.

POTENTIAL IMPACT

What one pause can add up to.

A pause becomes a deliberate choice. Choices become a habit. The habit becomes a wardrobe you actually wear, and enough of those, across enough people, chip at the cycle that fills landfills.

NEXT STEPS

Prototype to production.

Next is shipping this as a real extension. The concept is tested and the prototype works end to end; production is what I'm in now. I'm not a coder, so I'm working through how to run Sift cleanly on real retailer sites, and how to keep people's reflections safe.

Further out, I want to bring Sift to mobile, where targeted ads really do their work. That's harder: apps can't overlay each other the way an extension sits on a webpage, so I'd keep the heart of it and rethink the form.

Either way, I'm glad to be starting from a tested concept that actually moves behavior.

REFLECTIONS

On designing friction.

Everything I know about checkout flows is about removing friction. This one asked me to add it, and to add it kindly. Getting the tone right was hard, but it felt like a real service to people who already see their patterns and just need help moving past them. A small push back against a very large machine, and small push backs, at scale, add up.

On building with AI

Working with Claude Code and Figma MCP moved my job toward judgment. When a motion felt too abrupt, I could adjust it in minutes. Deciding what felt calm, what felt like Sift, stayed mine. I intend to keep exploring creative prototyping using tools like these.

NEXT STEPS

Prototype to production.

Next is shipping this as a publicly-available extension. The concept is tested and the prototype works end to end. I'm not a coder, so I'm working through how to run Sift cleanly on real retailer sites, and how to keep people's reflections safe.

Further out, I want to bring Sift to mobile, where targeted ads really do their work. Apps can't overlay each other the way an extension sits on a webpage, so I'll have to completely rethink the form and flows.

Either way, I'm glad to be starting from a tested concept that shifts behavior.

Navigate case studies

Navigate case studies

Navigate case studies

Thank you for visiting <3

Feel free to reach out!

Thank you for visiting <3

Feel free to reach out!

Thank you for visiting <3

Feel free to reach out!

BASED IN CHICAGO,IL

CONNECT

CONNECT

CONNECT

PAGES

PAGES

PAGES