This feature adds an AI matching agent to the Soundmouse Partnerships flow - proposing cue-to-rights matches automatically, but never applying them without review. The core bet: a wrong suggestion needs to be cheap and obvious to correct, since trust in high-stakes data work is earned through a visible, checkable track record, not granted through a permissions toggle switched on once. Confidence indicators, an exception queue for uncertain matches, and visibility into the agent’s own accuracy over time are the pieces that make that possible.
Soundmouse is a cue sheet reporting platform for film and broadcast. The Partnerships feature I designed lets music users share cue sheet data with rights owners automatically, instead of over email. But sharing the data doesn’t solve the next problem: someone still has to match each reported cue to the correct composition and rights holder, by hand, across thousands of rows. This concept asks what happens when an AI agent takes the first pass at that matching - and what it takes to make that trustworthy rather than reckless.

Soundmouse is a cue sheet reporting platform for film and broadcast. Rights owners had no reliable way to see what music users were reporting - that data lived in emails, spreadsheets, and manual reports outside the platform, so both sides spent time chasing information that should have been automatic.
The obvious solution was a share button. Research with both sides pointed somewhere more durable: people didn’t want to re-grant access every time, and they wanted the relationship itself to be visible and manageable, not a one-off action buried in a menu. That shaped the core decision - model this as a persistent partnership with its own lifecycle (Active, Incoming Request, Request Sent, Suspended, Rejected), not a single sharing action.
The trickiest design problem was direction: “Send” and “Receive” describe who sets up the connection, not which way the data actually flows - cue sheets always move from the music user to the rights owner, regardless of who initiated it. Getting that distinction right in the UI, without making users think about it, was most of the work. I also cut the original setup flow from several sparse screens down to two: Setup, then Scope & Confirm.
Results in the first 6 months: 38% of active music-user organizations created at least one partnership, 3,140 partnerships were created, and 62% reached Active status. Manual email and report-sharing dropped by roughly 65%, saving music users an estimated 4–6 hours a month and rights owners 3–5 hours a month previously spent chasing usage data.

Link for the visuals:
https://www.twine.net/signin

An e-commerce concept for a sustainable denim brand, built around a specific tension: sustainability credentials need to be credible, but leading with them can make a product feel like a lecture instead of something desirable.
I surfaced sustainability information on demand - available when a shopper wants to dig in - rather than forcing it into the primary visual hierarchy, so the product photography and craft could still do the work of making someone want the jeans.

Link to the website:
https://www.twine.net/signin

A mobile-first PWA concept for tracking cultivation batches — built for growers working with both mushroom and plant tissue culture, a niche with no existing tool spanning both workflows.
Designed mobile-first since the real use case is standing at a workbench or in the field, not sitting at a desk — large touch targets, quick photo logging over long forms, and offline support built in as a PWA.
The project covered the full design lifecycle in one pass: naming, competitive research, logo, and screen design across twelve core screens.

Link for the visuals:
https://www.twine.net/signin

Scale Cost is a project management tool built for AT Kearney’s PMO function. I have re-designed the workflows and improved the measure creation experience.
Alongside the interface work, I produced a 25-part UX strategy and competitive analysis report, benchmarking against Valuedesk, MSO TRACK, and ServiceNow SPM. One finding shaped the design directly: a data-model mismatch between what gets entered and what gets reported, plus unclear states around which financial fields were calculated versus manually entered — both flagged as real opportunities to differentiate the tool.

Link for the visual:
https://www.twine.net/signin

SoundMouse is a royalty reporting and cue sheet platform for film and broadcast. When the brand team required a font size change from 12pt to 14pt system-wide, with no smaller compromise size available, it broke nearly every dense screen in the product - cue lists, production headers, filters.
I accepted the full 14pt change and redesigned the structure around it instead of fighting for a smaller size. Secondary data moved into tabs and drawers, and actions consolidated into overflow menus, so the product stayed on-brand without becoming harder to use for people scanning dense rights and production data all day.
I worked closely with the business development manager and product owner as the platform changed to support onboarding major clients, including Disney and Sony.

Link for the visuals:
https://www.twine.net/signin